{"object": "list", "data": [{"id": "assistant", "object": "model", "created": 1694610718936, "description": "General-purpose assistant. Write, code, ask for real-time information, create images, and more.\n\nQueries are automatically routed based on the task and subscription status.\n\nFor subscribers:\n- General queries: @GPT-5.2-Instant\n- Image generation: @Nano-Banana\n- Video-input tasks: @Gemini-3.1-Pro\n\nFor non-subscribers:\n- General queries: @GPT-5.4-Nano\n- Image generation: @Flux-1-Schnell-FW / @FLUX-schnell\n- Video-input tasks: @Gemini-3-Flash\n", "owned_by": "Poe", "root": "assistant", "architecture": {"input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "modality": "text,image,video->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": null, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "Assistant", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3002-200-vcmrcgoloaktppabmdfsgeczaixswmxt.jpeg", "alt": "Assistant model icon", "width": 200, "height": 200}, "url": "https://poe.com/assistant"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": []}, {"id": "claude-opus-4.7", "object": "model", "created": 1776230250028, "description": "Anthropic\u2019s flagship model for enterprise-grade knowledge work. Powered by an Extended Thinking Mode and an optimized Model Context Protocol (MCP), Opus 4.7 excels at multi-agent coordination, complex coding, and long-running autonomous tasks. It leverages a massive 1M-token context window to seamlessly execute intricate workflows with elite reasoning, safety, and reliability.\n\nThis bot supports optional parameters for advanced customization.", "owned_by": "Anthropic", "root": "claude-opus-4.7", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/messages", "/v1/responses", "/v1/chat/completions"], "pricing": {"prompt": "0.0000042929", "completion": "0.0000214646", "image": null, "request": null, "input_cache_read": "0.0000004293", "input_cache_write": "0.0000053662"}, "context_window": {"context_length": 1048576, "max_output_tokens": 128000}, "context_length": 1048576, "metadata": {"display_name": "Claude-Opus-4.7", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-1043-200-xkuecwwdwkvsxgdvunqzllrnozmhaodl.jpeg", "alt": "Claude-Opus-4.7 model icon", "width": 200, "height": 200}, "url": "https://poe.com/claude-opus-4.7"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": false}, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}, {"name": "output_effort", "schema": {"enum": ["max", "xhigh", "high", "medium", "low", "none"]}, "default_value": "high"}, {"name": "thinking_display", "schema": {"enum": ["omitted", "summarized"]}, "default_value": "omitted"}, {"name": "task_budget", "schema": {"type": "number", "minimum": 20000, "maximum": 1048576}, "default_value": 128000, "description": "Advisory token budget for agentic turns. The model will attempt to stay within budget."}]}, {"id": "nano-banana-2", "object": "model", "created": 1772107200000, "description": "Google's latest image model combines Pro-level intelligence with lightning-fast generation. It features advanced world knowledge, precise text rendering, strong subject consistency, and 4K production-ready outputs.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Google", "root": "nano-banana-2", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": ["/v1/images", "/v1/responses"], "pricing": {"prompt": "0.0000005051", "completion": "0.0000030303", "image": "0.0000606061", "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 65536, "max_output_tokens": null}, "context_length": 65536, "metadata": {"display_name": "Nano-Banana-2", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6818286-200-plmqoxsqehcxarfvcyuxtsgscphxibii.jpeg", "alt": "Nano-Banana-2 model icon", "width": 200, "height": 200}, "url": "https://poe.com/nano-banana-2"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9"]}}, {"name": "image_only", "schema": {"type": "boolean"}, "default_value": false, "description": "The model defaults to returning text and images. Turn on to only return images."}, {"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}, {"name": "image_size", "schema": {"enum": ["1K", "2K", "4K"]}}]}, {"id": "gpt-image-2", "object": "model", "created": 1776802127647, "description": "OpenAI\u2019s state-of-the-art image generation model as of April 21, 2026, designed for fast, high-quality image generation and editing with strong prompt adherence and flexible image sizes. It supports generating, editing, restyling, and combining images attached to the latest user query.\n\nOptional Parameters:\n\nSet aspect ratio, with options 3:2, 1:1, and 2:3.\nSet quality to low, medium, and high.\nEnable use mask by toggling it on or by typing use_mask in the prompt. This option is turned off by default.", "owned_by": "OpenAI", "root": "gpt-image-2", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": "0.0000050505", "completion": "0.0000323232", "image": null, "request": null, "input_cache_read": "0.0000012626", "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "GPT-Image-2", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6952099-200-txbyqqgorneealaprxalydadyvxptcfh.jpeg", "alt": "GPT-Image-2 model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-image-2"}, "reasoning": null, "parameters": [{"name": "size", "schema": {"enum": ["auto", "1024x1024", "1536x1024", "1024x1536"]}, "default_value": "auto"}, {"name": "quality", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "high"}, {"name": "use_mask", "schema": {"type": "boolean"}, "default_value": false, "description": "Indicates that the last attached image is a mask for inpainting (editing specific regions). The mask must match the dimensions of the base image, with transparent (zero-alpha) areas showing which parts to edit. Only takes effect when an image is attached."}]}, {"id": "gpt-5.5", "object": "model", "created": 1775666019094, "description": "GPT-5.5 is OpenAI's smartest and most intuitive model, built for agentic coding, computer use, knowledge work, and early scientific research. It handles complex multi-step tasks with less guidance, figures out what needs to happen next on unclear problems, and matches GPT-5.4 per-token latency while delivering a much higher level of intelligence. Achieves state-of-the-art accuracy on Terminal-Bench 2.0 and SWE-Bench Pro, solving more tasks end-to-end in a single pass than previous models. Supports 400k tokens of input context and native vision.", "owned_by": "OpenAI", "root": "gpt-5.5", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text", "image"], "modality": "text,image->text,image"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000045455", "completion": "0.0000272727", "image": null, "request": null, "input_cache_read": "0.0000004545", "input_cache_write": null}, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "GPT-5.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3065-200-oacxisvffbnadtxpgprhqocxnshbvlso.jpeg", "alt": "GPT-5.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5.5"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": true, "description": "Enable web search and real-time information access."}, {"name": "reasoning_effort", "schema": {"enum": ["none", "low", "medium", "high", "xhigh"]}, "default_value": "none"}, {"name": "verbosity", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "gpt-5.5-pro", "object": "model", "created": 1775666099817, "description": "A smarter, more precise version of GPT-5.5 that leverages additional compute to think harder and provide consistently better answers. Designed to tackle your toughest problems, this model operates with the highest reasoning capability to ensure maximum accuracy on complex agentic, coding, and research tasks.", "owned_by": "OpenAI", "root": "gpt-5.5-pro", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text", "image"], "modality": "text,image->text,image"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000272727", "completion": "0.0001636364", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "GPT-5.5-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3066-200-avdqrhoryvdezhaiohushrvdhxhaakkz.jpeg", "alt": "GPT-5.5-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5.5-pro"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": true, "description": "Enable web search and real-time information access."}, {"name": "reasoning_effort", "schema": {"enum": ["medium", "high", "xhigh"]}, "default_value": "medium"}, {"name": "verbosity", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "gpt-5.4", "object": "model", "created": 1772143119942, "description": "GPT-5.4 is the most capable AI model from OpenAI, built for advanced real-world tasks across coding, computer use, deep research, complex document understanding, and multi-step problem solving. It outperforms previous versions on agentic workflows and tool use, delivering stronger reasoning, higher accuracy, and more reliable results on complex tasks.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "OpenAI", "root": "gpt-5.4", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text", "image"], "modality": "text,image->text,image"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000022727", "completion": "0.0000136364", "image": null, "request": null, "input_cache_read": "0.0000002273", "input_cache_write": null}, "context_window": {"context_length": 1050000, "max_output_tokens": 128000}, "context_length": 1050000, "metadata": {"display_name": "GPT-5.4", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3059-200-ftfdcmjibjzhyaworsxmtkykumwdemnw.jpeg", "alt": "GPT-5.4 model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5.4"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}, {"name": "reasoning_effort", "schema": {"enum": ["none", "low", "medium", "high", "xhigh"]}, "default_value": "none"}, {"name": "verbosity", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "gpt-5.4-nano", "object": "model", "created": 1773272021193, "description": "GPT\u20115.4 Nano is the fastest and most cost\u2011efficient model in the GPT\u20115 family, built for high\u2011volume tasks such as summarization, categorization, extraction, and lightweight multimodal workflows. It supports native vision and a 400k\u2011token context window for efficient large\u2011scale processing.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "OpenAI", "root": "gpt-5.4-nano", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text", "image"], "modality": "text,image->text,image"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000001818", "completion": "0.0000011364", "image": null, "request": null, "input_cache_read": "0.0000000182", "input_cache_write": null}, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "GPT-5.4-Nano", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3064-200-jjrjbaldtpsxqapxmifgyxtvcwvitkdq.jpeg", "alt": "GPT-5.4-Nano model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5.4-nano"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}, {"name": "reasoning_effort", "schema": {"enum": ["none", "low", "medium", "high", "xhigh"]}, "default_value": "none"}, {"name": "verbosity", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "gpt-5.4-mini", "object": "model", "created": 1773276546626, "description": "GPT\u20115.4 Mini is a fast, affordable general\u2011purpose model designed for production assistants, coding support, document analysis, and multimodal reasoning. With a 400k\u2011token context window, it handles complex inputs and scalable workflows with strong reliability. \n\nThis bot supports optional parameters for additional customization.", "owned_by": "OpenAI", "root": "gpt-5.4-mini", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text", "image"], "modality": "text,image->text,image"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000006818", "completion": "0.0000040909", "image": null, "request": null, "input_cache_read": "0.0000000682", "input_cache_write": null}, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "GPT-5.4-Mini", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3063-200-xmakbmbxmoyhxrapobefciakgzdpocuw.jpeg", "alt": "GPT-5.4-Mini model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5.4-mini"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}, {"name": "reasoning_effort", "schema": {"enum": ["none", "low", "medium", "high", "xhigh"]}, "default_value": "none"}, {"name": "verbosity", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "gemini-3.1-pro", "object": "model", "created": 1771460884211, "description": "Gemini 3.1 Pro is a state-of-the-art model for complex problem-solving, advanced reasoning, creative coding, and ambitious agentic workflows, delivering top benchmark results including a verified score of 77.1% on the ARC-AGI-2 benchmark (more than double the reasoning performance of Gemini 3 Pro).\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Google", "root": "gemini-3.1-pro", "architecture": {"input_modalities": ["text", "image", "video", "audio"], "output_modalities": ["text"], "modality": "text,image,video,audio->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000020202", "completion": "0.0000121212", "image": null, "request": null, "input_cache_read": "0.000000202", "input_cache_write": null}, "context_window": {"context_length": 1048576, "max_output_tokens": 65536}, "context_length": 1048576, "metadata": {"display_name": "Gemini-3.1-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6029-200-wpcheprrnbiehsmmhqlcsdwnjvxfqppq.jpeg", "alt": "Gemini-3.1-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/gemini-3.1-pro"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "thinking_level", "schema": {"enum": ["low", "high"]}, "default_value": "low"}, {"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "script-bot-creator", "object": "model", "created": 1759738360550, "description": "Specializes in building workflows that combine bots on Poe. Powered by Claude Code. Guide and tips: https://creator.poe.com/docs/script-bots/quick-start\n\nNote: Script-Bot-Creator cannot access messages sent to or from other bots.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Poe Tools", "root": "script-bot-creator", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Script-Bot-Creator", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6477437-200-gkfmvjyqszpvtqarbskdttwyimhmyqwj.jpeg", "alt": "Script-Bot-Creator model icon", "width": 200, "height": 200}, "url": "https://poe.com/script-bot-creator"}, "reasoning": null, "parameters": [{"name": "model", "schema": {"enum": ["claude-sonnet-4-5", "claude-opus-4-6", "claude-opus-4-7", "claude-haiku-4-5"]}, "default_value": "claude-opus-4-6", "description": "Select the Claude model to use."}, {"name": "thinking_budget", "schema": {"type": "number", "minimum": 0, "maximum": 31999}, "default_value": 4096, "description": "The maximum number of tokens to spend on thinking."}, {"name": "effort", "schema": {"enum": ["max", "high", "medium", "low", "none", "xhigh"]}, "default_value": "high"}, {"name": "thinking_display", "schema": {"enum": ["omitted", "summarized"]}, "default_value": "omitted"}, {"name": "task_budget", "schema": {"type": "number", "minimum": 20000, "maximum": 1048576}, "default_value": 128000, "description": "Advisory token budget for agentic turns. The model will attempt to stay within budget."}]}, {"id": "canvas-creator", "object": "model", "created": 1758612381235, "description": "Specializes in building interactive web applications designed for publishing as apps on Poe. Powered by Claude Code.\n\nSee what's new: https://creator.poe.com/changelog?tag=canvas-apps\n\nNote: Canvas-Creator cannot access messages sent to or from other bots.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Poe Tools", "root": "canvas-creator", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Canvas-Creator", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6443209-200-gzcekhhdszpsqdvzjyioaceskumtzmqp.jpeg", "alt": "Canvas-Creator model icon", "width": 200, "height": 200}, "url": "https://poe.com/canvas-creator"}, "reasoning": null, "parameters": [{"name": "model", "schema": {"enum": ["claude-sonnet-4-5", "claude-opus-4-6", "claude-opus-4-7", "claude-haiku-4-5"]}, "default_value": "claude-opus-4-6", "description": "Select the Claude model to use."}, {"name": "thinking_budget", "schema": {"type": "number", "minimum": 0, "maximum": 31999}, "default_value": 4096, "description": "The maximum number of tokens to spend on thinking."}, {"name": "effort", "schema": {"enum": ["max", "high", "medium", "low", "none", "xhigh"]}, "default_value": "high"}, {"name": "thinking_display", "schema": {"enum": ["omitted", "summarized"]}, "default_value": "omitted"}, {"name": "task_budget", "schema": {"type": "number", "minimum": 20000, "maximum": 1048576}, "default_value": 128000, "description": "Advisory token budget for agentic turns. The model will attempt to stay within budget."}]}, {"id": "gpt-5.4-pro", "object": "model", "created": 1772735432534, "description": "A smarter, more precise version of GPT-5.4 that leverages additional compute to think harder and provide consistently better answers. Designed to tackle your toughest problems, this model operates with the highest reasoning capability to ensure maximum accuracy on complex tasks.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "OpenAI", "root": "gpt-5.4-pro", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text", "image"], "modality": "text,image->text,image"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000272727", "completion": "0.0001636364", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 1050000, "max_output_tokens": 128000}, "context_length": 1050000, "metadata": {"display_name": "GPT-5.4-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3062-200-xkeutmibkvqgfuvcprpuivgjohdgesee.jpeg", "alt": "GPT-5.4-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5.4-pro"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}, {"name": "reasoning_effort", "schema": {"enum": ["medium", "high", "xhigh"]}, "default_value": "medium"}, {"name": "verbosity", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "gemini-3.1-flash-lite", "object": "model", "created": 1771380296910, "description": "Gemini 3.1 Flash Lite Preview is the fastest and cheapest model in the Gemini 3.1 family. It provides multimodal understanding and intelligence similar to or better than Gemini 2.5 Flash at a low price that makes it perfect for high volume workloads. Supports 1M tokens of context\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Google", "root": "gemini-3.1-flash-lite", "architecture": {"input_modalities": ["text", "image", "video", "audio"], "output_modalities": ["text"], "modality": "text,image,video,audio->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000002525", "completion": "0.0000015152", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 1048576, "max_output_tokens": 65536}, "context_length": 1048576, "metadata": {"display_name": "Gemini-3.1-Flash-Lite", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6028-200-rhcmndoxcnwipsnazrdezbpsjvoggkzg.jpeg", "alt": "Gemini-3.1-Flash-Lite model icon", "width": 200, "height": 200}, "url": "https://poe.com/gemini-3.1-flash-lite"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "thinking_level", "schema": {"enum": ["minimal", "low", "high"]}, "default_value": "low"}, {"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "gpt-5.3-codex", "object": "model", "created": 1770761529560, "description": "GPT\u20115.3\u2011Codex excels in software development. It understands complex codebases, provides accurate completions, explains algorithms, and assists with debugging across modern programming languages. Designed for developers, it elevates productivity and supports full\u2011stack coding workflows with precision. Supports 400k tokens of input context.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "OpenAI", "root": "gpt-5.3-codex", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000015909", "completion": "0.0000127273", "image": null, "request": null, "input_cache_read": "0.0000001591", "input_cache_write": null}, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "GPT-5.3-Codex", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3058-200-nmhrgwkrbaduvcwwngbrkusuxkgtpunz.jpeg", "alt": "GPT-5.3-Codex model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5.3-codex"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high", "xhigh"]}, "default_value": "medium"}]}, {"id": "gemma-4-31b", "object": "model", "created": 1775161622456, "description": "Google's most capable open model, delivering frontier-class reasoning and multimodal understanding in a 31 billion parameter dense architecture. Gemma 4 supports a 256K token context window, understands over 140 languages, and accepts both text and image inputs. It features built-in chain-of-thought reasoning for complex multi-step tasks, strong coding and math performance, and function calling support. Released under the Apache 2.0 license, Gemma 4 31B offers competitive performance with leading proprietary models while being fully open-weight. This bot may experience degraded performance due to high traffic to this model.", "owned_by": "Google", "root": "gemma-4-31b", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.00", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 262144, "max_output_tokens": 8192}, "context_length": 262144, "metadata": {"display_name": "Gemma-4-31B", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6030-200-wkjlyhtvpgcrxgyvbunnepjymkoatazd.jpeg", "alt": "Gemma-4-31B model icon", "width": 200, "height": 200}, "url": "https://poe.com/gemma-4-31b"}, "reasoning": null, "parameters": []}, {"id": "glm-5.1-fw", "object": "model", "created": 1775595828552, "description": "GLM-5.1 is Z.ai's next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin on NL2Repo (repo generation) and Terminal-Bench 2.0 (real-world terminal tasks)", "owned_by": "Fireworks AI", "root": "glm-5.1-fw", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0061", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "GLM-5.1-FW", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6927055-200-uyxmlfbkjqogxuvkymjaareadbcrfwax.jpeg", "alt": "GLM-5.1-FW model icon", "width": 200, "height": 200}, "url": "https://poe.com/glm-5.1-fw"}, "reasoning": null, "parameters": []}, {"id": "gpt-5.3-instant", "object": "model", "created": 1772564731085, "description": "GPT-5.3 Instant focuses on making everyday conversations smoother, more accurate, and more directly helpful. It reduces hallucinations, unnecessary refusals, and long defensive caveats while producing clearer answers and better-synthesized results when using web information. It\u2019s designed to feel faster and more natural in normal chats rather than adding new capabilities or heavy reasoning features.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "OpenAI", "root": "gpt-5.3-instant", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000015909", "completion": "0.0000127273", "image": null, "request": null, "input_cache_read": "0.0000001591", "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": 16384}, "context_length": 128000, "metadata": {"display_name": "GPT-5.3-Instant", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3060-200-dpslgyvabiaxitxvmanvmqjlcoxaajxf.jpeg", "alt": "GPT-5.3-Instant model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5.3-instant"}, "reasoning": null, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "grok-4.20-multi-agent", "object": "model", "created": 1773433661072, "description": "Realtime Multi-agent Research enables Grok to orchestrate multiple AI agents that work together in real time to perform deep, multi-step research tasks. Each agent specializes in a particular aspect of the research (searching the web, analyzing data, synthesizing findings) and they collaborate to deliver comprehensive, well-sourced answers.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "XAI", "root": "grok-4.20-multi-agent", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000020202", "completion": "0.0000060606", "image": null, "request": null, "input_cache_read": "0.000000202", "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "Grok-4.20-Multi-Agent", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6874163-200-aomwgdhhcvvlzfvdzcfnpibugcpnzidf.jpeg", "alt": "Grok-4.20-Multi-Agent model icon", "width": 200, "height": 200}, "url": "https://poe.com/grok-4.20-multi-agent"}, "reasoning": null, "parameters": [{"name": "reasoning_effort", "schema": {"enum": ["medium", "high"]}, "default_value": "medium", "description": "Controls how deeply the bot researches before answering."}]}, {"id": "qwen3.6-plus", "object": "model", "created": 1775107805241, "description": "The Qwen3.6 native vision-language Plus series models demonstrate exceptional performance on par with the current state-of-the-art models, with a significant improvement in overall results compared to the 3.5 series. The models have been markedly enhanced in code-related capabilities such as agentic coding, front-end programming, and Vibe coding, as well as in multi-modal general object recognition, OCR, and object localization.\nThis model is served by Alibaba Cloud Int. from Singapore.\n\nNotes:\n- Context Window: 1,000,000\n- Text, Image, & Video input are supported\n- Built-in tool calls are not supported with video attachments\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "qwen3.6-plus", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3.6-Plus", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6918107-200-iosxdbqrvwbibxcaqxpxurhoxnirnyjv.jpeg", "alt": "Qwen3.6-Plus model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3.6-plus"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Let the model reason step-by-step before answering"}, {"name": "vl_high_resolution_images", "schema": {"type": "boolean"}, "default_value": true, "description": "Use maximum resolution for input images (more tokens). Only applies when a video is attached or 4+ images are treated as video; image-only requests use the default resolution."}, {"name": "max_pixels", "schema": {"type": "string"}, "default_value": "2621440", "description": "Maximum pixel count per image (min 4096, default 2621440, max 16777216). Only applies when a video is attached or 4+ images are treated as video."}, {"name": "tool_web_search", "schema": {"type": "boolean"}, "default_value": true, "description": "Search the web for real-time information"}, {"name": "tool_web_extractor", "schema": {"type": "boolean"}, "default_value": true, "description": "Extract and read content from URLs (requires Web Search and Thinking)"}, {"name": "tool_code_interpreter", "schema": {"type": "boolean"}, "default_value": true, "description": "Run Python code in a sandbox (requires thinking)"}, {"name": "tool_web_search_image", "schema": {"type": "boolean"}, "default_value": true, "description": "Search the web for images based on text descriptions"}, {"name": "tool_image_search", "schema": {"type": "boolean"}, "default_value": true, "description": "Find similar images based on an uploaded image"}, {"name": "video_fps", "schema": {"type": "number", "minimum": 0.1, "maximum": 10.0}, "default_value": 2.0, "description": "Frames per second to extract from video"}, {"name": "treat_images_as_video", "schema": {"type": "boolean"}, "default_value": false, "description": "Combine 4+ images into a video sequence"}]}, {"id": "kimi-k2.5", "object": "model", "created": 1769511157082, "description": "Kimi K2.5 is the latest flagship iteration of Moonshot AI's large language model series, representing a significant leap in multimodal and agentic capabilities. It features a native multimodal architecture supporting both visual and text inputs, alongside versatile thinking and non-thinking modes. This model maintains the substantial 256k token context window found in the K2 series but achieves new open-source state-of-the-art (SoTA) performance across general intelligence, coding, and visual understanding benchmarks. Kimi K2.5 delivers a breakthrough in frontend development, enabling the generation of fully functional, aesthetically polished interactive interfaces with complex dynamic layouts directly from natural language. Optimized for complex problem-solving, it excels in multi-step tool invocation, logical reasoning, and full-stack code synthesis.\n\nOptional parameters:\nEnable thinking about the response before giving a final answer: toggle it `on`, otherwise it is `off` by default.\nSet temperature to control randomness in the response: Set number from 1 to 2. This is set to 0.7 by default. Lower values make the output more focused and deterministic.\nSet max output tokens: Set number from 1 to 262144. This is set to 262144 by default.", "owned_by": "Novita AI", "root": "kimi-k2.5", "architecture": {"input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "modality": "text,image,video->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000006061", "completion": "0.0000030303", "image": null, "request": null, "input_cache_read": "0.000000101", "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "Kimi-K2.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6767008-200-nlbqfbtluvgvpmlkdzxpgxrxwdusnxca.jpeg", "alt": "Kimi-K2.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/kimi-k2.5"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": false, "description": "This will cause the model to think..."}, {"name": "temperature", "schema": {"type": "number", "minimum": 0, "maximum": 2}, "default_value": 0.7, "description": "Controls randomness in the response. Lower values make the output more focused and deterministic."}, {"name": "max_output_tokens", "schema": {"type": "number", "minimum": 1, "maximum": 262144}, "default_value": 262144.0, "description": "Maximum number of tokens to generate in the response."}]}, {"id": "minimax-m2.7", "object": "model", "created": 1773820893957, "description": "MiniMax M2.7 is an all-around evolved, versatile open-source large language model that seamlessly blends hardcore engineering productivity with high-EQ, human-like interaction capabilities.\nIn real-world software engineering, M2.7 excels by independently driving end-to-end project delivery while efficiently handling advanced tasks such as log analysis, bug troubleshooting, code security, and machine learning. In the professional workspace, it boasts the highest open-source GDPval-AA score (1495 ELO). It delivers high-fidelity, complex editing and multi-turn revisions across the Office suite (Excel, PPT, Word), elevating task execution to industry-leading standards.\nBuilt for complex environment interactions, M2.7 maintains an impressive 97% skill-following rate even with complex, long-context tool calls (>2000 tokens).  Beyond its robust productivity, M2.7 breaks the \"cold tool\" stereotype of traditional models. With exceptional identity retention and high emotional intelligence (EQ), it not only empowers enterprise productivity, but also opens up more room for product innovation.\n\nContext window: 205k tokens\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Novita AI", "root": "minimax-m2.7", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.000000303", "completion": "0.0000012121", "image": null, "request": null, "input_cache_read": "0.0000000606", "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Minimax-M2.7", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6885560-200-ontorjpvkiowoosbmyegynxpyxfpibfw.jpeg", "alt": "Minimax-M2.7 model icon", "width": 200, "height": 200}, "url": "https://poe.com/minimax-m2.7"}, "reasoning": null, "parameters": [{"name": "temperature", "schema": {"type": "number", "minimum": 0, "maximum": 2}, "default_value": 0.7, "description": "Controls randomness in the response. Lower values make the output more focused and deterministic."}, {"name": "max_output_tokens", "schema": {"type": "number", "minimum": 1, "maximum": 131072}, "default_value": 131072, "description": "Maximum number of tokens to generate in the response."}]}, {"id": "mistral-small-4", "object": "model", "created": 1773801727930, "description": "Mistral Small 4 is a powerful hybrid model capable of acting as both a general instruction model and a reasoning model. It unifies the capabilities of three different model families\u2014Instruct, Reasoning (previously called Magistral), and Devstral\u2014into a single, unified model.\n\nWith its multimodal capabilities, efficient architecture, and flexible mode switching, it is a powerful general-purpose model for any task. In a latency-optimized setup, Mistral Small 4 achieves a 40% reduction in end-to-end completion time, and in a throughput-optimized setup, it handles 3x more requests per second compared to Mistral Small 3.\n\nNotes:\n- Context Window: 256k\n- Supported input modalities: Text, Image, Documents\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "mistral-small-4", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Mistral-Small-4", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6884881-200-qvewgzsrxrhzemydunfvckxtnajkpcrj.jpeg", "alt": "Mistral-Small-4 model icon", "width": 200, "height": 200}, "url": "https://poe.com/mistral-small-4"}, "reasoning": null, "parameters": [{"name": "reasoning_enabled", "schema": {"type": "boolean"}, "default_value": true, "description": "Step-by-step reasoning before answering."}, {"name": "tool_web_search", "schema": {"type": "boolean"}, "default_value": true, "description": "Search the web for real-time information"}, {"name": "web_search_tier", "schema": {"enum": ["standard", "premium"]}, "default_value": "standard", "description": "Premium includes verified news sources"}, {"name": "tool_code_interpreter", "schema": {"type": "boolean"}, "default_value": true, "description": "Execute Python code for calculations and data analysis"}, {"name": "tool_image_generation", "schema": {"type": "boolean"}, "default_value": true, "description": "Generate images from text descriptions"}]}, {"id": "mimo-v2-flash", "object": "model", "created": 1773985456579, "description": "Xiaomi MiMo-V2-Flash is a proprietary MoE model developed by Xiaomi, designed for extreme inference efficiency with 309B total parameters (15B active). By incorporating an innovative Hybrid attention architecture and multi-layer MTP inference acceleration, it ranks among the top 2 global open-source models across multiple Agent benchmarks. Its coding capabilities surpass all open-source models and rival the industry-leading closed-source model, Claude 4.5 Sonnet\u2014yet at only 2.5% of the inference cost and with 2x the generation speed, successfully pushing the limits of both model performance and efficiency.\n\nContext window: 262k tokens\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Novita AI", "root": "mimo-v2-flash", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.000000101", "completion": "0.000000303", "image": null, "request": null, "input_cache_read": "0.0000000202", "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "MiMo-V2-Flash", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6890586-200-atjpdaarkivevbbjniipndybrwupnsmw.jpeg", "alt": "MiMo-V2-Flash model icon", "width": 200, "height": 200}, "url": "https://poe.com/mimo-v2-flash"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": false, "description": "This will cause the model to think..."}, {"name": "temperature", "schema": {"type": "number", "minimum": 0, "maximum": 2}, "default_value": 0.7, "description": "Controls randomness in the response. Lower values make the output more focused and deterministic."}, {"name": "max_output_tokens", "schema": {"type": "number", "minimum": 1, "maximum": 32000}, "default_value": 32000, "description": "Maximum number of tokens to generate in the response."}]}, {"id": "qwen3.5-plus", "object": "model", "created": 1771229977166, "description": "Qwen3.5-Plus is a state-of-the-art multimodal model featuring a hybrid architecture designed for efficient deep thinking and robust visual understanding. It supports text, image, and video inputs within a massive 1M token context window, delivering performance comparable to leading global models across diverse tasks.\nThis model is served by Alibaba Cloud Int. from Singapore.\n\nNotes:\n- Context Window: 1,000,000\n- Text, Image, & Video input are supported\n- Built-in tool calls are not supported with video attachments\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "qwen3.5-plus", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3.5-Plus", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6813257-200-qiwbimbiiywxnoppxmhwkcairtgdtxmy.jpeg", "alt": "Qwen3.5-Plus model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3.5-plus"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Let the model reason step-by-step before answering"}, {"name": "vl_high_resolution_images", "schema": {"type": "boolean"}, "default_value": true, "description": "Use maximum resolution for input images (more tokens). Only applies when a video is attached or 4+ images are treated as video; image-only requests use the default resolution."}, {"name": "max_pixels", "schema": {"type": "string"}, "default_value": "2621440", "description": "Maximum pixel count per image (min 4096, default 2621440, max 16777216). Only applies when a video is attached or 4+ images are treated as video."}, {"name": "tool_web_search", "schema": {"type": "boolean"}, "default_value": true, "description": "Search the web for real-time information"}, {"name": "tool_web_extractor", "schema": {"type": "boolean"}, "default_value": true, "description": "Extract and read content from URLs (requires Web Search and Thinking)"}, {"name": "tool_code_interpreter", "schema": {"type": "boolean"}, "default_value": true, "description": "Run Python code in a sandbox (requires thinking)"}, {"name": "tool_web_search_image", "schema": {"type": "boolean"}, "default_value": true, "description": "Search the web for images based on text descriptions"}, {"name": "tool_image_search", "schema": {"type": "boolean"}, "default_value": true, "description": "Find similar images based on an uploaded image"}, {"name": "video_fps", "schema": {"type": "number", "minimum": 0.1, "maximum": 10.0}, "default_value": 2.0, "description": "Frames per second to extract from video"}, {"name": "treat_images_as_video", "schema": {"type": "boolean"}, "default_value": false, "description": "Combine 4+ images into a video sequence"}]}, {"id": "qwen3.5-omni-flash", "object": "model", "created": 1774908896258, "description": "Qwen3.5-Omni Flash is the cost-efficient variant of Qwen's latest omni-modal model, supporting text, image, audio, and video understanding and interaction. It handles up to 3 hours of audio and 1 hour of video input, with audio input in 90+ languages and speech output in 30+ languages across 55 voice timbres.\n\nNotes:\n- Context Window: 256K\n- Recommended: instruct the model to avoid markdown formatting in Text + Audio mode\n\nInput limits:\n- Images: up to 2,048 files, \u226420 MB each, min 10\u00d710 px, aspect ratio \u2264200:1\n- Audio: up to 2,048 files, \u22642 GB each, up to 3 hrs\n- Video: up to 512 files, \u22642 GB each, up to 1 hr\n- Formats \u2014 Image: JPG, JPEG, JPE, PNG, WebP, BMP, TIF, TIFF, HEIC, GIF | Audio: AMR, WAV, 3GP, 3GPP, AAC, MP3 | Video: MP4, AVI, MKV, MOV, FLV, WMV\n- Audio Input: 92 languages, 21 dialects\n\nOutput:\n- Modalities: text only, or text + audio (audio-only not available)\n- 55 voice timbres (default: Tina)\n- Audio output: 29 languages, 7 dialects\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "qwen3.5-omni-flash", "architecture": {"input_modalities": ["text", "video", "audio"], "output_modalities": ["text"], "modality": "text,video,audio->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3.5-Omni-Flash", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6914148-200-jkmknqfuhujzudeiyuflhmwskdqwuutc.jpeg", "alt": "Qwen3.5-Omni-Flash model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3.5-omni-flash"}, "reasoning": null, "parameters": [{"name": "output_mode", "schema": {"enum": ["text", "text_audio"]}, "default_value": "text", "description": "Choose whether the model responds with text only, or text with synthesized audio"}, {"name": "voice", "schema": {"enum": ["Tina", "Cindy", "Liora Mira", "Sunnybobi", "Raymond", "Ethan", "Theo Calm", "Serena", "Harvey", "Maia", "Evan", "Qiao", "Momo", "Wil", "Angel", "Li Cassian", "Mia", "Joyner", "Gold", "Katerina", "Ryan", "Jennifer", "Aiden", "Mione", "Sunny", "Dylan", "Eric", "Peter", "Joseph Chen", "Marcus", "Li", "Rocky", "Sohee", "Lenn", "Ono Anna", "Sonrisa", "Bodega", "Emilien", "Andre", "Radio Gol", "Alek", "Rizky", "Roya", "Arda", "Hana", "Dolce", "Jakub", "Griet", "Eli\u0161ka", "Marina", "Siiri", "Ingrid", "Sigga", "Bea", "Chloe"]}, "default_value": "Tina", "description": "Select the voice timbre for audio output (55 timbres available)"}, {"name": "enable_web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search for real-time information (charged per request when enabled)"}, {"name": "video_fps", "schema": {"type": "number", "minimum": 0.1, "maximum": 10.0}, "default_value": 2.0, "description": "Frames per second to extract from video input (higher = more detail, more tokens)"}, {"name": "vl_high_resolution_images", "schema": {"type": "boolean"}, "default_value": true, "description": "Use maximum resolution for input images (more tokens, better detail)"}, {"name": "max_pixels", "schema": {"type": "string"}, "default_value": "2621440", "description": "Maximum pixel count per image (min 4096, default 2621440, max 16777216). Lower = fewer tokens."}]}, {"id": "qwen3.5-flash", "object": "model", "created": 1771963175057, "description": "The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the 3 series, these models deliver a leap forward in performance for both pure text and multimodal tasks, offering fast response times while balancing inference speed and overall performance.\nThis model is served by Alibaba Cloud Int. from Singapore.\nSave 10% on input tokens and 8% on output tokens compared to standard API rates.\n\nNotes:\n- Context Window: 1,000,000\n- Text, Image, & Video input are supported\n- Built-in tool calls are not supported with video attachments\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "qwen3.5-flash", "architecture": {"input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "modality": "text,image,video->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000000909", "completion": "0.0000003717", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3.5-Flash", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6830484-200-nsuelnjzjhljcqkxxoesiykvmjmednhg.jpeg", "alt": "Qwen3.5-Flash model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3.5-flash"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Let the model reason step-by-step before answering"}, {"name": "vl_high_resolution_images", "schema": {"type": "boolean"}, "default_value": true, "description": "Use maximum resolution for input images (more tokens). Only applies when a video is attached or 4+ images are treated as video; image-only requests use the default resolution."}, {"name": "max_pixels", "schema": {"type": "string"}, "default_value": "2621440", "description": "Maximum pixel count per image (min 4096, default 2621440, max 16777216). Only applies when a video is attached or 4+ images are treated as video."}, {"name": "tool_web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Search the web for real-time information"}, {"name": "tool_web_extractor", "schema": {"type": "boolean"}, "default_value": false, "description": "Extract and read content from URLs (requires Web Search and Thinking)"}, {"name": "tool_code_interpreter", "schema": {"type": "boolean"}, "default_value": false, "description": "Run Python code in a sandbox (requires thinking)"}, {"name": "tool_web_search_image", "schema": {"type": "boolean"}, "default_value": false, "description": "Search the web for images based on text descriptions"}, {"name": "tool_image_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Find similar images based on an uploaded image"}, {"name": "video_fps", "schema": {"type": "number", "minimum": 0.1, "maximum": 10.0}, "default_value": 2.0, "description": "Frames per second to extract from video"}, {"name": "treat_images_as_video", "schema": {"type": "boolean"}, "default_value": false, "description": "Combine 4+ images into a video sequence"}]}, {"id": "seed-2.0-lite", "object": "model", "created": 1772817225611, "description": "Seed 2.0 Lite is a balanced model designed for high-frequency enterprise workloads, optimizing for both capability and cost. Its overall performance surpasses the previous-generation ByteDance-Seed-1.8. It is well-suited for production tasks such as unstructured information processing, text content creation, search and recommendation, and data analysis. The model supports long-context processing, multi-source information fusion, multi-step instruction execution, and high-fidelity structured outputs\u2014delivering stable quality while significantly reducing cost.\nThis model is served from Malaysia.\n\nNotes: \n- Pricing is 2x when input tokens >128k\n- Context Window: 256k \n- Temperature and top_p are fixed by the model (temp=1, top_p=0.95).\n\nParameter controls available:\n1. Reasoning\n- Default: Thinking enabled\n- Reasoning effort [low, medium, high]: How deeply the model thinks. Low=fast, Medium=balanced, High=thorough (default: medium). Only applies if thinking is enabled.\n\n2. Search & Vision\n- Web Search: Enable real-time web search for up-to-date information (default: false).\n- Image Detail [low, high, xhigh]: Quality for image understanding. Higher = more accurate but uses more tokens (default: high).\n- Video FPS [0.2-5]: Frame sampling rate for video input. Higher = more frames analyzed, more accurate, more tokens (default: 1).", "owned_by": "EmpirioLabs AI", "root": "seed-2.0-lite", "architecture": {"input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "modality": "text,image,video->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000003157", "completion": "0.0000025253", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Seed-2.0-Lite", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6854989-200-otkjsrqfhykvgucidgeylvqopnjvrjki.jpeg", "alt": "Seed-2.0-Lite model icon", "width": 200, "height": 200}, "url": "https://poe.com/seed-2.0-lite"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Let the model reason step-by-step before answering."}, {"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium", "description": "How deeply the model thinks. Low=fast, Medium=balanced, High=thorough."}, {"name": "enable_web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable real-time web search for up-to-date information."}, {"name": "image_detail", "schema": {"enum": ["low", "high", "xhigh"]}, "default_value": "high", "description": "Quality for image understanding. Higher = more accurate but more tokens."}, {"name": "video_fps", "schema": {"type": "number", "minimum": 0.2, "maximum": 5}, "default_value": 1, "description": "Frame sampling rate for video input (0.2-5). Higher = more frames, more accurate, more tokens."}]}, {"id": "qwen3.5-omni-plus", "object": "model", "created": 1774889310984, "description": "Qwen3.5-Omni Plus is the flagship variant of Qwen's latest omni-modal model, supporting text, image, audio, and video understanding and interaction. It handles up to 3 hours of audio and 1 hour of video input, with audio input in 90+ languages and speech output in 30+ languages across 55 voice timbres.\nThis model is served by Alibaba Cloud Int. from Singapore.\n\nNotes:\n- Context Window: 256K\n- Recommended: instruct the model to avoid markdown formatting in Text + Audio mode\n\nInput limits:\n- Images: up to 2,048 files, \u226420 MB each, min 10\u00d710 px, aspect ratio \u2264200:1\n- Audio: up to 2,048 files, \u22642 GB each, up to 3 hrs\n- Video: up to 512 files, \u22642 GB each, up to 1 hr\n- Formats \u2014 Image: JPG, JPEG, JPE, PNG, WebP, BMP, TIF, TIFF, HEIC, GIF | Audio: AMR, WAV, 3GP, 3GPP, AAC, MP3 | Video: MP4, AVI, MKV, MOV, FLV, WMV\n- Audio Input: 92 languages, 21 dialects\n\nOutput:\n- Modalities: text only, or text + audio (audio-only not available)\n- 55 voice timbres (default: Tina)\n- Audio output: 29 languages, 7 dialects\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "qwen3.5-omni-plus", "architecture": {"input_modalities": ["text", "video", "audio"], "output_modalities": ["text"], "modality": "text,video,audio->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3.5-Omni-Plus", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6913743-200-ilhmvtkwnojtqqeygzkmdpjapwgznkxe.jpeg", "alt": "Qwen3.5-Omni-Plus model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3.5-omni-plus"}, "reasoning": null, "parameters": [{"name": "output_mode", "schema": {"enum": ["text", "text_audio"]}, "default_value": "text", "description": "Choose whether the model responds with text only, or text with synthesized audio"}, {"name": "voice", "schema": {"enum": ["Tina", "Cindy", "Liora Mira", "Sunnybobi", "Raymond", "Ethan", "Theo Calm", "Serena", "Harvey", "Maia", "Evan", "Qiao", "Momo", "Wil", "Angel", "Li Cassian", "Mia", "Joyner", "Gold", "Katerina", "Ryan", "Jennifer", "Aiden", "Mione", "Sunny", "Dylan", "Eric", "Peter", "Joseph Chen", "Marcus", "Li", "Rocky", "Sohee", "Lenn", "Ono Anna", "Sonrisa", "Bodega", "Emilien", "Andre", "Radio Gol", "Alek", "Rizky", "Roya", "Arda", "Hana", "Dolce", "Jakub", "Griet", "Eli\u0161ka", "Marina", "Siiri", "Ingrid", "Sigga", "Bea", "Chloe"]}, "default_value": "Tina", "description": "Select the voice timbre for audio output (55 timbres available)"}, {"name": "enable_web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search for real-time information (charged per request when enabled)"}, {"name": "video_fps", "schema": {"type": "number", "minimum": 0.1, "maximum": 10.0}, "default_value": 2.0, "description": "Frames per second to extract from video input (higher = more detail, more tokens)"}, {"name": "vl_high_resolution_images", "schema": {"type": "boolean"}, "default_value": true, "description": "Use maximum resolution for input images (more tokens, better detail)"}, {"name": "max_pixels", "schema": {"type": "string"}, "default_value": "2621440", "description": "Maximum pixel count per image (min 4096, default 2621440, max 16777216). Lower = fewer tokens."}]}, {"id": "mimo-v2-omni", "object": "model", "created": 1773985518635, "description": "MiMo V2 Omni is Xiaomi\u2019s omni-modal foundation model that natively sees, hears, and understands text, images, audio, and video within a single unified architecture. It combines deep reasoning and web search with agent-like capabilities\u2014such as multi-step planning and tool use\u2014to seamlessly power complex, real-world workflows.\n\nNotes:\n- Context Window: 256K\n- Max Output: 128K\n- Supported input modalities: Text, Image, Audio, Video\n\nParameter controls available:\n1. Reasoning\n- Deep Thinking (toggle, default: on): Step-by-step reasoning before answering.\n\n2. Web Search\n- Enable Web Search (toggle, default: off): Search the web for real-time information.\n- Force Search (toggle, default: off): Always search, even if the model thinks it can answer directly. Only shown when Web Search is enabled.\n- Max Keywords (slider, 1\u20135, default: 3): Maximum search keywords per round. Each keyword triggers a separate search call. More = broader but costlier. Only shown when Web Search is enabled.\n- Results Limit (slider, 1\u201310, default: 5): Maximum web pages returned per search round. Only shown when Web Search is enabled.\n\n3. Video Settings\n- Video FPS (slider, 0.1-10, default: 2): Frames extracted per second from video. Higher = finer temporal detail but more tokens.\n- Video Resolution (dropdown, default/max, default: default): Resolution tier for video frame analysis. 'Max' enhances recognition of small objects and fine details but uses more tokens.\n\nInput Limits\n- Images: JPEG, PNG, GIF, WebP, BMP (max 10 MB each). Multiple images supported.\n- Audio: MP3, WAV, FLAC, M4A, OGG (max 100 MB each). Multiple files supported.\n- Video: MP4, MOV, AVI, WMV (max 300 MB each). Multiple videos supported.", "owned_by": "EmpirioLabs AI", "root": "mimo-v2-omni", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "MiMo-V2-Omni", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6890588-200-qorttykhcjowvoiqbojxsizpbjkxpeqk.jpeg", "alt": "MiMo-V2-Omni model icon", "width": 200, "height": 200}, "url": "https://poe.com/mimo-v2-omni"}, "reasoning": null, "parameters": [{"name": "deep_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Step-by-step reasoning before answering."}, {"name": "web_search_enabled", "schema": {"type": "boolean"}, "default_value": false, "description": "Allow the model to search the web for real-time information."}, {"name": "web_search_force", "schema": {"type": "boolean"}, "default_value": false, "description": "Always search, even if the model thinks it can answer directly."}, {"name": "web_search_max_keyword", "schema": {"type": "number", "minimum": 1, "maximum": 5}, "default_value": 3, "description": "Maximum search keywords per round. Each keyword triggers a separate API call. More = broader but costlier."}, {"name": "web_search_limit", "schema": {"type": "number", "minimum": 1, "maximum": 10}, "default_value": 5, "description": "Maximum web pages returned per search round."}, {"name": "video_fps", "schema": {"type": "number", "minimum": 0.1, "maximum": 10}, "default_value": 2, "description": "Frames extracted per second from video. Higher = finer temporal detail but more tokens."}, {"name": "video_resolution", "schema": {"enum": ["default", "max"]}, "default_value": "default", "description": "Resolution tier for video frame analysis. 'Max' enhances recognition of small objects and fine details but uses more tokens."}]}, {"id": "gemma-4-26b-a4b", "object": "model", "created": 1775147437939, "description": "Gemma 4 26B A4B is built for developers who need scalable performance without sacrificing core capabilities. Crucially, it retains the massive 262k-token context window of the 31B model, making it highly competitive for long-context RAG and processing extensive, image-rich document datasets. It fully supports the series' core innovations: native Thinking mode for advanced logic, Interleaved Multimodal Input for dynamic text-image workflows, and flawless document/UI parsing. Equipped with native Function Calling and robust coding proficiencies, the 26B A4B is the ideal, cost-effective engine for powering real-world agentic workflows, visual automation, and global applications across its 140+ pre-trained languages.\n\nFile Support: Text, Markdown, Image and PDF files\nContext window: 262k tokens\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Novita AI", "root": "gemma-4-26b-a4b", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": "0.0000001313", "completion": "0.000000404", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Gemma-4-26B-A4B", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6918889-200-xkfdbzauzcemlduvlnlvtomxpinhfbcq.jpeg", "alt": "Gemma-4-26B-A4B model icon", "width": 200, "height": 200}, "url": "https://poe.com/gemma-4-26b-a4b"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": false, "description": "This will cause the model to think..."}, {"name": "temperature", "schema": {"type": "number", "minimum": 0, "maximum": 2}, "default_value": 0.7, "description": "Controls randomness in the response. Lower values make the output more focused and deterministic."}, {"name": "max_output_tokens", "schema": {"type": "number", "minimum": 1, "maximum": 131072}, "default_value": 131072, "description": "Maximum number of tokens to generate in the response."}]}, {"id": "seedance-2-fast", "object": "model", "created": 1775769251552, "description": "Seedance 2.0 Fast supports the text and image inputs but is optimized for speed, making it ideal for rapid iteration, quick concept testing, and high\u2011volume creative workflows.\n\nCost estimate - $0.115 per second (10300 tokens per second) at 480p, $0.24752 per second (22100 tokens per second) at 720p, at a rate of $0.0112  per 1000 tokens.", "owned_by": "Bytedance", "root": "seedance-2-fast", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Seedance-2-Fast", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6930468-200-ftwjaiyifumzyzpdetqowurpeqjlwvmi.jpeg", "alt": "Seedance-2-Fast model icon", "width": 200, "height": 200}, "url": "https://poe.com/seedance-2-fast"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["21:9", "16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "16:9"}, {"name": "resolution", "schema": {"enum": ["480p", "720p"]}, "default_value": "720p"}, {"name": "duration", "schema": {"enum": ["4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15"]}, "default_value": "5", "description": "Video duration in seconds"}]}, {"id": "seedance-2.0", "object": "model", "created": 1775769075017, "description": "Seedance 2.0 delivers high\u2011quality video generation across text and image inputs \u2014 built for cinematic scenes, consistent characters, and detailed motion control.\nCost estimate - $0.1442 per second at 480p (10300 tokens per second), $0.3094 per second at 720p (22100 tokens per second) at a rate of $0.014 per 1000 tokens.", "owned_by": "Bytedance", "root": "seedance-2.0", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Seedance-2.0", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6930463-200-mwttqrnjumnkclajylacpgimeaesoqsr.jpeg", "alt": "Seedance-2.0 model icon", "width": 200, "height": 200}, "url": "https://poe.com/seedance-2.0"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["21:9", "16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "16:9"}, {"name": "resolution", "schema": {"enum": ["480p", "720p"]}, "default_value": "720p"}, {"name": "duration", "schema": {"enum": ["4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15"]}, "default_value": "5", "description": "Video duration in seconds"}]}, {"id": "mimo-v2-pro", "object": "model", "created": 1773956336321, "description": "MiMo-V2-Pro is Xiaomi's flagship reasoning and agentic foundation model, built on a trillion-parameter MoE architecture with 42B active parameters and up to 1M-token context. It excels at complex reasoning, coding, and agentic workloads, ranking among the global top tier on agent benchmarks.\n\nNotes:\nContext Window: 1M tokens\nMax Output: 128K tokens\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "mimo-v2-pro", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "MiMo-V2-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6889733-200-jmwfneudhseejihyfcqrplwjqnqppeux.jpeg", "alt": "MiMo-V2-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/mimo-v2-pro"}, "reasoning": null, "parameters": [{"name": "deep_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Step-by-step reasoning before answering."}, {"name": "web_search_enabled", "schema": {"type": "boolean"}, "default_value": false, "description": "Allow the model to search the web for real-time information."}, {"name": "web_search_force", "schema": {"type": "boolean"}, "default_value": false, "description": "Always search, even if the model thinks it can answer directly."}, {"name": "web_search_max_keyword", "schema": {"type": "number", "minimum": 1, "maximum": 5}, "default_value": 3, "description": "Maximum search keywords per round. Each keyword triggers a separate API call. More = broader but costlier."}, {"name": "web_search_limit", "schema": {"type": "number", "minimum": 1, "maximum": 10}, "default_value": 5, "description": "Maximum web pages returned per search round."}]}, {"id": "claude-opus-4.6", "object": "model", "created": 1770248062467, "description": "Claude Opus 4.6 is Anthropic\u2019s most advanced AI model, built for deep reasoning, complex coding, and long\u2011running autonomous tasks. It excels at planning, debugging, and working across large codebases, and supports a 1M\u2011token context window for understanding massive amounts of information. Designed for professional knowledge work, it combines state\u2011of\u2011the\u2011art performance with strong safety and reliability.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Anthropic", "root": "claude-opus-4.6", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/messages", "/v1/responses", "/v1/chat/completions"], "pricing": {"prompt": "0.0000042929", "completion": "0.0000214646", "image": null, "request": null, "input_cache_read": "0.0000004293", "input_cache_write": "0.0000053662"}, "context_window": {"context_length": 983040, "max_output_tokens": 128000}, "context_length": 983040, "metadata": {"display_name": "Claude-Opus-4.6", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-1041-200-rudbeeackfrlnorayijivnutjqtoxtcu.jpeg", "alt": "Claude-Opus-4.6 model icon", "width": 200, "height": 200}, "url": "https://poe.com/claude-opus-4.6"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": false}, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}, {"name": "output_effort", "schema": {"enum": ["max", "high", "medium", "low", "none"]}, "default_value": "high"}]}, {"id": "claude-haiku-4.5", "object": "model", "created": 1760556959473, "description": "Claude Haiku 4.5 is Anthropic\u2019s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4\u2019s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications. It introduces extended thinking to the Haiku line, and scores >73% on SWE-bench verified, ranking among the world's best coding models. Supports 200k tokens of context.", "owned_by": "Anthropic", "root": "claude-haiku-4.5", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/messages", "/v1/responses", "/v1/chat/completions"], "pricing": {"prompt": "0.0000008586", "completion": "0.0000042929", "image": null, "request": null, "input_cache_read": "0.0000000859", "input_cache_write": "0.0000010732"}, "context_window": {"context_length": 192000, "max_output_tokens": 64000}, "context_length": 192000, "metadata": {"display_name": "Claude-Haiku-4.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-1039-200-xohshfkzydkgnfmpdshdydgzqiphlumw.jpeg", "alt": "Claude-Haiku-4.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/claude-haiku-4.5"}, "reasoning": {"budget": {"max_tokens": 63999, "min_tokens": 0}, "required": false, "supports_reasoning_effort": false}, "parameters": [{"name": "thinking_budget", "schema": {"type": "number", "minimum": 0, "maximum": 63999}, "default_value": 0, "description": "The maximum number of tokens to spend on thinking."}, {"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "qwen3.5-397b-a17b-t", "object": "model", "created": 1771354710620, "description": "Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance. Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency.\n\nQwen3.5 features the following enhancement:\n\nUnified Vision-Language Foundation: Early fusion training on multimodal tokens achieves cross-generational parity with Qwen3 and outperforms Qwen3-VL models across reasoning, coding, agents, and visual understanding benchmarks.\n\nEfficient Hybrid Architecture: Gated Delta Networks combined with sparse Mixture-of-Experts deliver high-throughput inference with minimal latency and cost overhead.\n\nScalable RL Generalization: Reinforcement learning scaled across million-agent environments with progressively complex task distributions for robust real-world adaptability.\n\nGlobal Linguistic Coverage: Expanded support to 201 languages and dialects, enabling inclusive, worldwide deployment with nuanced cultural and regional understanding.\n\nNext-Generation Training Infrastructure: Near-100% multimodal training efficiency compared to text-only training and asynchronous RL frameworks supporting massive-scale agent scaffolds and environment orchestration.", "owned_by": "Together AI", "root": "qwen3.5-397b-a17b-t", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.00", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3.5-397B-A17B-T", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6816075-200-pmjwiobbezofrhpxnsrsinlpjlfehspp.jpeg", "alt": "Qwen3.5-397B-A17B-T model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3.5-397b-a17b-t"}, "reasoning": null, "parameters": []}, {"id": "seed-2.0-mini", "object": "model", "created": 1771632981140, "description": "Seed-2.0-Mini from Bytedance targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It supports 256k context, four reasoning effort modes, and multimodal understanding (including image and video), and is optimized for lightweight tasks where cost and speed take priority.\nThis model is served from Malaysia.\n\nNote: Pricing is 2x when input tokens >128k\n\nParameter controls available:\n1. Reasoning\n- Default: Thinking enabled\n- Reasoning effort [low, medium, high]: How deeply the model thinks. Low=fast, Medium=balanced, High=thorough (default: medium). Only applies if thinking is enabled.\n\n2. Search & Vision\n- Web Search: Enable real-time web search for up-to-date information (default: false).\n- Image Detail [low, high, xhigh]: Quality for image understanding. Higher = more accurate but uses more tokens (default: high).\n- Video FPS [0.2-5]: Frame sampling rate for video input. Higher = more frames analyzed, more accurate, more tokens (default: 1).", "owned_by": "EmpirioLabs AI", "root": "seed-2.0-mini", "architecture": {"input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "modality": "text,image,video->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000001263", "completion": "0.0000005051", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Seed-2.0-Mini", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6822254-200-ddnfzxiawffeqryxrluxuldbxcyatpgt.jpeg", "alt": "Seed-2.0-Mini model icon", "width": 200, "height": 200}, "url": "https://poe.com/seed-2.0-mini"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Let the model reason step-by-step before answering."}, {"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium", "description": "How deeply the model thinks. Low=fast, Medium=balanced, High=thorough."}, {"name": "enable_web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable real-time web search for up-to-date information."}, {"name": "image_detail", "schema": {"enum": ["low", "high", "xhigh"]}, "default_value": "high", "description": "Quality for image understanding. Higher = more accurate but more tokens."}, {"name": "video_fps", "schema": {"type": "number", "minimum": 0.2, "maximum": 5}, "default_value": 1, "description": "Frame sampling rate for video input (0.2-5). Higher = more frames, more accurate, more tokens."}]}, {"id": "claude-sonnet-4.6", "object": "model", "created": 1770262891433, "description": "Claude Sonnet 4.6 from Anthropic is built for high-quality conversations, advanced coding, and agentic workflows at scale. It excels at iterative development and navigating complex codebases, supports end-to-end project management with memory, and produces polished documents. The model also enables confident computer use for web QA and workflow automation, along with financial modeling, compliance review, and accurate data summarization. It features a 1M token context window for handling extensive projects and long-form content with ease.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Anthropic", "root": "claude-sonnet-4.6", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/messages", "/v1/responses", "/v1/chat/completions"], "pricing": {"prompt": "0.0000025758", "completion": "0.0000128788", "image": null, "request": null, "input_cache_read": "0.0000002576", "input_cache_write": "0.0000032197"}, "context_window": {"context_length": 983040, "max_output_tokens": 128000}, "context_length": 983040, "metadata": {"display_name": "Claude-Sonnet-4.6", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-1042-200-ojftpbuyljsmmohjrdguquhuaqdlprew.jpeg", "alt": "Claude-Sonnet-4.6 model icon", "width": 200, "height": 200}, "url": "https://poe.com/claude-sonnet-4.6"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": false}, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}, {"name": "output_effort", "schema": {"enum": ["max", "high", "medium", "low", "none"]}, "default_value": "medium"}]}, {"id": "qwen3.5-397b-a17b", "object": "model", "created": 1771239767882, "description": "The Qwen3.5 series 397B-A17B native vision-language model is based on a hybrid architecture design that integrates linear attention mechanisms with sparse Mixture-of-Experts (MoE), achieving higher inference efficiency. Across a variety of tasks\u2014including language understanding, logical reasoning, code generation, agentic tasks, image understanding, video understanding, and graphical user interface (GUI) interaction\u2014it demonstrates exceptional performance comparable to current top-tier frontier models. Possessing robust code generation and agentic capabilities, it exhibits strong generalization across various agent scenarios.\n\nFile Support: Text, Markdown, Image, Video and PDF files\nContext window: 262k tokens\n\nOptional parameters:\nEnable thinking about the response before giving a final answer: toggle it `on`, otherwise it is `off`  by default.\nSet temperature to control randomness in the response: Set number from 1 to 2.  This is set to `0.7` by default. Lower values make the output more focused and deterministic.\nSet max output tokens: Set number from 1 to 64000. This is set to 64000 by default.", "owned_by": "Novita AI", "root": "qwen3.5-397b-a17b", "architecture": {"input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "modality": "text,image,video->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000006061", "completion": "0.0000036364", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3.5-397B-A17B", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6813466-200-gaeagtwigznhnkaddiiplbxadkcqofrg.jpeg", "alt": "Qwen3.5-397B-A17B model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3.5-397b-a17b"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": false, "description": "This will cause the model to think..."}, {"name": "temperature", "schema": {"type": "number", "minimum": 0, "maximum": 2}, "default_value": 0.7, "description": "Controls randomness in the response. Lower values make the output more focused and deterministic."}, {"name": "max_output_tokens", "schema": {"type": "number", "minimum": 1, "maximum": 64000}, "default_value": 64000.0, "description": "Maximum number of tokens to generate in the response."}]}, {"id": "mimo-v2-flash-el", "object": "model", "created": 1773981634473, "description": "MiMo V2 Flash is Xiaomi's lightweight, high-speed reasoning model designed for fast and cost-effective text generation. It uses a hybrid attention architecture and multi-token prediction to keep inference costs low while maintaining strong performance on complex reasoning benchmarks.\n\nNotes:\nContext Window: 256K\nMax Output: 64K\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "mimo-v2-flash-el", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "MiMo-V2-Flash-EL", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6890481-200-txzirhqmbjmsjkrfswkphlwdeyxpzsmx.jpeg", "alt": "MiMo-V2-Flash-EL model icon", "width": 200, "height": 200}, "url": "https://poe.com/mimo-v2-flash-el"}, "reasoning": null, "parameters": [{"name": "deep_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Step-by-step reasoning before answering."}, {"name": "web_search_enabled", "schema": {"type": "boolean"}, "default_value": false, "description": "Allow the model to search the web for real-time information."}, {"name": "web_search_force", "schema": {"type": "boolean"}, "default_value": false, "description": "Always search, even if the model thinks it can answer directly."}, {"name": "web_search_max_keyword", "schema": {"type": "number", "minimum": 1, "maximum": 5}, "default_value": 3, "description": "Maximum search keywords per round. Each keyword triggers a separate API call. More = broader but costlier."}, {"name": "web_search_limit", "schema": {"type": "number", "minimum": 1, "maximum": 10}, "default_value": 5, "description": "Maximum web pages returned per search round."}]}, {"id": "gemma-4-31b-n", "object": "model", "created": 1775147397334, "description": "Gemma 4 31B is engineered to tackle the most demanding enterprise workloads and complex reasoning tasks. With an expansive 256K-token context window, the 31B model can effortlessly ingest entire codebases, and massive sets of images in a single prompt. It boasts state-of-the-art vision-language capabilities, allowing developers to freely interleave text and images. It excels at parsing UI screens, comprehending complex charts, and executing multilingual OCR or handwriting recognition. Combined with native structured Function Calling, robust code generation, and out-of-the-box fluency in 35+ languages, Gemma 4 31B is the ultimate foundation for building sophisticated, autonomous AI agents and heavy-duty multimodal analysis pipelines.\n\nFile Support: Text, Markdown, Image and PDF files\nContext window: 262k tokens\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Novita AI", "root": "gemma-4-31b-n", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": "0.0000001414", "completion": "0.000000404", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Gemma-4-31B-N", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6918888-200-hjuxkingreouqwflfiooablystlxiyvm.jpeg", "alt": "Gemma-4-31B-N model icon", "width": 200, "height": 200}, "url": "https://poe.com/gemma-4-31b-n"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": false, "description": "This will cause the model to think..."}, {"name": "temperature", "schema": {"type": "number", "minimum": 0, "maximum": 2}, "default_value": 0.7, "description": "Controls randomness in the response. Lower values make the output more focused and deterministic."}, {"name": "max_output_tokens", "schema": {"type": "number", "minimum": 1, "maximum": 131072}, "default_value": 131072, "description": "Maximum number of tokens to generate in the response."}]}, {"id": "grok-imagine-image", "object": "model", "created": 1769805492868, "description": "Create creative and artistic images with Grok Imagine Image. Supports text-to-image and image-editing (single image of jpeg/png/webp format). Set aspect ratio via parameter controls.", "owned_by": "fal", "root": "grok-imagine-image", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Grok-Imagine-Image", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6774867-200-fggmuawglvqtkbnfrwmiwdmlmuiitmrb.jpeg", "alt": "Grok-Imagine-Image model icon", "width": 200, "height": 200}, "url": "https://poe.com/grok-imagine-image"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["2:1", "20:9", "19.5:9", "16:9", "4:3", "3:2", "1:1", "2:3", "3:4", "9:16", "9:19.5", "9:20", "1:2"]}, "default_value": "1:1", "description": "Select the desired aspect ratio for your image"}]}, {"id": "kimi-k2.5-fw", "object": "model", "created": 1769497628504, "description": "Kimi K2.5 is Moonshot AI's flagship agentic model and a new SOTA open model. It unifies vision and text, thinking and non-thinking modes, and single-agent and multi-agent execution into one model.", "owned_by": "Fireworks AI", "root": "kimi-k2.5-fw", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.00", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Kimi-K2.5-FW", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6766647-200-ditdypjluzdoyjkyttbcvgvtaprmnqfz.jpeg", "alt": "Kimi-K2.5-FW model icon", "width": 200, "height": 200}, "url": "https://poe.com/kimi-k2.5-fw"}, "reasoning": null, "parameters": []}, {"id": "seed-2.0-pro", "object": "model", "created": 1774508584107, "description": "Seed 2.0 Pro is a flagship all-purpose general model designed for complex reasoning and long-chain task execution in the Agent era. It emphasizes multimodal understanding, long-context reasoning, structured generation, and tool-augmented execution. It delivers outstanding performance in handling complex instructions and multi-constraint execution, and can reliably address scenarios such as multi-step complex planning, sophisticated visual-text reasoning, video content understanding, and high-difficulty analysis.\nThis model is served from Malaysia.\n\nNotes:\n- Pricing is 2x when input tokens >128k\n- Context Window: 256k\n- Temperature and top_p are fixed by the model (temp=1, top_p=0.95).\n\nParameter controls available:\n1. Reasoning\n- Default: Thinking enabled\n- Reasoning effort [low, medium, high]: How deeply the model thinks. Low=fast, Medium=balanced, High=thorough (default: medium). Only applies if thinking is enabled.\n\n2. Search & Vision\n- Web Search: Enable real-time web search for up-to-date information (default: false).\n- Image Detail [low, high, xhigh]: Quality for image understanding. Higher = more accurate but uses more tokens (default: high).\n- Video FPS [0.2-5]: Frame sampling rate for video input. Higher = more frames analyzed, more accurate, more tokens (default: 1).", "owned_by": "EmpirioLabs AI", "root": "seed-2.0-pro", "architecture": {"input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "modality": "text,image,video->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000006313", "completion": "0.0000037879", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Seed-2.0-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6904621-200-dopcynjylmhafwsfbdahfxwynvfcegua.jpeg", "alt": "Seed-2.0-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/seed-2.0-pro"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Let the model reason step-by-step before answering."}, {"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium", "description": "How deeply the model thinks. Low=fast, Medium=balanced, High=thorough."}, {"name": "enable_web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable real-time web search for up-to-date information."}, {"name": "image_detail", "schema": {"enum": ["low", "high", "xhigh"]}, "default_value": "high", "description": "Quality for image understanding. Higher = more accurate but more tokens."}, {"name": "video_fps", "schema": {"type": "number", "minimum": 0.2, "maximum": 5}, "default_value": 1, "description": "Frame sampling rate for video input (0.2-5). Higher = more frames, more accurate, more tokens."}]}, {"id": "minimax-speech-2.8", "object": "model", "created": 1774510258443, "description": "MiniMax Speech 2.8 is a premium text-to-speech model delivering studio-quality audio with enhanced clarity and naturalness. With support for multiple voice presets, emotional tones, and fine-grained audio controls, it produces broadcast-ready speech synthesis for professional applications.", "owned_by": "Novita AI", "root": "minimax-speech-2.8", "architecture": {"input_modalities": ["text"], "output_modalities": ["audio"], "modality": "text->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0061", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "MiniMax-Speech-2.8", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6904717-200-kmvvzbitpvffoywnjdqsghzrgwypshtn.jpeg", "alt": "MiniMax-Speech-2.8 model icon", "width": 200, "height": 200}, "url": "https://poe.com/minimax-speech-2.8"}, "reasoning": null, "parameters": [{"name": "model", "schema": {"enum": ["turbo", "hd"]}, "default_value": "turbo", "description": "HD: high quality, async, max 50K chars. Turbo: fast, sync, max 10K chars."}, {"name": "voice_id", "schema": {"enum": ["Chinese (Mandarin)_Lyrical_Voice", "Chinese (Mandarin)_HK_Flight_Attendant", "moss_audio_ce44fc67-7ce3-11f0-8de5-96e35d26fb85", "moss_audio_aaa1346a-7ce7-11f0-8e61-2e6e3c7ee85d", "English_Graceful_Lady", "English_Insightful_Speaker", "English_radiant_girl", "English_Persuasive_Man", "English_Lucky_Robot", "moss_audio_6dc281eb-713c-11f0-a447-9613c873494c", "moss_audio_570551b1-735c-11f0-b236-0adeeecad052", "moss_audio_ad5baf92-735f-11f0-8263-fe5a2fe98ec8", "Japanese_Whisper_Belle", "moss_audio_24875c4a-7be4-11f0-9359-4e72c55db738", "moss_audio_7f4ee608-78ea-11f0-bb73-1e2a4cfcd245", "moss_audio_c1a6a3ac-7be6-11f0-8e8e-36b92fbb4f95"]}, "default_value": "Chinese (Mandarin)_Lyrical_Voice", "description": "Select a voice for speech synthesis"}, {"name": "speed", "schema": {"enum": ["0.5", "0.75", "1.0", "1.25", "1.5", "1.75", "2.0"]}, "default_value": "1.0", "description": "Speech speed (1.0 = normal)"}, {"name": "vol", "schema": {"enum": ["0.5", "1.0", "2.0", "3.0", "5.0"]}, "default_value": "1.0", "description": "Audio volume (1.0 = default)"}, {"name": "pitch", "schema": {"enum": ["-12", "-6", "-3", "0", "3", "6", "12"]}, "default_value": "0", "description": "Voice pitch (-12 = low, 0 = original, 12 = high)"}, {"name": "sound_effects", "schema": {"enum": ["none", "spacious_echo", "auditorium_echo", "lofi_telephone", "robotic"]}, "default_value": "none", "description": "Apply a sound effect to the voice"}, {"name": "format", "schema": {"enum": ["mp3", "flac", "wav", "pcm"]}, "default_value": "mp3", "description": "Audio output format (wav only available for Turbo)"}, {"name": "sample_rate", "schema": {"enum": ["8000", "16000", "22050", "24000", "32000", "44100"]}, "default_value": "32000", "description": "Audio sample rate in Hz"}, {"name": "language_boost", "schema": {"enum": ["auto", "Chinese", "Chinese,Yue", "English", "Japanese", "Korean", "French", "German", "Spanish", "Russian", "Arabic", "Portuguese", "Italian", "Thai", "Vietnamese", "Indonesian", "Hindi"]}, "default_value": "auto", "description": "Enhance recognition for a specific language"}]}, {"id": "manus", "object": "model", "created": 1761671380766, "description": "Manus is an autonomous AI agent that executes tasks. It can take a high-level prompt, break it into subtasks, interact with tools/APIs, and deliver end-to-end results (like reports, code, websites, images, and more) without you managing each step.\n\nNotes: \n- Sometimes, files that Manus has created are incorrectly uploaded to the Poe message. In such cases, please check the Manus chat for the file. \n- Responses may take several minutes to complete, depending on complexity. \n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "manus", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Manus", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6537696-200-gxbrsointtdxnjzjfrzjddeuazsqlgmm.jpeg", "alt": "Manus model icon", "width": 200, "height": 200}, "url": "https://poe.com/manus"}, "reasoning": null, "parameters": [{"name": "task_mode", "schema": {"enum": ["adaptive"]}, "default_value": "adaptive", "description": "Adaptive lets Manus handle each request automatically. Adaptive is the only mode available."}, {"name": "agent_profile", "schema": {"enum": ["manus-1.6", "manus-1.6-lite", "manus-1.6-max"]}, "default_value": "manus-1.6", "description": "Choose Manus 1.6 Lite for speed/savings, Manus 1.6 for standard tasks, or Manus 1.6 Max for complex reasoning. You can switch profiles between messages, including on follow-ups within the same task."}]}, {"id": "glm-5", "object": "model", "created": 1770830055326, "description": "GLM-5 is an open-source foundation model engineered for complex system engineering and long-horizon Agent tasks, delivering reliable productivity for top-tier programmers. Transcending the boundary from \"writing code\" to \"building systems,\" it moves beyond traditional snippet generation to offer senior-architect-level planning and execution capabilities. By rejecting the \"frontend-heavy, logic-light\" approach, GLM-5 demonstrates exceptional reasoning and self-healing abilities in backend refactoring, complex algorithm implementation, and deep debugging\u2014autonomously analyzing logs and iteratively fixing persistent bugs until the system runs. As the first open-source model featuring Opus-class style and system engineering depth, GLM-5 provides extreme logic density alongside the freedom of local deployment and high cost-effectiveness, making it the ideal choice for large-scale backend development and automated Agent construction. Context window: 205k tokens\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Novita AI", "root": "glm-5", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000010101", "completion": "0.0000032323", "image": null, "request": null, "input_cache_read": "0.000000202", "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "GLM-5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6802092-200-sqrsdkzksaocmqhyynlwkagfcrkajwyw.jpeg", "alt": "GLM-5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/glm-5"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": false, "description": "This will cause the model to think..."}, {"name": "temperature", "schema": {"type": "number", "minimum": 0, "maximum": 2}, "default_value": 0.7, "description": "Controls randomness in the response. Lower values make the output more focused and deterministic."}, {"name": "max_output_tokens", "schema": {"type": "number", "minimum": 1, "maximum": 131072}, "default_value": 131072, "description": "Maximum number of tokens to generate in the response."}]}, {"id": "gpt-5.2", "object": "model", "created": 1765227300074, "description": "GPT-5.2 is a state-of-the-art AI model from OpenAI designed for real work across writing, analysis, coding, and problem solving. It handles long contexts and multi-step tasks better than earlier versions, and it\u2019s tuned to give accurate responses with fewer errors. Supports 400k tokens of context, and native vision.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "OpenAI", "root": "gpt-5.2", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000015909", "completion": "0.0000127273", "image": null, "request": null, "input_cache_read": "0.0000001591", "input_cache_write": null}, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "GPT-5.2", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3054-200-ioeukwfyirwsvmffoxyxbdsdbnqjfivn.jpeg", "alt": "GPT-5.2 model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5.2"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}, {"name": "reasoning_effort", "schema": {"enum": ["none", "low", "medium", "high", "xhigh"]}, "default_value": "none"}, {"name": "verbosity", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "gemini-3-flash", "object": "model", "created": 1759803302884, "description": "Building on the reasoning capabilities of Gemini 3 Pro, Gemini 3 Flash is a powerful but affordable and performant model. It has exceptional world knowledge, multimodal understanding and reasoning capabilities at a fraction of the cost of equivalent models (as of December 2025).\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Google", "root": "gemini-3-flash", "architecture": {"input_modalities": ["text", "image", "video", "audio"], "output_modalities": ["text"], "modality": "text,image,video,audio->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.000000404", "completion": "0.0000024242", "image": null, "request": null, "input_cache_read": "0.0000000404", "input_cache_write": null}, "context_window": {"context_length": 1048576, "max_output_tokens": 65536}, "context_length": 1048576, "metadata": {"display_name": "Gemini-3-Flash", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6023-200-tmjxdrusvxhxxlsabsspmpthsjrtedpq.jpeg", "alt": "Gemini-3-Flash model icon", "width": 200, "height": 200}, "url": "https://poe.com/gemini-3-flash"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "thinking_level", "schema": {"enum": ["minimal", "low", "high"]}, "default_value": "low"}, {"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "gpt-5.2-instant", "object": "model", "created": 1765479696878, "description": "A fast, steady conversational model built for day-to-day use. It handles long threads without drifting, keeps context clean, and answers in a straightforward way. Good for planning, rewriting, summarizing, and quick technical help. Supports 400k tokens of context and native vision.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "OpenAI", "root": "gpt-5.2-instant", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000015909", "completion": "0.0000127273", "image": null, "request": null, "input_cache_read": "0.0000001591", "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": 16384}, "context_length": 128000, "metadata": {"display_name": "GPT-5.2-Instant", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3055-200-kwvylnhdgvpjdtdlpntwftpvfeiarivu.jpeg", "alt": "GPT-5.2-Instant model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5.2-instant"}, "reasoning": null, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "grok-4.1-fast-reasoning", "object": "model", "created": 1763585722548, "description": "Grok-4.1-Fast-Reasoning is a high-performance version of xAI\u2019s Grok\u202f4.1\u202fFast, the company\u2019s best agentic tool\u2011calling model. It works great in real-world use cases like customer support, deep research, and advanced analytical reasoning. Equipped with 2M\u2011token context window, this model processes vast information seamlessly, delivering coherent, context\u2011aware, and deeply reasoned insights at exceptional speed.", "owned_by": "XAI", "root": "grok-4.1-fast-reasoning", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.000000202", "completion": "0.0000005051", "image": null, "request": null, "input_cache_read": "0.0000000505", "input_cache_write": null}, "context_window": {"context_length": 2000000, "max_output_tokens": null}, "context_length": 2000000, "metadata": {"display_name": "Grok-4.1-Fast-Reasoning", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6597748-200-kkhryunydbqlontqwtlsbusethvuyego.jpeg", "alt": "Grok-4.1-Fast-Reasoning model icon", "width": 200, "height": 200}, "url": "https://poe.com/grok-4.1-fast-reasoning"}, "reasoning": null, "parameters": []}, {"id": "veo-3.1-lite", "object": "model", "created": 1774976562653, "description": "Google\u2019s Veo 3.1 Lite is the most cost-efficient model in the Veo 3.1 family, delivering high-quality video generation with native audio at a fraction of the cost. It supports both text-to-video and image-to-video workflows, with synchronized dialogue, sound effects, and ambient audio. While optimized for affordability, it still benefits from the Veo 3.1 generation\u2019s improved prompt adherence and cinematic understanding.\n\nThis bot supports optional parameters for additional customization.\n\nNote: 1080p requires 8s duration\nReference mode: Use up to 3 input images as references for video generation\nReference images require 8s duration\nPlease only upload photos that you own or have the right to use. Otherwise, the bot will return an error.", "owned_by": "Google", "root": "veo-3.1-lite", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["video"], "modality": "text,image->video"}, "supported_features": [], "supported_endpoints": ["/v1/videos"], "pricing": null, "context_window": {"context_length": 480, "max_output_tokens": null}, "context_length": 480, "metadata": {"display_name": "Veo-3.1-Lite", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6915732-200-ysfhzieddahakgceidzsedlsthcyyyvz.jpeg", "alt": "Veo-3.1-Lite model icon", "width": 200, "height": 200}, "url": "https://poe.com/veo-3.1-lite"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["16:9", "9:16"]}, "default_value": "16:9"}, {"name": "duration", "schema": {"enum": ["4", "6", "8"]}, "default_value": "8"}, {"name": "seed", "schema": {"type": "string"}}, {"name": "resolution", "schema": {"enum": ["720p", "1080p"]}, "default_value": "720p"}]}, {"id": "qwen3-max-thinking", "object": "model", "created": 1769457283480, "description": "Qwen3-Max-Thinking is a flagship reasoning model that integrates adaptive tool use, autonomously employing search, memory, and code interpretation to address complex tasks. It further optimizes performance through test-time scaling, a strategy that allocates additional computation during inference to improve reasoning accuracy and context efficiency.\nThis model is served by Alibaba Cloud Int. from Singapore.\n\nNotes:\n- Context window: 256K\n- Supported file types: PNG, JPG, JPEG, HEIC, PDF, TXT, DOC, DOCX\n- Audio/Video files are not supported.\n\nParameter controls available:\n1. Model Configuration\nThinking to let the model reason step-by-step before answering. It is `on`  by default.\n\n2. Tools\n- Web search to search the web for real-time info. It is `on` by default.\n- Web search mode. Select from `Standard` for efficient search or `Thorough` for comprehensive search. It is set to `Standard` by default (requires thinking enabled).\n- Web extractor to extract/read content from URLs (requires thinking enabled). It is `on` by default.\n- Code interpreter to run Python code in a sandbox (requires thinking enabled). It is `on` by default.", "owned_by": "EmpirioLabs AI", "root": "qwen3-max-thinking", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3-Max-Thinking", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6765424-200-iaxrjliquttidyreitgqikzjflxlassb.jpeg", "alt": "Qwen3-Max-Thinking model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3-max-thinking"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Model thinks step-by-step before responding. Recommended for complex reasoning, math, and coding tasks. Increases output tokens."}, {"name": "enable_web_search", "schema": {"type": "boolean"}, "default_value": true, "description": "Allow the model to search the web for current information."}, {"name": "web_search_mode", "schema": {"enum": ["standard", "thorough"]}, "default_value": "standard", "description": "Standard: efficient search. Thorough: comprehensive multi-step search (requires Deep Thinking)."}, {"name": "enable_code_interpreter", "schema": {"type": "boolean"}, "default_value": true, "description": "Execute Python code. Requires Deep Thinking."}, {"name": "enable_web_extractor", "schema": {"type": "boolean"}, "default_value": true, "description": "Extract URL content. Requires Deep Thinking."}]}, {"id": "grok-imagine-video", "object": "model", "created": 1769805671349, "description": "Create artistic and creative videos with Grok Imagine Video. Supports text to video, image to video (single jpeg/png/webp attachment), and video editing (single mp4 video attachment). Check parameter controls for all supported controls (resolution, video duration, and aspect_ratio).", "owned_by": "fal", "root": "grok-imagine-video", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": ["/v1/videos"], "pricing": null, "context_window": {"context_length": 256, "max_output_tokens": null}, "context_length": 256, "metadata": {"display_name": "Grok-Imagine-Video", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6774869-200-saxwogavkvozttjhagjaacioqlrtzkcg.jpeg", "alt": "Grok-Imagine-Video model icon", "width": 200, "height": 200}, "url": "https://poe.com/grok-imagine-video"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "3:2", "1:1", "2:3", "3:4", "9:16"]}, "default_value": "16:9"}, {"name": "duration", "schema": {"type": "number", "minimum": 1, "maximum": 8}, "default_value": 6}, {"name": "resolution", "schema": {"enum": ["auto", "480p", "720p"]}, "default_value": "720p", "description": "Resolution of the output video."}, {"name": "auto_aspect", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to automatically select the aspect ratio based on the input image/video. Only works with image/video attachments."}]}, {"id": "claude-sonnet-4.5", "object": "model", "created": 1758868894776, "description": "Claude Sonnet 4.5 represents a major leap forward in AI capability and alignment. It is the most advanced model released by Anthropic to date, distinguished by dramatic improvements in reasoning, mathematics, and real-world coding. Supports 1m tokens of context.", "owned_by": "Anthropic", "root": "claude-sonnet-4.5", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/messages", "/v1/responses", "/v1/chat/completions"], "pricing": {"prompt": "0.0000025758", "completion": "0.0000128788", "image": null, "request": null, "input_cache_read": "0.0000002576", "input_cache_write": "0.0000032197"}, "context_window": {"context_length": 983040, "max_output_tokens": 32768}, "context_length": 983040, "metadata": {"display_name": "Claude-Sonnet-4.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-1038-200-hvgoplfizexakailvxqusqblfeuchxsd.jpeg", "alt": "Claude-Sonnet-4.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/claude-sonnet-4.5"}, "reasoning": {"budget": {"max_tokens": 31999, "min_tokens": 0}, "required": false, "supports_reasoning_effort": false}, "parameters": [{"name": "thinking_budget", "schema": {"type": "number", "minimum": 0, "maximum": 31999}, "default_value": 0, "description": "The maximum number of tokens to spend on thinking."}, {"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "seedream-5.0-lite", "object": "model", "created": 1772025732993, "description": "Seedream 5.0 Lite is ByteDance's latest text-to-image model with greater intelligence. Seedream 5.0 Lite can also take in  multiple images as references and combine them together or edit them to return an output. \n\nOptional parameters:\nSet the aspect ratio for the model (One of `16:9`, `4:3`, `1:1`, `3:4`, `9:16`).", "owned_by": "Bytedance", "root": "seedream-5.0-lite", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Seedream-5.0-Lite", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6832169-200-cipadhokqkmwwcqlavyguxtmkjucdkau.jpeg", "alt": "Seedream-5.0-Lite model icon", "width": 200, "height": 200}, "url": "https://poe.com/seedream-5.0-lite"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "kling-v3-motion-ctrl", "object": "model", "created": 1773103662749, "description": "Kling v3 Motion Control uses Kuaishou's Kling 3.0 model to transfer motion from a reference video onto a character from a reference image, generating a new video where the subject performs the movements with high fidelity and temporal consistency with support for Standard (720p) and Pro (1080p) quality tiers.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "kling-v3-motion-ctrl", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Kling-v3-Motion-Ctrl", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6862938-200-quaixmwkghzghccwaankouzxipvsoyjw.jpeg", "alt": "Kling-v3-Motion-Ctrl model icon", "width": 200, "height": 200}, "url": "https://poe.com/kling-v3-motion-ctrl"}, "reasoning": null, "parameters": [{"name": "mode", "schema": {"enum": ["pro", "std"]}, "default_value": "std", "description": "Pro \u2013 1080p, higher fidelity output. Standard \u2013 720p, faster and more affordable."}, {"name": "character_orientation", "schema": {"enum": ["image", "video"]}, "default_value": "image", "description": "Image \u2013 character starts in the pose from your reference image (max 10 s video).  Video \u2013 character matches the pose of the person in the reference video (max 30 s video)."}, {"name": "keep_original_sound", "schema": {"type": "boolean"}, "default_value": true, "description": "Keep the audio track from the reference video in the generated output."}]}, {"id": "runway-gen-4.5", "object": "model", "created": 1769636825513, "description": "Runway Gen 4.5 is an advanced video model that generates cinematic, high\u2011fidelity video from natural language and images. It offers fine\u2011grained control over motion, camera behavior, composition, and style, producing physically realistic and temporally consistent scenes.\n\nOptional parameters:\nSet aspect ratio. Select from (21:9, 16:9, 4:3, 1:1, 3:4, 9:16). It is set to 16:9 aspect ratio as default.\nSet Duration. Select from (5 seconds, 8 seconds, 10 seconds) to specify video length in seconds. Set to 5 seconds as default.", "owned_by": "RunwayML", "root": "runway-gen-4.5", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": ["/v1/videos"], "pricing": null, "context_window": {"context_length": 256, "max_output_tokens": null}, "context_length": 256, "metadata": {"display_name": "Runway-Gen-4.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6770327-200-qwnqmpvnklwwbbwtdgprpkgjauhzacqy.jpeg", "alt": "Runway-Gen-4.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/runway-gen-4.5"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["16:9", "9:16", "1:1", "4:3", "3:4", "21:9"]}, "default_value": "16:9"}, {"name": "duration", "schema": {"enum": ["5", "8", "10"]}, "default_value": "5"}]}, {"id": "qwen3-coder-next", "object": "model", "created": 1770157079067, "description": "Qwen3-Coder-Next is an open-weight language model specifically engineered for coding agents and local development environments. This highly efficient model delivers exceptional performance with only 3B activated parameters out of 80B total parameters, achieving results comparable to models with 10-20x more active parameters while maintaining remarkable cost-effectiveness for agent deployment. Through its sophisticated training methodology, Qwen3-Coder-Next excels in advanced agentic capabilities including long-horizon reasoning, complex tool usage, and robust recovery from execution failures, ensuring reliable performance across dynamic coding tasks. The model's versatility is further enhanced by its 256k context length and adaptability to various scaffold templates, enabling seamless integration with diverse CLI/IDE platforms such as Claude Code, Qwen Code, Qoder, Kilo, Trae, and Cline, making it an ideal solution for comprehensive development environments.\n\nOptional parameters:\nSet temperature to control randomness in the response: Set number from 1 to 2.  This is set to 0.7 by default. Lower values make the output more focused and deterministic.\nSet max output tokens: Set number from 1 to 65536. This is set to 65536 by default.", "owned_by": "Novita AI", "root": "qwen3-coder-next", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.000000202", "completion": "0.0000015152", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3-Coder-Next", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6784074-200-sonuttgoxmrcqyecpbzgxruzhipcajfm.jpeg", "alt": "Qwen3-Coder-Next model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3-coder-next"}, "reasoning": null, "parameters": [{"name": "temperature", "schema": {"type": "number", "minimum": 0, "maximum": 2}, "default_value": 0.7, "description": "Controls randomness in the response. Lower values make the output more focused and deterministic."}, {"name": "max_output_tokens", "schema": {"type": "number", "minimum": 1, "maximum": 65536}, "default_value": 65536.0, "description": "Maximum number of tokens to generate in the response."}]}, {"id": "minimax-m2.5", "object": "model", "created": 1770910818129, "description": "MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.\n\nContext window: 205k tokens\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Novita AI", "root": "minimax-m2.5", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.000000303", "completion": "0.0000012121", "image": null, "request": null, "input_cache_read": "0.0000000303", "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Minimax-M2.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6804219-200-ijeualnurqajzhlmprlofqopbkcgssib.jpeg", "alt": "Minimax-M2.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/minimax-m2.5"}, "reasoning": null, "parameters": [{"name": "temperature", "schema": {"type": "number", "minimum": 0, "maximum": 2}, "default_value": 0.7, "description": "Controls randomness in the response. Lower values make the output more focused and deterministic."}, {"name": "max_output_tokens", "schema": {"type": "number", "minimum": 1, "maximum": 131100}, "default_value": 131100, "description": "Maximum number of tokens to generate in the response."}]}, {"id": "grok-4.1-fast-non-reasoning", "object": "model", "created": 1763585662409, "description": "Grok-4.1-Fast-Non-Reasoning is a streamlined companion to Grok\u202f4.1\u202fFast, xAI\u2019s best agentic tool\u2011calling model. It has 2M context window and high responsiveness but is optimized for non\u2011reasoning tasks \u2014 excelling at text generation, summarization, and automated workflows that demand speed and efficiency over deep logic. Ideal for high-throughput use cases like customer support automation, bulk content creation, and fast conversational responses.", "owned_by": "XAI", "root": "grok-4.1-fast-non-reasoning", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.000000202", "completion": "0.0000005051", "image": null, "request": null, "input_cache_read": "0.0000000505", "input_cache_write": null}, "context_window": {"context_length": 2000000, "max_output_tokens": null}, "context_length": 2000000, "metadata": {"display_name": "Grok-4.1-Fast-Non-Reasoning", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6597745-200-dzxfpprbwqnpjfdgiungnkscddycdnub.jpeg", "alt": "Grok-4.1-Fast-Non-Reasoning model icon", "width": 200, "height": 200}, "url": "https://poe.com/grok-4.1-fast-non-reasoning"}, "reasoning": null, "parameters": []}, {"id": "kimi-k2-thinking", "object": "model", "created": 1762485029151, "description": "The kimi-k2-thinking model is a general-purpose agentic reasoning model developed by Moonshot AI. \n\nFile Support: Text, Markdown and PDF files\nContext window: 262k tokens", "owned_by": "Novita AI", "root": "kimi-k2-thinking", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000006061", "completion": "0.0000025253", "image": null, "request": null, "input_cache_read": "0.0000001515", "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Kimi-K2-Thinking", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6563264-200-rdevwoigqgyhouhdkfpbolhewkqppmrr.jpeg", "alt": "Kimi-K2-Thinking model icon", "width": 200, "height": 200}, "url": "https://poe.com/kimi-k2-thinking"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": false, "description": "This will cause the model to think..."}, {"name": "temperature", "schema": {"type": "number", "minimum": 0, "maximum": 2}, "default_value": 0.7, "description": "Controls randomness in the response. Lower values make the output more focused and deterministic."}, {"name": "max_output_tokens", "schema": {"type": "number", "minimum": 1, "maximum": 262144}, "default_value": 262144.0, "description": "Maximum number of tokens to generate in the response."}]}, {"id": "glm-5.1-t", "object": "model", "created": 1775682073807, "description": "GLM-5.1 is Z.ai's next-generation flagship model for agentic engineering. It achieves state-of-the-art on SWE-Bench Pro and leads GLM-5 by a wide margin on NL2Repo and Terminal-Bench 2.0. The real breakthrough, though, is endurance. Previous models plateau early \u2014 they apply familiar techniques for quick gains, then stall. More time doesn't help. GLM-5.1 stays productive over far longer horizons, breaking down ambiguous problems, running experiments, reading results, and revising its strategy with real precision. Across hundreds of rounds and thousands of tool calls, it keeps optimizing. The longer it runs, the better the result.", "owned_by": "Together AI", "root": "glm-5.1-t", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.00", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "GLM-5.1-T", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6928677-200-eguxuhpkqgoypnrtdyywoqxwmjarxsjo.jpeg", "alt": "GLM-5.1-T model icon", "width": 200, "height": 200}, "url": "https://poe.com/glm-5.1-t"}, "reasoning": null, "parameters": []}, {"id": "gpt-5.2-codex", "object": "model", "created": 1768427021441, "description": "GPT\u20115.2\u2011Codex extends GPT\u20115.2\u2019s capabilities for software development. It understands complex codebases, provides accurate completions, explains algorithms, and assists with debugging across modern programming languages. Designed for developers, it elevates productivity and supports full\u2011stack coding workflows with precision. Supports 400k tokens of input context.\n\nOptional parameters:\nSet reasoning effort: Select from  `low`, `medium`, `high`, `xhigh`. This is set to `medium` by default.", "owned_by": "OpenAI", "root": "gpt-5.2-codex", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000015909", "completion": "0.0000127273", "image": null, "request": null, "input_cache_read": "0.0000001591", "input_cache_write": null}, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "GPT-5.2-Codex", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3057-200-nmskwcorivwjuubipstvqqbbhsvjzwhw.jpeg", "alt": "GPT-5.2-Codex model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5.2-codex"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high", "xhigh"]}, "default_value": "medium"}]}, {"id": "deepseek-v3.2", "object": "model", "created": 1764585257709, "description": "We introduce DeepSeek-V3.2, a next-generation foundation model designed to unify high computational efficiency with state-of-the-art reasoning and agentic performance. DeepSeek-V3.2 is built upon three core technical breakthroughs:\n\n\u2022 DeepSeek Sparse Attention (DSA):\nA new highly efficient attention mechanism that significantly reduces computational overhead while preserving model quality, purpose-built for long-context reasoning and high-throughput workloads.\n\n\u2022 Scalable Reinforcement Learning Framework:\nDeepSeek-V3.2 leverages a robust RL training protocol and expanded post-training compute to reach GPT-5-level performance. Its high-compute variant, DeepSeek-V3.2-Speciale, surpasses GPT-5 and demonstrates reasoning capabilities comparable to Gemini-3.0-Pro.\n\n\u2022 Large-Scale Agentic Task Synthesis Pipeline:\nTo enable reliable tool-use and multi-step decision-making, we develop a novel agentic data synthesis pipeline that generates high-quality interactive reasoning tasks at scale, greatly enhancing the model\u2019s\n\nFile Support: Text, Markdown and PDF files\nContext window: 164k tokens", "owned_by": "Novita AI", "root": "deepseek-v3.2", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000002717", "completion": "0.000000404", "image": null, "request": null, "input_cache_read": "0.0000001359", "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "DeepSeek-V3.2", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6632595-200-zjfoedfpabhdybodxxoirwfxbnhgnepz.jpeg", "alt": "DeepSeek-V3.2 model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepseek-v3.2"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "This will cause the model to think about the response before giving a final answer."}]}, {"id": "gemma-4-31b-t", "object": "model", "created": 1775698044531, "description": "Gemma 4 models are designed to deliver frontier-level performance at each size, targeting deployment scenarios on consumer GPUs and workstations. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.", "owned_by": "Together AI", "root": "gemma-4-31b-t", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.00", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Gemma-4-31B-T", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6928893-200-yvrkalnmcyryubzlfbjdyvtzedcdizhq.jpeg", "alt": "Gemma-4-31B-T model icon", "width": 200, "height": 200}, "url": "https://poe.com/gemma-4-31b-t"}, "reasoning": null, "parameters": []}, {"id": "grok-4", "object": "model", "created": 1752143407651, "description": "Grok 4 is xAI's latest and most intelligent language model. It features state-of-the-art capabilities in coding, reasoning, and answering questions. It excels at handling complex and multi-step tasks. Reasoning traces are not available via the xAI API.", "owned_by": "XAI", "root": "grok-4", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000030303", "completion": "0.0000151515", "image": null, "request": null, "input_cache_read": "0.0000007576", "input_cache_write": null}, "context_window": {"context_length": 256000, "max_output_tokens": null}, "context_length": 256000, "metadata": {"display_name": "Grok-4", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6210158-200-lxepzmfzmkadvenvwgzminlczywoxhom.jpeg", "alt": "Grok-4 model icon", "width": 200, "height": 200}, "url": "https://poe.com/grok-4"}, "reasoning": null, "parameters": []}, {"id": "gpt-image-1.5", "object": "model", "created": 1765850472161, "description": "OpenAI's frontier image generation model in ChatGPT as of December 2025, offering exceptional prompt adherence, world knowledge, precise edits, facial preservation, level of detail, and overall quality with improved latency/generation times. It supports editing, restyling, and combining images attached to the latest user query. For a conversational image generation and editing experience use: https://poe.com/GPT-5.2\n\nOptional Parameters:\nSet aspect ratio, with options 3:2, 1:1 and 2:3. \nSet quality to low, medium and high. Default is set to high.\nEnable use mask by toggling it on or by typing 'use_mask' in the prompt. This option is turned off by default.\nDisable high fidelity by toggling it off or by typing 'use_high_fidelity'. This option is turned on by default.", "owned_by": "OpenAI", "root": "gpt-image-1.5", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": ["/v1/images"], "pricing": null, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "GPT-Image-1.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6672155-200-wxaffodsvussaktjknijciktnwlyzxyz.jpeg", "alt": "GPT-Image-1.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-image-1.5"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["1:1", "3:2", "2:3"]}}, {"name": "quality", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "high"}, {"name": "use_mask", "schema": {"type": "boolean"}, "default_value": false, "description": "Indicates that the last attached image is a mask for inpainting (editing specific regions). The mask must match the dimensions of the base image, with transparent (zero-alpha) areas showing which parts to edit."}, {"name": "use_high_fidelity", "schema": {"type": "boolean"}, "default_value": true, "description": "High input fidelity allows you to make subtle edits to an image without altering unrelated areas. This is ideal for controlled, localized changes."}]}, {"id": "claude-code", "object": "model", "created": 1764280744155, "description": "A powerful assistant that can read, write, and analyze files across many formats.  It can also delegate to other Poe bots to handle complex, multi-step tasks.\n\nBuilt on the Claude Agent SDK from Anthropic.", "owned_by": "Poe Tools", "root": "claude-code", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Claude-Code", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6624122-200-eqzlivkawkxozndgzdufnolrgzrwlgko.jpeg", "alt": "Claude-Code model icon", "width": 200, "height": 200}, "url": "https://poe.com/claude-code"}, "reasoning": null, "parameters": [{"name": "model", "schema": {"enum": ["claude-sonnet-4-5", "claude-opus-4-6", "claude-opus-4-7", "claude-haiku-4-5"]}, "default_value": "claude-sonnet-4-5", "description": "Select the Claude model to use."}, {"name": "thinking_budget", "schema": {"type": "number", "minimum": 0, "maximum": 31999}, "default_value": 4096, "description": "The maximum number of tokens to spend on thinking."}, {"name": "effort", "schema": {"enum": ["max", "high", "medium", "low", "none", "xhigh"]}, "default_value": "high"}, {"name": "thinking_display", "schema": {"enum": ["omitted", "summarized"]}, "default_value": "omitted"}, {"name": "task_budget", "schema": {"type": "number", "minimum": 20000, "maximum": 1048576}, "default_value": 128000, "description": "Advisory token budget for agentic turns. The model will attempt to stay within budget."}]}, {"id": "minimax-m2.1", "object": "model", "created": 1766743140197, "description": "MiniMax M2.1 is a cutting-edge AI model designed to revolutionize how developers build software. With enhanced multi-language programming support, it excels in generating high-quality code across popular languages like Rust, Java, Golang, C++, Kotlin, Objective-C, TypeScript, and JavaScript.\n\nKey improvements include:\n\n22% faster response times and 30% lower token consumption for efficient workflows.\nSeamless integration with leading development frameworks (Claude Code, Droid Factory AI, BlackBox, etc.).\nFull-stack development capabilities, from mobile (Android/iOS) to web and 3D interactive prototyping.\nOptimized performance-to-cost ratio, making AI-assisted development more accessible.\nWhether you're a software engineer, app developer, or tech innovator, M2.1 empowers smarter coding with industry-leading AI.\n\nContext window: 205k tokens\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Novita AI", "root": "minimax-m2.1", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.000000303", "completion": "0.0000012121", "image": null, "request": null, "input_cache_read": "0.0000000303", "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Minimax-M2.1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6696121-200-cxyzlwpzarivcurfdfyucjcynxxzouzs.jpeg", "alt": "Minimax-M2.1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/minimax-m2.1"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": false, "description": "This will cause the model to think before providing a response."}, {"name": "temperature", "schema": {"type": "number", "minimum": 0, "maximum": 2}, "default_value": 0.7, "description": "Controls randomness in the response. Lower values make the output more focused and deterministic."}, {"name": "max_output_tokens", "schema": {"type": "number", "minimum": 1, "maximum": 131072}, "default_value": 131072.0, "description": "Maximum number of tokens to generate in the response."}]}, {"id": "qwen-image-2.0", "object": "model", "created": 1772682269871, "description": "Qwen Image 2.0 is Alibaba's unified image generation and editing model, excelling at complex text rendering in both Chinese and English, realistic textures, precise semantic adherence, and multi-image fusion. The Pro variant delivers enhanced detail fidelity and professional-grade text-in-image accuracy, while the Standard variant balances quality with faster response times.\n\nNotes:\n- This model is served from the Singapore region.\n- Upload 1-3 images to enable image editing mode. Without images, the bot operates in text-to-image generation mode.\n- Responses may take 10-30 seconds depending on resolution, number of images, and prompt complexity.\n- Positive prompt has a max of 800 characters, negative prompt has a max of 500 characters. \n\nAttachments (Image Editing Mode):\n- Attach 1-3 images (JPEG, PNG, BMP, WEBP, TIFF, GIF) with a text instruction to edit them.\n- For best results, input image resolution should be between 384 and 3072 pixels per side.\n- Maximum file size per image: 10 MB.\n- Multi-image editing: Reference images by order (e.g. \"The girl in Image 1 wears the dress from Image 2 and sits in the pose from Image 3\") (images should be referenced in the order they are uploaded by).\n- Supported editing operations: style transfer, text modification, object addition/removal, pose changes, background replacement, viewpoint transformation, sketch-to-image, depth map generation, and more.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "qwen-image-2.0", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen-Image-2.0", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6851147-200-ciefdezxmcgjdysoyyodtyztpydakoul.jpeg", "alt": "Qwen-Image-2.0 model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen-image-2.0"}, "reasoning": null, "parameters": [{"name": "model", "schema": {"enum": ["qwen-image-2.0-pro-2026-04-22", "qwen-image-2.0-pro-2026-03-03", "qwen-image-2.0"]}, "default_value": "qwen-image-2.0-pro-2026-04-22", "description": "Pro costs more and offers stronger text rendering, realism, and semantic adherence. Standard is cheaper but lower quality."}, {"name": "aspect_ratio", "schema": {"enum": ["16:9", "9:16", "1:1", "3:2", "2:3", "4:3", "3:4", "5:4", "4:5"]}, "description": "Optional: if selected, this size is sent. If not selected: text-to-image defaults to 16:9; image editing uses model defaults based on input image ratio (for multiple images, the last image determines ratio). 16:9 = 1920x1080 \u00b7 3:2 = 1536x1024 \u00b7 4:3 = 1440x1080 \u00b7 5:4 = 1280x1024 \u00b7 1:1 = 1024x1024 \u00b7 4:5 = 1024x1280 \u00b7 3:4 = 1080x1440 \u00b7 2:3 = 1024x1536 \u00b7 9:16 = 1080x1920"}, {"name": "use_custom_size", "schema": {"type": "boolean"}, "default_value": false, "description": "Override aspect ratio with custom pixel dimensions (512-2048 per side)."}, {"name": "custom_width", "schema": {"type": "string"}, "default_value": "1920", "description": "Width in pixels (512-2048)"}, {"name": "custom_height", "schema": {"type": "string"}, "default_value": "1080", "description": "Height in pixels (512-2048)"}, {"name": "num_images", "schema": {"type": "number", "minimum": 1, "maximum": 6}, "default_value": 1, "description": "Generate 1 to 6 images per request. Each image is billed separately."}, {"name": "prompt_extend", "schema": {"type": "boolean"}, "default_value": true, "description": "Automatically optimize short prompts for better results. Adds 3-5 seconds of latency."}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "", "description": "Describe content to exclude from the generated image."}, {"name": "seed", "schema": {"type": "string"}, "default_value": "", "description": "Random seed for reproducible results (0-2147483647). Leave empty for random."}, {"name": "watermark", "schema": {"type": "boolean"}, "default_value": false, "description": "Add a Qwen-Image watermark to the bottom-right corner."}]}, {"id": "perplexity-adv-deep-research", "object": "model", "created": 1770838387525, "description": "Perplexity Advanced Deep Research is designed for institutional-grade inquiry, leveraging the powerful reasoning of Claude Opus 4.6 to deliver sophisticated analysis and maximum depth. With enhanced tool access and extensive source coverage, it is the ideal choice for complex tasks requiring rigorous, comprehensive research.\n\nSupported file types: PNG, JPEG, WEBP, GIF, PDF, DOCX, TXT\n\nParameter controls available:\n1. General\n- Reasoning effort [low/medium/high]: Level of reasoning depth (default: high)\n- Max output tokens [10000-16000]: Maximum response length in tokens (default: 10000)\n- Max tokens per page [4096-16384]: Max tokens extracted per search result page (default: 4096)\n\n2. Search Filters\n- Search domain filter [domains]: Comma-separated domains to include/exclude. Prefix with '-' to exclude. Max 20. (e.g., \"nature.com, arxiv.org, -pinterest.com\")\n- Search language filter [codes]: Comma-separated ISO 639-1 language codes. Max 10. (e.g., \"en, fr, de\")\n\n3. Date & Recency\n- Search after date [MM/DD/YYYY]: Only include sources published after this date\n- Search before date [MM/DD/YYYY]: Only include sources published before this date\n- Search recency filter [none/day/week/month/year]: Relative time filter (cannot be combined with specific dates)\n\n4. Location\n- Country [code]: Two-letter ISO 3166-1 country code (e.g., \"US\", \"FR\", \"JP\")\n- Region [name]: State or province (e.g., \"California\")\n- City [name]: City name (e.g., \"San Francisco\")\n- Latitude [decimal]: Latitude (must be provided with longitude and country)\n- Longitude [decimal]: Longitude (must be provided with latitude and country)", "owned_by": "EmpirioLabs AI", "root": "perplexity-adv-deep-research", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Perplexity-Adv-Deep-Research", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6802305-200-qogfjfjcwzoabbhjcvbghtsbeioxgacj.jpeg", "alt": "Perplexity-Adv-Deep-Research model icon", "width": 200, "height": 200}, "url": "https://poe.com/perplexity-adv-deep-research"}, "reasoning": null, "parameters": [{"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "high", "description": "Level of reasoning depth. Higher effort = more thorough analysis."}, {"name": "max_output_tokens", "schema": {"type": "number", "minimum": 10000, "maximum": 16000}, "default_value": 10000, "description": "Maximum length of the response (higher = longer reports)."}, {"name": "max_tokens_per_page", "schema": {"type": "number", "minimum": 4096, "maximum": 16384}, "default_value": 4096, "description": "Max tokens extracted per search result page. Higher = more content per source but slower. Default is 4096."}, {"name": "search_domain_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated domains. Prefix with '-' to exclude. Max 20."}, {"name": "search_language_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated ISO 639-1 codes (2 letters). Max 10."}, {"name": "search_after_date", "schema": {"type": "string"}, "default_value": "", "description": "Only include sources published after this date."}, {"name": "search_before_date", "schema": {"type": "string"}, "default_value": "", "description": "Only include sources published before this date."}, {"name": "search_recency_filter", "schema": {"enum": ["none", "day", "week", "month", "year"]}, "default_value": "none", "description": "Relative time filter. Cannot be combined with specific dates."}, {"name": "country", "schema": {"type": "string"}, "default_value": "", "description": "Two-letter ISO 3166-1 code."}, {"name": "region", "schema": {"type": "string"}, "default_value": "", "description": "State or province."}, {"name": "city", "schema": {"type": "string"}, "default_value": ""}, {"name": "latitude", "schema": {"type": "string"}, "default_value": "", "description": "Must be provided with Longitude and Country."}, {"name": "longitude", "schema": {"type": "string"}, "default_value": "", "description": "Must be provided with Latitude and Country."}]}, {"id": "deepseek-v3.2-el", "object": "model", "created": 1775491301503, "description": "DeepSeek V3.2 is a powerful open-source large language model designed to compete with top-tier models on reasoning, coding, and general language tasks. Built on a Mixture-of-Experts (MoE) architecture, it delivers strong performance while remaining highly efficient to run.\nThis model is served by Alibaba Cloud Int. from Singapore.\n\nNotes:\n- Context Window: 128K\n- Supported input modalities: Text, Image (non-native), Documents\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "deepseek-v3.2-el", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "DeepSeek-V3.2-EL", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6924965-200-ixqqwjruoeiqqsxbremcdmhxcyusiiqi.jpeg", "alt": "DeepSeek-V3.2-EL model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepseek-v3.2-el"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Let the model reason step-by-step before answering"}, {"name": "thinking_budget", "schema": {"type": "number", "minimum": 1, "maximum": 32768}, "default_value": 32768, "description": "Maximum tokens for the thinking process (higher = deeper reasoning, more output tokens)"}, {"name": "enable_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Search the web for real-time information before answering (adds latency)"}]}, {"id": "perplexity-search", "object": "model", "created": 1771723986988, "description": "Utilize Perplexity's technology for real-time web search with filtering by domain, language, date and more.\nNote: This endpoint does not return an LLM-style response. File upload is not supported.\n\nParameter Controls Available:\n1. General\n   - `query` (required): Your search query as a single string\n   - `multi_query`: Up to 5 queries separated by newlines for batch searching\n   - `max_results` [1-20]: Number of search results to return (default 5)\n   - `max_tokens` [5000-100000]: Total content token budget across all results\n   - `max_tokens_per_page` [256-8192]: Maximum tokens extracted per individual page\n\n2. Filters\n   - `search_domain_filter`: Allow or deny specific domains (prefix with `-` to deny, max 20, no mixing allow/deny)\n   - `search_language_filter`: Restrict results by language using ISO 639-1 codes (e.g. `en`, `fr`), comma-separated, max 10\n   - `country`: Restrict results by country using ISO 3166-1 alpha-2 code (e.g. `US`, `GB`)\n\n3. Date & Recency\n   - `search_recency_filter`: Limit results to `hour`, `day`, `week`, `month`, or `year`\n   - `search_after_date_filter` (MM/DD/YYYY): Only return results published after this date (overrides recency)\n   - `search_before_date_filter` (MM/DD/YYYY): Only return results published before this date (overrides recency)\n   - `last_updated_after_filter` (MM/DD/YYYY): Only return results last updated after this date\n   - `last_updated_before_filter` (MM/DD/YYYY): Only return results last updated before this date\n   - `display_server_time`: Toggle to include the server timestamp in the response", "owned_by": "EmpirioLabs AI", "root": "perplexity-search", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Perplexity-Search", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6824178-200-emrwrxuurgkbjyukiwkmzfokhvbkbwfr.jpeg", "alt": "Perplexity-Search model icon", "width": 200, "height": 200}, "url": "https://poe.com/perplexity-search"}, "reasoning": null, "parameters": [{"name": "max_results", "schema": {"type": "number", "minimum": 1, "maximum": 20}, "default_value": 10, "description": "Maximum number of search results to return (1-20). Note: The API may return fewer results than requested depending on the query."}, {"name": "multi_query_mode", "schema": {"type": "boolean"}, "default_value": false, "description": "Send multiple queries in one request. Enter one query per line (max 5)."}, {"name": "max_tokens", "schema": {"enum": ["10000", "50000", "100000", "500000", "1000000"]}, "default_value": "1000000", "description": "Total token budget across all results. Higher values return longer snippets. No per-token cost."}, {"name": "max_tokens_per_page", "schema": {"enum": ["256", "512", "1024", "2048", "4096", "8192"]}, "default_value": "4096", "description": "Content extraction limit per individual result page."}, {"name": "country", "schema": {"type": "string"}, "default_value": "", "description": "ISO 3166-1 alpha-2 country code for geographically relevant results."}, {"name": "display_server_time", "schema": {"type": "boolean"}, "default_value": false, "description": "Include server processing timestamp in the response."}, {"name": "search_domain_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated domains. Allowlist (example.com) or denylist (-example.com). Max 20. Cannot mix modes."}, {"name": "search_language_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated ISO 639-1 codes (2 lowercase letters). Max 10."}, {"name": "search_recency_filter", "schema": {"enum": ["none", "hour", "day", "week", "month", "year"]}, "default_value": "none", "description": "Filter by relative time period. Overridden by specific publication dates if both are set."}, {"name": "search_after_date_filter", "schema": {"type": "string"}, "default_value": "", "description": "Only include content published after this date. Takes priority over recency filter."}, {"name": "search_before_date_filter", "schema": {"type": "string"}, "default_value": "", "description": "Only include content published before this date."}, {"name": "last_updated_after_filter", "schema": {"type": "string"}, "default_value": "", "description": "Only include content last modified after this date."}, {"name": "last_updated_before_filter", "schema": {"type": "string"}, "default_value": "", "description": "Only include content last modified before this date."}]}, {"id": "wan2.7-image", "object": "model", "created": 1775077688892, "description": "Wan2.7 Image is Alibaba's Wan 2.7 series image generation and editing model, supporting text-to-image, image editing, interactive editing with bounding boxes, and cohesive image set generation from a single prompt. The Pro variant supports up to 4K output resolution with enhanced quality, while the Standard variant offers faster generation at lower cost.\n\nNotes:\n- This model is served from the Singapore region.\n- Upload 1-9 images to enable image editing mode. Without images, the bot operates in text-to-image generation mode.\n- Responses may take 10-60 seconds depending on resolution, number of images, model variant, and whether thinking mode is enabled.\n- Prompt has a max of 5,000 characters.\n\nAttachments (Image Editing Mode):\n- Attach 1-9 images (JPEG, PNG, BMP, WEBP) with a text instruction to edit them.\n- Input image resolution must be between 240-8000 pixels per side with an aspect ratio between 1:8 and 8:1.\n- Maximum file size per image: 20 MB.\n- Multi-image editing: Reference images by order (e.g. \"Spray the graffiti from image 2 onto the car in image 1\").\n- Interactive editing: Use bounding boxes to specify regions on images for targeted edits (e.g. \"Place the object from image 1 in the selected area of image 2\").\n- Supported operations: style transfer, object placement, graffiti/texture application, scene blending, background replacement, multi-reference composition, and more.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "wan2.7-image", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Wan2.7-Image", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6917596-200-gpyyoixnyfpgzxhvvmlkmdabujsogvxi.jpeg", "alt": "Wan2.7-Image model icon", "width": 200, "height": 200}, "url": "https://poe.com/wan2.7-image"}, "reasoning": null, "parameters": [{"name": "model", "schema": {"enum": ["wan2.7-image-pro", "wan2.7-image"]}, "default_value": "wan2.7-image-pro", "description": "Pro: supports 4K, enhanced quality, thinking mode. Standard: faster generation, lower cost."}, {"name": "aspect_ratio", "schema": {"enum": ["16:9", "1:1", "9:16", "3:2", "2:3", "4:3", "3:4", "5:4", "4:5"]}, "description": "Optional: if selected, this size is used at the chosen resolution. If not selected: text-to-image defaults to 16:9; image editing matches the last input image's native ratio."}, {"name": "resolution", "schema": {"enum": ["1K", "2K", "4K"]}, "default_value": "2K", "description": "Output quality tier. 1K: ~1 megapixel | 2K: ~4 megapixels | 4K: ~16 megapixels (Pro text-to-image only). Actual dimensions depend on aspect ratio."}, {"name": "use_custom_size", "schema": {"type": "boolean"}, "default_value": false, "description": "Override aspect ratio and resolution with exact pixel dimensions. Aspect ratio must be between 1:8 and 8:1."}, {"name": "custom_width", "schema": {"type": "string"}, "default_value": "2048", "description": "Width in pixels (768-2048). Pro text-to-image allows up to 4096."}, {"name": "custom_height", "schema": {"type": "string"}, "default_value": "2048", "description": "Height in pixels (768-2048). Pro text-to-image allows up to 4096."}, {"name": "enable_sequential", "schema": {"type": "boolean"}, "default_value": false, "description": "Generate a cohesive set of related images from a single prompt. Unlocks up to 12 images. Disables Thinking Mode and Color Palette. Describe each image sequentially in your prompt (e.g. 'First image: ... Second image: ...')."}, {"name": "num_images", "schema": {"type": "number", "minimum": 1, "maximum": 4}, "default_value": 1, "description": "How many images to generate. Each image is billed separately."}, {"name": "num_images_set", "schema": {"type": "number", "minimum": 1, "maximum": 12}, "default_value": 1, "description": "Maximum images in the set. The model decides the actual count (up to this limit). You're only billed for images actually generated."}, {"name": "thinking_mode", "schema": {"type": "boolean"}, "default_value": true, "description": "Enhanced inference for better image quality at the cost of longer generation time. Automatically ignored when images are attached."}, {"name": "seed", "schema": {"type": "string"}, "default_value": "", "description": "Random seed for reproducible results (0\u20132147483647). Leave empty for random. Note: results may still vary slightly."}, {"name": "color_palette", "schema": {"type": "string"}, "default_value": "", "description": "Optional custom color theme. JSON array of 3\u201310 objects with hex and ratio fields. Ratios must sum to 100.00%. Example: [{\"hex\":\"#C2D1E6\",\"ratio\":\"60.00%\"},{\"hex\":\"#636574\",\"ratio\":\"40.00%\"}]"}, {"name": "bbox_list", "schema": {"type": "string"}, "default_value": "", "description": "Interactive editing: define regions on input images. JSON array with one entry per input image. Use [] for no box, [[x1,y1,x2,y2]] for one box (max 2 per image). Coordinates are absolute pixels (top-left origin)."}]}, {"id": "qwen-image-2-pro", "object": "model", "created": 1772745663512, "description": "Qwen-Image-2-Pro is Alibaba's latest image generation model. This model can edit images (png/jpeg/webp, maximum of 3 images).\n\nThis bot supports optional parameters for additional customization.", "owned_by": "fal", "root": "qwen-image-2-pro", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen-Image-2-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6853007-200-nkddnsylopmhaymatbfnyintscoxnvzq.jpeg", "alt": "Qwen-Image-2-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen-image-2-pro"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "pixverse-v5.6", "object": "model", "created": 1771637794517, "description": "PixVerse v5.6 is capable of creating high-quality videos from text prompts alone or by animating uploaded images (1 or 2 frames). It supports resolutions up to 1080p, multiple aspect ratios, durations of 5\u201310 seconds, optional synchronized audio, and the ability to control style presets, thinking mode, negative prompts, and seed-based reproducibility.\n\nParameter controls available:\n1. Basic\n- Default: text-to-video (no images needed)\n- If animating from image(s): attach 1 image (first frame) or 2 images (first + last frame)\n- Resolution [360p | 540p | 720p | 1080p]` (default: 1080p)\n- Aspect ratio [16:9 | 4:3 | 1:1 | 3:4 | 9:16]` (default: 16:9) (ignored for image input)\n- Audio [true | false]` generate synchronized audio (default: true)\n\n2. Timing and Randomness\n- Duration [5 | 8 | 10]` seconds (default: 5; 10s not available at 1080p)\n- Seed [1-9223372036854775807]` for reproducible results (omit for random)\n\n3. Advanced\n- Style [none | anime | 3d_animation | clay | comic | cyberpunk]` visual style preset (default: none)\n- Thinking [auto | enabled | disabled]` enhanced reasoning during generation (default: auto)\n- Negative prompt \"blurry, low quality, distorted\"` content to exclude (max 2048 chars)\n\nInput Limits & Requirements:\n- Prompt length: 2,048 characters max (both positive and negative prompt)\n- Image inputs: JPEG, PNG, WEBP, or HEIC only. Max 20MB per file. Images below 300x300 are automatically upscaled; images above 4000x4000 are automatically downscaled.", "owned_by": "EmpirioLabs AI", "root": "pixverse-v5.6", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Pixverse-v5.6", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6822353-200-eomvqyhvxmamlhxjrzcdrljaepswvwvh.jpeg", "alt": "Pixverse-v5.6 model icon", "width": 200, "height": 200}, "url": "https://poe.com/pixverse-v5.6"}, "reasoning": null, "parameters": [{"name": "resolution", "schema": {"enum": ["360p", "540p", "720p", "1080p"]}, "default_value": "1080p", "description": "Output video resolution"}, {"name": "aspect_ratio", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "16:9", "description": "Applies to text-to-video only. Ignored when images are attached."}, {"name": "duration", "schema": {"enum": ["5", "8", "10"]}, "default_value": "5", "description": "Video length in seconds (10s not available at 1080p)"}, {"name": "audio", "schema": {"type": "boolean"}, "default_value": true, "description": "Generate synchronized audio with the video"}, {"name": "style", "schema": {"enum": ["none", "anime", "3d_animation", "clay", "comic", "cyberpunk"]}, "default_value": "none", "description": "Visual style applied to the video"}, {"name": "thinking", "schema": {"enum": ["auto", "enabled", "disabled"]}, "default_value": "auto", "description": "Enhanced reasoning during generation"}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "", "description": "Content to exclude from the video (max 2048 chars)"}, {"name": "seed", "schema": {"type": "string"}, "default_value": "", "description": "For reproducible results (1 - 9223372036854775807)"}]}, {"id": "moss-video-and-audio", "object": "model", "created": 1771382022972, "description": "MOSS Video and Audio (MOVA) is an open-source foundation model developed by OpenMOSS that generates synchronized, high-fidelity video and audio in a single end-to-end inference step. Built on a 32-billion parameter Mixture-of-Experts (MoE) architecture, it employs an asymmetric dual-tower design to achieve precise lip-synchronization and eliminate the error accumulation found in traditional cascaded systems. \n\nThis model is hosted by EmpirioLabs.ai and is exclusive to the Poe platform.\n\nLearn more: https://mosi.cn/models/mova\n\nNotes:\n- Generations may take upwards of 20 minutes to complete.\n- Image-to-Video generations will likely yield superior results.\n- Supported image upload file types: .jpg, .jpeg, .png, .webp, .heic, .heif, .bmp, .tiff, .tif, .gif\n- Only 1 image attachment is supported (first frame), and video attachments are not supported.\n\nParameter controls available:\n1. Generation\n- Resolution `360p` or q720p` (default: 360p)\n- Aspect ratio `landscape` or `portrait` or `square` (default: landscape; auto-detected for uploaded images)\n- Duration [2-8] video length in seconds (default: 4)\n- t2v quality 1fast` or `quality` (default: quality; only for text-to-video)\n\n2. Advanced\n- Inference steps [10-50] more steps = higher quality but slower (default: 25, step: 5)\n- CFG scale [1.0-10.0] prompt adherence strength, higher = more literal (default: 5.0, step: 0.5)\n- Sigma_shift [1.0-10.0] noise schedule shift, 360p only (default: 5.0, step: 0.5)\n- Seed [number] for reproducibility, omit for random\n- Negative prompt \"your negative prompt\" leave blank for optimized default", "owned_by": "EmpirioLabs AI", "root": "moss-video-and-audio", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "MOSS-Video-and-Audio", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6816628-200-wqqkoetzdyuinkrsfawtwluvdcriwuto.jpeg", "alt": "MOSS-Video-and-Audio model icon", "width": 200, "height": 200}, "url": "https://poe.com/moss-video-and-audio"}, "reasoning": null, "parameters": [{"name": "resolution", "schema": {"enum": ["360p", "720p"]}, "default_value": "360p", "description": "Higher resolution takes longer but produces sharper output."}, {"name": "aspect_ratio", "schema": {"enum": ["landscape", "portrait"]}, "default_value": "landscape", "description": "Controls generated image aspect for text-to-video. Auto-detected for uploaded images."}, {"name": "duration", "schema": {"type": "number", "minimum": 2, "maximum": 8}, "default_value": 4, "description": "Video length. Longer videos cost proportionally more."}, {"name": "t2v_quality", "schema": {"enum": ["fast", "quality"]}, "default_value": "quality", "description": "Generation quality for text-to-video. Higher quality takes longer."}, {"name": "num_inference_steps", "schema": {"type": "number", "minimum": 10, "maximum": 50}, "default_value": 25, "description": "More steps = higher quality but slower."}, {"name": "cfg_scale", "schema": {"type": "number", "minimum": 1.0, "maximum": 10.0}, "default_value": 5.0, "description": "Prompt adherence strength. Higher = more literal."}, {"name": "sigma_shift", "schema": {"type": "number", "minimum": 1.0, "maximum": 10.0}, "default_value": 5.0, "description": "Noise schedule shift (360p only)."}, {"name": "seed", "schema": {"type": "string"}, "default_value": "", "description": "For reproducibility. Leave blank for random."}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "", "description": "Leave blank to use the optimized default."}]}, {"id": "qwen-image-2", "object": "model", "created": 1772745424015, "description": "Qwen-Image-2 is Alibaba's latest image generation model. This model can edit images (png/jpeg/webp, maximum of 3 images). \n\nThis bot supports optional parameters for additional customization.", "owned_by": "fal", "root": "qwen-image-2", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen-Image-2", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6852998-200-bqwhrlmxenmbgvsayhvlpqbtgmeulbxl.jpeg", "alt": "Qwen-Image-2 model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen-image-2"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "wan-2.7", "object": "model", "created": 1775194323304, "description": "Wan 2.7 is Alibaba's latest multimodal video generation model, capable of creating high-fidelity videos from text, images, video references, or by editing existing videos. It supports four generation modes: Text-to-Video (T2V), Image-to-Video (I2V), Video Edit, and Reference-to-Video (R2V).\n\nNotes:\n- This model is served from the Singapore area.\n- Upload an image to enable image-to-video, a video for video editing, or images/videos for reference-to-video. The mode is auto-detected from your attachments, or you can choose manually to override.\n- Responses may take upwards of 30 minutes to finish generating.\n- Shot type is described directly in your prompt (e.g., \"Generate a multi-shot video\" or use timeline syntax like \"Shot 1 [0-5s] wide shot of...\").\n\nAttachments:\n- For T2V: No attachments required. Optionally attach an audio file for custom audio.\n- For I2V (First Frame): Attach 1 image as the first frame. Optionally attach an audio file for driving audio.\n- For I2V (First + Last Frame): Attach exactly 2 images (first frame and last frame). Optionally attach an audio file for driving audio.\n- For I2V (Video Continuation): Attach 1 video (2\u201310s) as the first clip. Optionally attach 1 image as the target last frame.\n- For Video Edit: Attach 1 video (2\u201310s, \u2264100 MB, MP4/MOV) + up to 3 reference images. If your video is shorter than the selected duration, the output will match your video's length instead.\n- For R2V: Attach up to 5 references total (images + videos combined). Use `Video1`, `Video2` in your prompt to reference subjects from uploaded videos, and `Image1`, `Image2` for uploaded images. Optionally attach an audio file for voice timbre reference.\n- Audio files: For T2V and I2V: 2\u201330 seconds. For R2V: 1\u201310 seconds (voice timbre sample). Max 15 MB, .mp3/.wav. Audio is automatically trimmed to the mode's limit if too long.\n- Images are automatically resized to fit limits (240\u20138,000px per side). HEIC/HEIF images are auto-converted. Videos are validated (MP4/MOV, \u2264100 MB) and auto-trimmed if exceeding the mode's max duration.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "wan-2.7", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Wan-2.7", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6919735-200-qgcerfztojcaaqquhsfmpaacgmwktpax.jpeg", "alt": "Wan-2.7 model icon", "width": 200, "height": 200}, "url": "https://poe.com/wan-2.7"}, "reasoning": null, "parameters": [{"name": "mode", "schema": {"enum": ["auto", "t2v", "i2v", "videoedit", "r2v"]}, "default_value": "auto", "description": "Auto-detected from your attachments, or choose manually to override."}, {"name": "resolution", "schema": {"enum": ["720p", "1080p"]}, "default_value": "1080p", "description": "Higher resolution costs more per second."}, {"name": "aspect_ratio", "schema": {"enum": ["16:9", "9:16", "1:1", "4:3", "3:4"]}, "description": "Optional. If not selected: Text-to-Video and Reference-to-Video default to 16:9; Image-to-Video auto-infers from input material; Video Edit matches the input video. Image-to-Video always auto-infers and ignores this setting."}, {"name": "duration", "schema": {"type": "number", "minimum": 2, "maximum": 15}, "default_value": 5, "description": "How long the generated video will be. Video Edit and Reference-to-Video are automatically capped to 10 seconds."}, {"name": "audio_setting", "schema": {"enum": ["auto", "origin"]}, "default_value": "auto", "description": "Video Edit only. Controls what happens to the original video's audio."}, {"name": "prompt_extend", "schema": {"type": "boolean"}, "default_value": true, "description": "Let AI rewrite your prompt for better results. Adds a little extra processing time."}, {"name": "seed", "schema": {"type": "string"}, "default_value": "", "description": "Set a number for reproducible results. Leave blank for random."}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "", "description": "Describe anything you want to avoid in the video."}]}, {"id": "seedream-4.5", "object": "model", "created": 1764771581018, "description": "Seedream-4.5 is ByteDance's latest and best text-to-image model, capable of impressive high fidelity image generation, with great text-rendering ability. Seedream-4.5 can also take in  multiple images as references and combine them together or edit them to return an output. Pass `--aspect` to set the aspect ratio for the model (One of `16:9`, `4:3`, `1:1`, `3:4`, `9:16`).", "owned_by": "Bytedance", "root": "seedream-4.5", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Seedream-4.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6639099-200-sqbltyhnfwfrnpxapmeygxbsmhrvxldf.jpeg", "alt": "Seedream-4.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/seedream-4.5"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "kling-v3-pro", "object": "model", "created": 1770843940984, "description": "Kling v3 Pro Video bot, capable of text to video and image to video. Send a text prompt for text to video, and optionally up to two images for start frame and end frame functionality. \nCheck parameter controls for further details.\n\nNote: Generations may take upwards of 20 minutes to complete.", "owned_by": "fal", "root": "kling-v3-pro", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": ["/v1/videos"], "pricing": null, "context_window": {"context_length": 256, "max_output_tokens": null}, "context_length": 256, "metadata": {"display_name": "Kling-v3-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6802467-200-hkcjntfkybaurcpiiilepkjyrsioldzd.jpeg", "alt": "Kling-v3-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/kling-v3-pro"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "1:1", "9:16"]}, "default_value": "16:9"}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "blur, distort, and low quality"}, {"name": "cfg_scale", "schema": {"type": "number", "minimum": 0.0, "maximum": 1.0}, "default_value": 0.5, "description": "Classifer Guidance Scale for generation."}, {"name": "duration", "schema": {"enum": ["3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15"]}, "default_value": "5", "description": "Video duration in seconds"}, {"name": "silent", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to use silent mode for video generation. This will generate a video without audio, decreasing the cost."}]}, {"id": "claude-opus-4.5", "object": "model", "created": 1763768938036, "description": "Claude Opus 4.5 from Anthropic, supports customizable thinking budget (up to 64k tokens) and 200k context window.", "owned_by": "Anthropic", "root": "claude-opus-4.5", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/messages", "/v1/responses", "/v1/chat/completions"], "pricing": {"prompt": "0.0000042929", "completion": "0.0000214646", "image": null, "request": null, "input_cache_read": "0.0000004293", "input_cache_write": "0.0000053662"}, "context_window": {"context_length": 196608, "max_output_tokens": 64000}, "context_length": 196608, "metadata": {"display_name": "Claude-Opus-4.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-1040-200-zvapxaaebgdsijgbrkllqkeyrzxddbsq.jpeg", "alt": "Claude-Opus-4.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/claude-opus-4.5"}, "reasoning": {"budget": {"max_tokens": 63999, "min_tokens": 0}, "required": false, "supports_reasoning_effort": false}, "parameters": [{"name": "thinking_budget", "schema": {"type": "number", "minimum": 0, "maximum": 63999}, "default_value": 0, "description": "The maximum number of tokens to spend on thinking."}, {"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}, {"name": "output_effort", "schema": {"enum": ["high", "medium", "low"]}, "default_value": "high"}]}, {"id": "gemini-2.5-flash", "object": "model", "created": 1745638152572, "description": "Gemini 2.5 Flash builds upon the popular foundation of Google's 2.0 Flash, this new version delivers a major upgrade in reasoning capabilities, search capabilities, and image/video understanding while still prioritizing speed and cost. Supports 1M tokens of input context. Serves the latest `gemini-2.5-flash-preview-09-2025` snapshot.", "owned_by": "Google", "root": "gemini-2.5-flash", "architecture": {"input_modalities": ["text", "image", "video", "audio"], "output_modalities": ["text"], "modality": "text,image,video,audio->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000002121", "completion": "0.0000017677", "image": null, "request": null, "input_cache_read": "0.0000000212", "input_cache_write": null}, "context_window": {"context_length": 1065535, "max_output_tokens": 65535}, "context_length": 1065535, "metadata": {"display_name": "Gemini-2.5-Flash", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6019-200-oadloswwmyllkqtzhzaaedzinkjznenr.jpeg", "alt": "Gemini-2.5-Flash model icon", "width": 200, "height": 200}, "url": "https://poe.com/gemini-2.5-flash"}, "reasoning": {"budget": {"max_tokens": 24576, "min_tokens": 0}, "required": false, "supports_reasoning_effort": false}, "parameters": [{"name": "thinking_budget", "schema": {"type": "number", "minimum": 0, "maximum": 24576}, "default_value": 0, "description": "The maximum number of tokens to spend on thinking."}, {"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "kling-o3", "object": "model", "created": 1771637573229, "description": "Kling O3 is a versatile AI video generation model capable of creating high-quality videos in Standard or Pro modes, with resolution varying by aspect ratio. It supports multiple workflows including Text-to-Video, Image-to-Video, Reference-to-Video, and Video Editing, with advanced features like native sound generation and multi-scene transitions.\n\nMulti-Scene Mode\n- Separate scenes with `|` in your prompt \u2014 automatically detected, no toggle needed (max 6 scenes)\n- Not compatible with video input workflows (video edit, reference with video)\n- Optional per-scene durations: `5s: Scene one | 3s: Scene two | 7s: Scene three`\n- Explicit per-scene durations override the total duration set\n- If no durations specified, the slider duration is distributed evenly across scenes\n- Per-scene duration may sometimes not be exact as the model treats them as guidance, not exact frame cuts\n\nInput Limits & Requirements\n- Prompt length: 3 characters minimum, 2,500 characters maximum\n- Image inputs: JPEG, PNG, or WEBP only. Max 10MB per file. Images below 300x300 are automatically upscaled; images outside the 1:2.5-2.5:1 aspect ratio range are automatically center-cropped to fit\n- Video inputs: MP4, MOV, or WEBM only. Videos longer than 10 seconds are automatically trimmed; videos outside the 720-2160px resolution range are automatically resized. Minimum 3 seconds (cannot be extended)\n- Video workflow duration: When a video input is used (Video Edit, Reference with video), output duration is automatically capped at 10 seconds\n- Image-to-Video: Max 2 images (first frame + optional last frame)\n- Reference-to-Video: Max 7 reference images (max 4 if a reference video is also included), max 1 reference video\n- Video Edit: Exactly 1 video, no images\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "kling-o3", "architecture": {"input_modalities": ["text", "video"], "output_modalities": ["video"], "modality": "text,video->video"}, "supported_features": [], "supported_endpoints": ["/v1/videos"], "pricing": null, "context_window": {"context_length": 256, "max_output_tokens": null}, "context_length": 256, "metadata": {"display_name": "Kling-O3", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6822349-200-kobsiommhqwgzlzgkhnaiogdkibicbsk.jpeg", "alt": "Kling-O3 model icon", "width": 200, "height": 200}, "url": "https://poe.com/kling-o3"}, "reasoning": null, "parameters": [{"name": "model_tier", "schema": {"enum": ["standard", "pro", "4k"]}, "default_value": "pro", "description": "Standard, Pro, or 4K quality tier. 4K supports text and image workflows only."}, {"name": "workflow", "schema": {"enum": ["auto", "t2v", "i2v", "reference", "video_edit"]}, "default_value": "auto", "description": "Auto-detect from attachments, or choose manually."}, {"name": "aspect_ratio", "schema": {"enum": ["16:9", "1:1", "9:16"]}, "default_value": "16:9", "description": "Used for Text-to-Video and Reference modes. Image-to-Video and Video Edit auto-infer from input."}, {"name": "duration", "schema": {"type": "number", "minimum": 3, "maximum": 15}, "default_value": 5, "description": "3-15 seconds. Ignored for Video Edit (matches input video length). Ignored for Multi-Scene if durations are specified."}, {"name": "sound", "schema": {"type": "boolean"}, "default_value": true, "description": "Generate native audio (dialogue, ambient). Not available with video input workflows."}, {"name": "keep_original_sound", "schema": {"type": "boolean"}, "default_value": true, "description": "Preserve audio from the input video. Only for Video Edit and Reference (with video) workflows."}]}, {"id": "kling-v3", "object": "model", "created": 1770844410383, "description": "Kling v3 Standard Video bot, capable of text to video and image to video. Send a text prompt for text to video, and optionally up to two images for start frame and end frame functionality. \nCheck parameter controls for further details.\n\nNote: Generations may take upwards of 20 minutes to complete.", "owned_by": "fal", "root": "kling-v3", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Kling-v3", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6802476-200-jyehzqxjxqxevsldhymihkllzwfqyjtd.jpeg", "alt": "Kling-v3 model icon", "width": 200, "height": 200}, "url": "https://poe.com/kling-v3"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "1:1", "9:16"]}, "default_value": "16:9"}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "blur, distort, and low quality"}, {"name": "cfg_scale", "schema": {"type": "number", "minimum": 0.0, "maximum": 1.0}, "default_value": 0.5, "description": "Classifer Guidance Scale for generation."}, {"name": "duration", "schema": {"enum": ["3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15"]}, "default_value": "5", "description": "Video duration in seconds"}, {"name": "silent", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to use silent mode for video generation. This will generate a video without audio, decreasing the cost."}]}, {"id": "gemini-2.5-pro", "object": "model", "created": 1738780524168, "description": "Gemini 2.5 Pro is Google's advanced model with frontier performance on various key benchmarks; supports web search and 1 million tokens of input context.", "owned_by": "Google", "root": "gemini-2.5-pro", "architecture": {"input_modalities": ["text", "image", "video", "audio"], "output_modalities": ["text"], "modality": "text,image,video,audio->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000008788", "completion": "0.0000070707", "image": null, "request": null, "input_cache_read": "0.0000000879", "input_cache_write": null}, "context_window": {"context_length": 1065535, "max_output_tokens": 65535}, "context_length": 1065535, "metadata": {"display_name": "Gemini-2.5-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6017-200-ennagqdohiliacvmrmcnqridyvztrpgb.jpeg", "alt": "Gemini-2.5-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/gemini-2.5-pro"}, "reasoning": {"budget": {"max_tokens": 32768, "min_tokens": 0}, "required": false, "supports_reasoning_effort": false}, "parameters": [{"name": "thinking_budget", "schema": {"type": "number", "minimum": 0, "maximum": 32768}, "default_value": 0, "description": "The maximum number of tokens to spend on thinking."}, {"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "gpt-5.2-pro", "object": "model", "created": 1765479729564, "description": "A powerful reasoning model that is ideal for your most complex, highest difficulty tasks. On x-high reasoning effort, scores a 90.5% on ARC-AGI-1 benchmark, an incredibly difficult problem-solving benchmark where humans score 100%. Note: the model can take up to 30 minutes to think through a problem and is quite expensive. Supports 400k tokens of context and native vision.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "OpenAI", "root": "gpt-5.2-pro", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000190909", "completion": "0.0001527273", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "GPT-5.2-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3056-200-trsojldzaaamtvabegdoyylhrpbbmvhh.jpeg", "alt": "GPT-5.2-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5.2-pro"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}, {"name": "reasoning_effort", "schema": {"enum": ["medium", "high", "xhigh"]}, "default_value": "medium"}, {"name": "verbosity", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "kling-omni", "object": "model", "created": 1764600004756, "description": "Bot for Kling Omni Image-to-Video inference. Send one image for image-to-video generation and two images for first-to-last frame video generation. \n\nOptional parameters:\nSet Duration. Select from (5 seconds, 10 seconds) to specify video length in seconds. Set to 5 seconds as default.\n\nNotes:\nAccepted file type: jpeg, png, webp, heic, heif. \nThis bot does not accept video files.\nPrompt is required after attaching images to generate video.", "owned_by": "fal", "root": "kling-omni", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["video"], "modality": "text,image->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Kling-Omni", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6633150-200-qhjybrzmruvjdphgdvwwmdbyopccjfep.jpeg", "alt": "Kling-Omni model icon", "width": 200, "height": 200}, "url": "https://poe.com/kling-omni"}, "reasoning": null, "parameters": [{"name": "duration", "schema": {"enum": ["5", "10"]}, "default_value": "5", "description": "Video duration in seconds"}]}, {"id": "glm-4.7-flash", "object": "model", "created": 1768838511598, "description": "GLM-4.7-Flash, a state-of-the-art model in the 30B class, delivers a compelling balance of high performance and efficiency. Tailored for Agentic Coding, it strengthens coding proficiency, long-horizon planning, and tool synergy, securing top-tier results on public benchmarks among similarly sized open-source models. It excels in complex agent tasks with superior instruction following for tool use, while significantly elevating the frontend aesthetics and completion efficiency of long-range workflows in Artifacts and Agentic Coding. \n\nContext window: 200k tokens\n\nOptional parameters:\nEnable thinking about the response before giving a final answer: toggle it `on`, otherwise it is `off`  by default.\nSet temperature to control randomness in the response: Set number from 1 to 2.  This is set to `0.7` by default. Lower values make the output more focused and deterministic.\nSet max output tokens: Set number from 1 to 65500. This is set to 65500 by default.", "owned_by": "Novita AI", "root": "glm-4.7-flash", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000000707", "completion": "0.000000404", "image": null, "request": null, "input_cache_read": "0.0000000101", "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "GLM-4.7-Flash", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6749261-200-aprgrchpkzqaponuvjvpakglncbotiet.jpeg", "alt": "GLM-4.7-Flash model icon", "width": 200, "height": 200}, "url": "https://poe.com/glm-4.7-flash"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": false, "description": "This will cause the model to think before providing a response."}, {"name": "temperature", "schema": {"type": "number", "minimum": 0, "maximum": 2}, "default_value": 0.7, "description": "Controls randomness in the response. Lower values make the output more focused and deterministic."}, {"name": "max_output_tokens", "schema": {"type": "number", "minimum": 1, "maximum": 65500}, "default_value": 65500.0, "description": "Maximum number of tokens to generate in the response."}]}, {"id": "gpt-5.1-instant", "object": "model", "created": 1762990086156, "description": "OpenAI\u2019s most flagship model optimized for conversational intelligence. It excels at natural dialogue, contextual memory, and adaptive tone, making it perfect for interactive agents, tutoring, and customer support. It balances speed, reliability, and empathy for seamless real\u2011time communication. \n\nSupports 128k tokens of input context.", "owned_by": "OpenAI", "root": "gpt-5.1-instant", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000011364", "completion": "0.0000090909", "image": null, "request": null, "input_cache_read": "0.0000001136", "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": 16384}, "context_length": 128000, "metadata": {"display_name": "GPT-5.1-Instant", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3050-200-grvhuoelpjmmuvzveeuufdozddtnjwyw.jpeg", "alt": "GPT-5.1-Instant model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5.1-instant"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": false}, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "gpt-5.1-codex", "object": "model", "created": 1762990136461, "description": "GPT\u20115.1\u2011Codex extends GPT\u20115.1\u2019s capabilities for software development. It understands complex codebases, provides accurate completions, explains algorithms, and assists with debugging across modern programming languages. Designed for developers, it elevates productivity and supports full\u2011stack coding workflows with precision. \n\nSupports 400k tokens of input context.\n\nOptional parameters:\nSet reasoning effort: Select from  low, medium, high. Medium effort is set by default.", "owned_by": "OpenAI", "root": "gpt-5.1-codex", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000011364", "completion": "0.0000090909", "image": null, "request": null, "input_cache_read": "0.0000001136", "input_cache_write": null}, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "GPT-5.1-Codex", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3051-200-kfxotsufqjcqgmfcnckmpanmtugugrup.jpeg", "alt": "GPT-5.1-Codex model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5.1-codex"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "elevenlabs-v3", "object": "model", "created": 1749151405074, "description": "ElevenLabs v3 is a cutting-edge text-to-speech model that brings scripts to life with remarkable realism and performance-level control. Unlike traditional TTS systems, it allows creators to shape the emotional tone, pacing, and soundscape of their audio through the use of inline audio tags. These tags are enclosed in square brackets and act as stage directions\u2014guiding how a line is spoken or what sound effects are inserted\u2014without being spoken aloud. This enables rich, expressive narration and dialogue for applications like audiobooks, games, podcasts, and interactive media. Whether you\u2019re aiming for a tense whisper, a sarcastic remark, or a dramatic soundscape full of explosions and ambient effects, v3 gives you granular control directly in the text prompt. This bot will also run text-to-speech on PDF attachments / URL links.\n\nExamples of voice delivery tags include:\n* [whispers] I have to tell you a secret. \n* [angry] That was *never* the plan.\n* [sarcastic] Oh, sure. That\u2019ll totally work.\n* and [laughs] You're hilarious.\n\nExamples of sound effect tags are:\n* [gunshot] Get down!\n* [applause] Thank you, everyone.\n* and [explosion] What was that?!\n\nThese can also be combined.\n\nMultiple speakers can be supported via the parameter control. Dialogue for multiple speakers must follow the format, e.g. for 3 speakers:\n\nSpeaker 1: [dialogue]\nSpeaker 2: [dialogue]\nSpeaker 3: [dialogue]\nSpeaker 1: [dialogue]\nSpeaker 2: [dialogue]\n\nThe following voices are supported:\nAlexandra - Conversational & Real\nAmy - Young & Natural\nArabella - Mature Female Narrator\nAustin - Good Ol' Texas Boy\nBlondie - Warm & Conversational\nBradford - British Male Storyteller\nCallum - Gravelly Yet Unsettling\nCharlotte - Raspy & Sensual\nChris - Down-to-Earth\nCoco Li - Shanghainese Female\nGaming - Unreal Tonemanagement 2003\nHarry - Animated Warrior\nHayato - Soothing Zen Male\nHope - Upbeat & Clear\nJames - Husky & Engaging\nJames Gao - Calm Chinese Voice\nJane - Professional Audiobook Reader\nJessica - Playful American Female\nJuniper - Grounded Female Professional\nKaro Yang - Youthful Asian Male\nKuon - Acute Fantastic Female\nLaura - Quirky Female Voice\nLiam - Warm, Energetic Youth\nMonika Sogam - Indian-English Accent\nNichalia Schwartz - Engaging Female American\nPriyanka Sogam - Late-Night Radio\nReginald - Brooding, Intense Villain\nShanShan - Young, Energetic Female\nXiao Bai - Shrill & Annoying\n\nPrompt input cannot exceed 5,000 characters.", "owned_by": "ElevenLabs", "root": "elevenlabs-v3", "architecture": {"input_modalities": ["text"], "output_modalities": ["audio"], "modality": "text->audio"}, "supported_features": [], "supported_endpoints": ["/v1/audio"], "pricing": null, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "ElevenLabs-v3", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6094170-200-uvaozfcoyijguaxwvhsaqhdtvzqehafw.jpeg", "alt": "ElevenLabs-v3 model icon", "width": 200, "height": 200}, "url": "https://poe.com/elevenlabs-v3"}, "reasoning": null, "parameters": [{"name": "speaker_count", "schema": {"type": "number", "minimum": 1, "maximum": 9}, "default_value": 1, "description": "Number of speakers in dialog"}, {"name": "voice_1", "schema": {"enum": ["Alexandra", "Amy", "Arabella", "Austin", "Blondie", "Bradford", "Callum", "Charlotte", "Chris", "Coco Li", "Gaming", "Harry", "Hayato", "Hope", "James", "James Gao", "Jane", "Jessica", "Juniper", "Karo Yang", "Kuon", "Laura", "Liam", "Monika Sogam", "Nichalia Schwartz", "Priyanka Sogam ", "Reginald", "ShanShan", "Xiao Bai"]}, "default_value": "Hope", "description": "Voice for speaker number 1 in the dialog"}, {"name": "voice_2", "schema": {"enum": ["Alexandra", "Amy", "Arabella", "Austin", "Blondie", "Bradford", "Callum", "Charlotte", "Chris", "Coco Li", "Gaming", "Harry", "Hayato", "Hope", "James", "James Gao", "Jane", "Jessica", "Juniper", "Karo Yang", "Kuon", "Laura", "Liam", "Monika Sogam", "Nichalia Schwartz", "Priyanka Sogam ", "Reginald", "ShanShan", "Xiao Bai"]}, "default_value": "Hope", "description": "Voice for speaker number 2 in the dialog"}, {"name": "voice_3", "schema": {"enum": ["Alexandra", "Amy", "Arabella", "Austin", "Blondie", "Bradford", "Callum", "Charlotte", "Chris", "Coco Li", "Gaming", "Harry", "Hayato", "Hope", "James", "James Gao", "Jane", "Jessica", "Juniper", "Karo Yang", "Kuon", "Laura", "Liam", "Monika Sogam", "Nichalia Schwartz", "Priyanka Sogam ", "Reginald", "ShanShan", "Xiao Bai"]}, "default_value": "Hope", "description": "Voice for speaker number 3 in the dialog"}, {"name": "voice_4", "schema": {"enum": ["Alexandra", "Amy", "Arabella", "Austin", "Blondie", "Bradford", "Callum", "Charlotte", "Chris", "Coco Li", "Gaming", "Harry", "Hayato", "Hope", "James", "James Gao", "Jane", "Jessica", "Juniper", "Karo Yang", "Kuon", "Laura", "Liam", "Monika Sogam", "Nichalia Schwartz", "Priyanka Sogam ", "Reginald", "ShanShan", "Xiao Bai"]}, "default_value": "Hope", "description": "Voice for speaker number 4 in the dialog"}, {"name": "voice_5", "schema": {"enum": ["Alexandra", "Amy", "Arabella", "Austin", "Blondie", "Bradford", "Callum", "Charlotte", "Chris", "Coco Li", "Gaming", "Harry", "Hayato", "Hope", "James", "James Gao", "Jane", "Jessica", "Juniper", "Karo Yang", "Kuon", "Laura", "Liam", "Monika Sogam", "Nichalia Schwartz", "Priyanka Sogam ", "Reginald", "ShanShan", "Xiao Bai"]}, "default_value": "Hope", "description": "Voice for speaker number 5 in the dialog"}, {"name": "voice_6", "schema": {"enum": ["Alexandra", "Amy", "Arabella", "Austin", "Blondie", "Bradford", "Callum", "Charlotte", "Chris", "Coco Li", "Gaming", "Harry", "Hayato", "Hope", "James", "James Gao", "Jane", "Jessica", "Juniper", "Karo Yang", "Kuon", "Laura", "Liam", "Monika Sogam", "Nichalia Schwartz", "Priyanka Sogam ", "Reginald", "ShanShan", "Xiao Bai"]}, "default_value": "Hope", "description": "Voice for speaker number 6 in the dialog"}, {"name": "voice_7", "schema": {"enum": ["Alexandra", "Amy", "Arabella", "Austin", "Blondie", "Bradford", "Callum", "Charlotte", "Chris", "Coco Li", "Gaming", "Harry", "Hayato", "Hope", "James", "James Gao", "Jane", "Jessica", "Juniper", "Karo Yang", "Kuon", "Laura", "Liam", "Monika Sogam", "Nichalia Schwartz", "Priyanka Sogam ", "Reginald", "ShanShan", "Xiao Bai"]}, "default_value": "Hope", "description": "Voice for speaker number 7 in the dialog"}, {"name": "voice_8", "schema": {"enum": ["Alexandra", "Amy", "Arabella", "Austin", "Blondie", "Bradford", "Callum", "Charlotte", "Chris", "Coco Li", "Gaming", "Harry", "Hayato", "Hope", "James", "James Gao", "Jane", "Jessica", "Juniper", "Karo Yang", "Kuon", "Laura", "Liam", "Monika Sogam", "Nichalia Schwartz", "Priyanka Sogam ", "Reginald", "ShanShan", "Xiao Bai"]}, "default_value": "Hope", "description": "Voice for speaker number 8 in the dialog"}, {"name": "voice_9", "schema": {"enum": ["Alexandra", "Amy", "Arabella", "Austin", "Blondie", "Bradford", "Callum", "Charlotte", "Chris", "Coco Li", "Gaming", "Harry", "Hayato", "Hope", "James", "James Gao", "Jane", "Jessica", "Juniper", "Karo Yang", "Kuon", "Laura", "Liam", "Monika Sogam", "Nichalia Schwartz", "Priyanka Sogam ", "Reginald", "ShanShan", "Xiao Bai"]}, "default_value": "Hope", "description": "Voice for speaker number 9 in the dialog"}]}, {"id": "gpt-audio-mini", "object": "model", "created": 1768926869174, "description": "OpenAI's gpt-audio-mini model, brought to Poe as a server bot! This model accepts text and audio inputs and can respond with natural-sounding speech. Learn more about this model at https://platform.openai.com/docs/models/gpt-audio-mini.\n\nWhen audio output is on, responses include both a voice recording and a text transcript. When audio output is off, one of the messages in the conversation must include an audio file attachment (audio in previous messages from either you or the bot is fine).\n\nOptional parameters:\n- enable_audio_output: either true or false to control whether responses are spoken aloud (default: true)\n- voice: the name of a voice for voice outputs: \"alloy\", \"ash\", \"ballad\", \"cedar\", \"coral\", \"echo\", \"fable\", \"marin\", \"nova\", \"onyx\", \"sage\", or \"shimmer\" (default: marin)\n-  model_snapshot: select a specific model version\n- auto_max_tokens: Let the model decide the max number of tokens to output (enabled by default). Disable this option to manually specify a token limit between 10 and 16,384 using the max_tokens parameter.", "owned_by": "Bina AI", "root": "gpt-audio-mini", "architecture": {"input_modalities": ["text"], "output_modalities": ["audio"], "modality": "text->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "GPT-Audio-Mini", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6751774-200-gqqzmfvdzfzzfgttxqrxeegnkwhzyucd.jpeg", "alt": "GPT-Audio-Mini model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-audio-mini"}, "reasoning": null, "parameters": [{"name": "enable_audio_output", "schema": {"type": "boolean"}, "default_value": true, "description": "If on, allows the bot to respond with audio instead of just text."}, {"name": "voice", "schema": {"enum": ["alloy", "ash", "ballad", "cedar", "coral", "echo", "fable", "marin", "nova", "onyx", "sage", "shimmer"]}, "default_value": "marin", "description": "Select a voice for the audio response. OpenAI recommends 'marin' or 'cedar' for best quality."}, {"name": "model_snapshot", "schema": {"enum": ["gpt-audio-mini", "gpt-audio-mini-2025-10-06", "gpt-audio-mini-2025-12-15"]}, "default_value": "gpt-audio-mini", "description": "Select a specific model snapshot version."}, {"name": "auto_max_tokens", "schema": {"type": "boolean"}, "default_value": true, "description": "Let the model decide the response length. Turn off to set a specific limit."}, {"name": "max_tokens", "schema": {"type": "number", "minimum": 10, "maximum": 16384}, "default_value": 4096, "description": "Maximum number of tokens in the response."}, {"name": "beta_streaming_mode", "schema": {"type": "boolean"}, "default_value": false, "description": "Output a stream of the data (including transcript text and audio)."}]}, {"id": "gpt-audio-1.5", "object": "model", "created": 1772683680804, "description": "OpenAI's gpt-audio-1.5 model, brought to Poe as a server bot! This model accepts text and audio inputs and can respond with natural-sounding speech. Learn more at https://platform.openai.com/docs/models/gpt-audio-1.5.\n\nWhen audio output is on, responses include both a voice recording and a text transcript. When audio output is off, one of the messages in the conversation must include an audio file attachment (audio in previous messages from either you or the bot is fine).\n\nOptional parameters:\n- enable_audio_output: either true or false to control whether responses are spoken aloud (default: true)\n- voice: the name of a voice for voice outputs: \"alloy\", \"ash\", \"ballad\", \"cedar\", \"coral\", \"echo\", \"fable\", \"marin\", \"nova\", \"onyx\", \"sage\", or \"shimmer\" (default: marin)\n- auto_max_tokens: Let the model decide the max number of tokens to output (enabled by default). Disable this option to manually specify a token limit between 10 and 16,384 using the max_tokens parameter.", "owned_by": "Bina AI", "root": "gpt-audio-1.5", "architecture": {"input_modalities": ["text"], "output_modalities": ["audio"], "modality": "text->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "GPT-Audio-1.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6851198-200-cdvnemdiluxudvcrehqiuagrrbqxjoah.jpeg", "alt": "GPT-Audio-1.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-audio-1.5"}, "reasoning": null, "parameters": [{"name": "enable_audio_output", "schema": {"type": "boolean"}, "default_value": true, "description": "If on, allows the bot to respond with audio instead of just text."}, {"name": "voice", "schema": {"enum": ["alloy", "ash", "ballad", "cedar", "coral", "echo", "fable", "marin", "nova", "onyx", "sage", "shimmer"]}, "default_value": "marin", "description": "Select a voice for the audio response. OpenAI recommends 'marin' or 'cedar' for best quality."}, {"name": "auto_max_tokens", "schema": {"type": "boolean"}, "default_value": true, "description": "Let the model decide the response length. Turn off to set a specific limit."}, {"name": "max_tokens", "schema": {"type": "number", "minimum": 10, "maximum": 16384}, "default_value": 4096, "description": "Maximum number of tokens in the response."}, {"name": "beta_streaming_mode", "schema": {"type": "boolean"}, "default_value": false, "description": "Output a stream of the data (including transcript text and audio)."}]}, {"id": "glm-4.7-n", "object": "model", "created": 1766425366576, "description": "GLM-4.7 is Z.AI's latest flagship model, with major upgrades focused on advanced coding capabilities and more reliable multi-step reasoning and execution. It shows clear gains in complex agent workflows, while delivering a more natural conversational experience and stronger front-end design sensibility.\n\nFile Support: Text, Markdown and PDF files\nContext window: 205k tokens\n\nOptional parameters:\nEnable thinking about the response before giving a final answer: toggle it `on`, otherwise it is `off`  by default.\nSet temperature to control randomness in the response: Set number from 1 to 2.  This is set to `0.7` by default. Lower values make the output more focused and deterministic.\nSet max output tokens: Set number from 1 to 131072. This is set to 131072 by default.", "owned_by": "Novita AI", "root": "glm-4.7-n", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000006061", "completion": "0.0000022222", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "GLM-4.7-N", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6688425-200-bilqlanglxoqolyuejulmtsutadayoea.jpeg", "alt": "GLM-4.7-N model icon", "width": 200, "height": 200}, "url": "https://poe.com/glm-4.7-n"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": false, "description": "This will cause the model to think before providing a response."}, {"name": "temperature", "schema": {"type": "number", "minimum": 0, "maximum": 2}, "default_value": 0.7, "description": "Controls randomness in the response. Lower values make the output more focused and deterministic."}, {"name": "max_output_tokens", "schema": {"type": "number", "minimum": 1, "maximum": 131072}, "default_value": 131072.0, "description": "Maximum number of tokens to generate in the response."}]}, {"id": "gpt-audio", "object": "model", "created": 1768927028324, "description": "OpenAI's gpt-audio model, brought to Poe as a server bot! This model accepts text and audio inputs and can respond with natural-sounding speech. Learn more at https://platform.openai.com/docs/models/gpt-audio.\n\nWhen audio output is on, responses include both a voice recording and a text transcript. When audio output is off, one of the messages in the conversation must include an audio file attachment (audio in previous messages from either you or the bot is fine).\n\nOptional parameters:\n- enable_audio_output: either true or false to control whether responses are spoken aloud (default: true)\n- voice: the name of a voice for voice outputs: \"alloy\", \"ash\", \"ballad\", \"cedar\", \"coral\", \"echo\", \"fable\", \"marin\", \"nova\", \"onyx\", \"sage\", or \"shimmer\" (default: marin)\n-  model_snapshot: select a specific model version\n- auto_max_tokens: Let the model decide the max number of tokens to output (enabled by default). Disable this option to manually specify a token limit between 10 and 16,384 using the max_tokens parameter.", "owned_by": "Bina AI", "root": "gpt-audio", "architecture": {"input_modalities": ["text"], "output_modalities": ["audio"], "modality": "text->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "GPT-Audio", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6751791-200-svarrqnxugcwnwfbdzydceopupqrijbm.jpeg", "alt": "GPT-Audio model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-audio"}, "reasoning": null, "parameters": [{"name": "enable_audio_output", "schema": {"type": "boolean"}, "default_value": true, "description": "If on, allows the bot to respond with audio instead of just text."}, {"name": "voice", "schema": {"enum": ["alloy", "ash", "ballad", "cedar", "coral", "echo", "fable", "marin", "nova", "onyx", "sage", "shimmer"]}, "default_value": "marin", "description": "Select a voice for the audio response. OpenAI recommends 'marin' or 'cedar' for best quality."}, {"name": "model_snapshot", "schema": {"enum": ["gpt-audio", "gpt-audio-2025-08-28"]}, "default_value": "gpt-audio", "description": "Select a specific model snapshot version."}, {"name": "auto_max_tokens", "schema": {"type": "boolean"}, "default_value": true, "description": "Let the model decide the response length. Turn off to set a specific limit."}, {"name": "max_tokens", "schema": {"type": "number", "minimum": 10, "maximum": 16384}, "default_value": 4096, "description": "Maximum number of tokens in the response."}, {"name": "beta_streaming_mode", "schema": {"type": "boolean"}, "default_value": false, "description": "Output a stream of the data (including transcript text and audio)."}]}, {"id": "gpt-5.1", "object": "model", "created": 1762989903319, "description": "OpenAI\u2019s flagship general\u2011purpose model, built for advanced reasoning, comprehension, and creativity. It delivers robust performance across text and code, with significant improvements in factual accuracy, long\u2011context understanding, and multilingual fluency. Ideal for research, content creation, analysis, and problem\u2011solving in any domain. \n\nSupports 400k of input context window.", "owned_by": "OpenAI", "root": "gpt-5.1", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000011364", "completion": "0.0000090909", "image": null, "request": null, "input_cache_read": "0.0000001136", "input_cache_write": null}, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "GPT-5.1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3049-200-khzrgexjrnngfcpmxpaxznhtitilhxqd.jpeg", "alt": "GPT-5.1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5.1"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}, {"name": "websearch_reasoning_effort", "schema": {"enum": ["none", "low", "medium", "high"]}, "default_value": "low"}, {"name": "reasoning_effort", "schema": {"enum": ["none", "low", "medium", "high"]}, "default_value": "none"}, {"name": "verbosity", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "gpt-5-pro", "object": "model", "created": 1759789057270, "description": "OpenAI\u2019s latest flagship model with significantly improved coding skills, long context (400k tokens), and improved instruction following. Supports native vision, and generally has more intelligence than GPT-4.1.\n\nNote: \nGPT-5-Pro thinks long and hard. When using this bot through the API, consider increasing your request timeouts.", "owned_by": "OpenAI", "root": "gpt-5-pro", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000136364", "completion": "0.0001090909", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "GPT-5-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3048-200-zdgatcscdmlcmyjoreojbddanjsmpmnu.jpeg", "alt": "GPT-5-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5-pro"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "seedance-2.0-pro-el", "object": "model", "created": 1775794202611, "description": "Seedance 2.0 Pro is a multimodal AI video generation model built for cinematic, high-quality output from text, images, audio, and video inputs, with strong motion stability, native audio-video generation, and consistent character handling. It is best suited for creators who want more control over references, editing, pacing, and polished storytelling across multiple assets in one workflow.\nThis model is served from Malaysia.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "seedance-2.0-pro-el", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Seedance-2.0-Pro-EL", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6930985-200-jqauaaxokhbtpsgsettgqnxtikasuwqz.jpeg", "alt": "Seedance-2.0-Pro-EL model icon", "width": 200, "height": 200}, "url": "https://poe.com/seedance-2.0-pro-el"}, "reasoning": null, "parameters": [{"name": "mode", "schema": {"enum": ["auto", "t2v", "i2v_first", "i2v_both", "reference", "edit", "extend"]}, "default_value": "auto", "description": "Auto-detected from attachments, or override manually."}, {"name": "resolution", "schema": {"enum": ["480p", "720p", "1080p"]}, "default_value": "720p", "description": "Output video resolution. Higher costs more."}, {"name": "aspect_ratio", "schema": {"enum": ["16:9", "9:16", "1:1", "4:3", "3:4", "21:9"]}, "default_value": "adaptive", "description": "Set to 'adaptive' by default \u2013 the model picks the best ratio from the input. Override if needed."}, {"name": "custom_duration", "schema": {"type": "boolean"}, "default_value": true, "description": "Enable to set a specific duration. When off, the model picks the best duration automatically."}, {"name": "duration", "schema": {"type": "number", "minimum": 4, "maximum": 15}, "default_value": 5, "description": "Generated video length (4\u201315 seconds)."}, {"name": "generate_audio", "schema": {"type": "boolean"}, "default_value": true, "description": "Include synchronized audio (voice, SFX, music). Put dialogue in double quotes in your prompt."}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "", "description": "Describe anything you want to avoid. Appended to the text prompt as guidance."}]}, {"id": "gpt-5-chat", "object": "model", "created": 1754589771417, "description": "ChatGPT-5 points to the non-reasoning model GPT-5 snapshot (gpt-5-chat-latest) currently used in ChatGPT. Supports native vision, 400k tokens of context, and generally has more intelligence than GPT-4.1. Provides a 90% chat history cache discount.", "owned_by": "OpenAI", "root": "gpt-5-chat", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000011364", "completion": "0.0000090909", "image": null, "request": null, "input_cache_read": "0.0000001136", "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": 16384}, "context_length": 128000, "metadata": {"display_name": "GPT-5-Chat", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3046-200-tzicdptmpvklsstitoczgsdaxdbcboir.jpeg", "alt": "GPT-5-Chat model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5-chat"}, "reasoning": null, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "claude-opus-4.1", "object": "model", "created": 1754419185968, "description": "Claude Opus 4.1 from Anthropic, supports customizable thinking budget (up to 32k tokens) and 200k context window.", "owned_by": "Anthropic", "root": "claude-opus-4.1", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/messages", "/v1/responses", "/v1/chat/completions"], "pricing": {"prompt": "0.0000128788", "completion": "0.0000643939", "image": null, "request": null, "input_cache_read": "0.0000012879", "input_cache_write": "0.0000160985"}, "context_window": {"context_length": 196608, "max_output_tokens": 32000}, "context_length": 196608, "metadata": {"display_name": "Claude-Opus-4.1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-1037-200-fvwljjdfnkcibpnnxvvakmnftibwvwon.jpeg", "alt": "Claude-Opus-4.1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/claude-opus-4.1"}, "reasoning": {"budget": {"max_tokens": 31999, "min_tokens": 0}, "required": false, "supports_reasoning_effort": false}, "parameters": [{"name": "thinking_budget", "schema": {"type": "number", "minimum": 0, "maximum": 31999}, "default_value": 0, "description": "The maximum number of tokens to spend on thinking."}, {"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "glm-4.6", "object": "model", "created": 1759223039599, "description": "As the latest iteration in the GLM series, GLM-4.6 achieves comprehensive enhancements across multiple domains, including real-world coding, long-context processing, reasoning, searching, writing, and agentic applications. \n\nFile Support: Text, Markdown and PDF files\nContext window: 205k tokens", "owned_by": "Novita AI", "root": "glm-4.6", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000005556", "completion": "0.0000022222", "image": null, "request": null, "input_cache_read": "0.0000001111", "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "GLM-4.6", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6462183-200-ebhirjmybgbzfjzsknkiimmkcjxdzwpz.jpeg", "alt": "GLM-4.6 model icon", "width": 200, "height": 200}, "url": "https://poe.com/glm-4.6"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": false, "description": "This will cause the model to think before providing a response."}, {"name": "temperature", "schema": {"type": "number", "minimum": 0, "maximum": 2}, "default_value": 0.7, "description": "Controls randomness in the response. Lower values make the output more focused and deterministic."}, {"name": "max_output_tokens", "schema": {"type": "number", "minimum": 1, "maximum": 131072}, "default_value": 131072.0, "description": "Maximum number of tokens to generate in the response."}]}, {"id": "gpt-5.1-codex-mini", "object": "model", "created": 1762990151662, "description": "GPT\u20115.1\u2011Codex\u2011Mini is a lightweight, fast, and efficient code\u2011generation model derived from GPT\u20115.1\u2011Codex. It\u2019s optimized for quick iterations, smaller environments, and edge applications\u2014offering strong coding assistance with lower computational cost while maintaining accuracy and utility. \n\nSupports 400k tokens of input context.\n\nOptional parameters:\nSet reasoning effort: Select from  `low`, `medium`, `high`. Medium reasoning effort is set by default.", "owned_by": "OpenAI", "root": "gpt-5.1-codex-mini", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000002273", "completion": "0.0000018182", "image": null, "request": null, "input_cache_read": "0.0000000227", "input_cache_write": null}, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "GPT-5.1-Codex-Mini", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3052-200-ttjhagjaacioqlrtzkcgaqfegdzyxqdl.jpeg", "alt": "GPT-5.1-Codex-Mini model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5.1-codex-mini"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "gpt-5.1-codex-max", "object": "model", "created": 1765227284928, "description": "OpenAI's most capable agentic coding model; recommended for use in agentic harnesses or similar environments (e.g. Cursor, Claude Code, Codex); the default reasoning effort is set to `Xhigh` so the model will reason extensively on problems given to it (i.e. expect long generation times) and points-intensive. Accepts image attachments.", "owned_by": "OpenAI", "root": "gpt-5.1-codex-max", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000011364", "completion": "0.0000090909", "image": null, "request": null, "input_cache_read": "0.0000001136", "input_cache_write": null}, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "GPT-5.1-Codex-Max", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3053-200-pehobsvrnfgjircfqthumtxpojovfxyj.jpeg", "alt": "GPT-5.1-Codex-Max model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5.1-codex-max"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high", "xhigh"]}, "default_value": "xhigh"}]}, {"id": "glm-4.6v", "object": "model", "created": 1765278260925, "description": "GLM-4.6V represents a significant multimodal advancement in the GLM series, achieving state-of-the-art visual understanding accuracy for models of its parameter scale. Notably, it's the first visual model to natively integrate Function Call capabilities directly into its architecture, creating a seamless pathway from visual perception to executable actions. This breakthrough establishes a unified technical foundation for deploying multimodal agents in real-world business applications.\n\nFile Support: Text, Markdown, Image and PDF files\nContext window: 131k tokens\n\nOptional parameters:\nEnable Thinking - Toggle this on for the model to think before providing a response. This is disabled by default\nTemperature - Controls randomness in the response. Lower values make the output more focused and deterministic. Select from 0 to 2 range. This is set to 0.7 by default.\nMax Output Tokens: Maximum number of tokens to generate in the response. This can be set from 1 to 32768. Set to Max token at 32768 by default.", "owned_by": "Novita AI", "root": "glm-4.6v", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.000000303", "completion": "0.0000009091", "image": null, "request": null, "input_cache_read": "0.0000000556", "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "GLM-4.6V", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6655058-200-byhnlafeprgwhfoftamknsrqpqaexgyy.jpeg", "alt": "GLM-4.6V model icon", "width": 200, "height": 200}, "url": "https://poe.com/glm-4.6v"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": false, "description": "This will cause the model to think before providing a response."}, {"name": "temperature", "schema": {"type": "number", "minimum": 0, "maximum": 2}, "default_value": 0.7, "description": "Controls randomness in the response. Lower values make the output more focused and deterministic."}, {"name": "max_output_tokens", "schema": {"type": "number", "minimum": 1, "maximum": 32768}, "default_value": 32768.0, "description": "Maximum number of tokens to generate in the response."}]}, {"id": "nano-banana-pro", "object": "model", "created": 1763518946353, "description": "Nano Banana Pro (Gemini 3 Pro Image Preview) can make detailed, context-rich visuals, precisely edit or restyle input images with exceptional fidelity, and even generate legible text in images in multiple languages.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Google", "root": "nano-banana-pro", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": ["/v1/images", "/v1/responses", "/v1/chat/completions"], "pricing": {"prompt": "0.0000020202", "completion": "0.0000121212", "image": "0.0001212121", "request": null, "input_cache_read": "0.000000202", "input_cache_write": null}, "context_window": {"context_length": 65536, "max_output_tokens": null}, "context_length": 65536, "metadata": {"display_name": "Nano-Banana-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6594978-200-xmkviblepufpzqergeyhvuplaucdmikb.jpeg", "alt": "Nano-Banana-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/nano-banana-pro"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9"]}}, {"name": "image_only", "schema": {"type": "boolean"}, "default_value": false, "description": "The model defaults to returning text and images. Turn on to only return images."}, {"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}, {"name": "image_size", "schema": {"enum": ["1K", "2K", "4K"]}}]}, {"id": "nano-banana", "object": "model", "created": 1755817420757, "description": "Google DeepMind's Nano Banana (i.e. Gemini 2.5 Flash Image model) offers image generation and editing capabilities, state-of-the-art performance in photo-realistic multi-turn edits at exceptional speeds. Supports a maximum input context of 32k tokens.\n\nOptional parameters:\nSet aspect ratio. Select from (1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9). It is set to 16:9 aspect ratio as default.\nImage only to only generate image output. It is `off` by default\n\nNote: Simply enabling image only will not result in an image unless the prompt is phrased specifically for image generation, but it does guarantee that only a single image (or none) will be produced.", "owned_by": "Google", "root": "nano-banana", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": ["/v1/images", "/v1/responses", "/v1/chat/completions"], "pricing": {"prompt": "0.0000002121", "completion": "0.0000017677", "image": "0.0000212121", "request": null, "input_cache_read": "0.0000000212", "input_cache_write": null}, "context_window": {"context_length": 65536, "max_output_tokens": null}, "context_length": 65536, "metadata": {"display_name": "Nano-Banana", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6348843-200-zqnidmlfltbivcuhqcvqpckxnwvpebdy.jpeg", "alt": "Nano-Banana model icon", "width": 200, "height": 200}, "url": "https://poe.com/nano-banana"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9"]}}, {"name": "image_only", "schema": {"type": "boolean"}, "default_value": false, "description": "The model defaults to returning text and images. Turn on to only return images."}]}, {"id": "glm-5-t", "object": "model", "created": 1775504271719, "description": "GLM-5 is an open-source foundation model built for complex systems engineering and long-horizon agent workflows. It delivers production-grade productivity in large-scale programming tasks, with performance aligned with top closed-source models, and is designed for expert developers who think and build at the system level. Purpose-built for multi-stage, long-step complex tasks, GLM-5 autonomously decomposes system-level requirements with an architect-level approach while maintaining context coherence across automated workflows that run for hours.", "owned_by": "Together AI", "root": "glm-5-t", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.00", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "GLM-5-T", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6925185-200-iksbaresyqgccjjvhkzgjgrbqyrusrrh.jpeg", "alt": "GLM-5-T model icon", "width": 200, "height": 200}, "url": "https://poe.com/glm-5-t"}, "reasoning": null, "parameters": []}, {"id": "gpt-5", "object": "model", "created": 1754429855700, "description": "OpenAI\u2019s most advanced general model with significantly improved coding skills, long context (400k tokens), and improved instruction following. Supports native vision, and generally has more intelligence than GPT-4.1. Provides a 90% chat history cache discount.", "owned_by": "OpenAI", "root": "gpt-5", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000011364", "completion": "0.0000090909", "image": null, "request": null, "input_cache_read": "0.0000001136", "input_cache_write": null}, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "GPT-5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3045-200-wkomexlqbcxpravoniszumuijaodcygr.jpeg", "alt": "GPT-5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}, {"name": "websearch_reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "low"}, {"name": "reasoning_effort", "schema": {"enum": ["minimal", "low", "medium", "high"]}, "default_value": "minimal"}]}, {"id": "seedance-2.0-fast-el", "object": "model", "created": 1775794638727, "description": "Seedance 2.0 Fast is the speed-optimized version of Seedance 2.0, designed to generate cinematic videos with native audio sync, camera control, and stable motion more quickly. It is a strong choice for rapid iteration and high-volume production because it is built to deliver faster results at a lower cost than the standard version.\nThis model is served from Malaysia.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "seedance-2.0-fast-el", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Seedance-2.0-Fast-EL", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6930990-200-jegkeotdhlarpyycagpvdxazkjvgohpp.jpeg", "alt": "Seedance-2.0-Fast-EL model icon", "width": 200, "height": 200}, "url": "https://poe.com/seedance-2.0-fast-el"}, "reasoning": null, "parameters": [{"name": "mode", "schema": {"enum": ["auto", "t2v", "i2v_first", "i2v_both", "reference", "edit", "extend"]}, "default_value": "auto", "description": "Auto-detected from attachments, or override manually."}, {"name": "resolution", "schema": {"enum": ["480p", "720p"]}, "default_value": "720p", "description": "Output video resolution. Higher costs more."}, {"name": "aspect_ratio", "schema": {"enum": ["16:9", "9:16", "1:1", "4:3", "3:4", "21:9"]}, "default_value": "adaptive", "description": "Set to 'adaptive' by default \u2013 the model picks the best ratio from the input. Override if needed."}, {"name": "custom_duration", "schema": {"type": "boolean"}, "default_value": true, "description": "Enable to set a specific duration. When off, the model picks the best duration automatically."}, {"name": "duration", "schema": {"type": "number", "minimum": 4, "maximum": 15}, "default_value": 5, "description": "Generated video length (4\u201315 seconds)."}, {"name": "generate_audio", "schema": {"type": "boolean"}, "default_value": true, "description": "Include synchronized audio (voice, SFX, music). Put dialogue in double quotes in your prompt."}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "", "description": "Describe anything you want to avoid. Appended to the text prompt as guidance."}]}, {"id": "gpt-5-nano", "object": "model", "created": 1754429832540, "description": "GPT-5 nano is an extremely fast and cheap model, ideal for text/vision summarization/categorization tasks. Supports native vision and 400k input tokens of context. Provides a 90% chat history cache discount.", "owned_by": "OpenAI", "root": "gpt-5-nano", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000000455", "completion": "0.0000003636", "image": null, "request": null, "input_cache_read": "0.0000000045", "input_cache_write": null}, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "GPT-5-nano", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3044-200-vigmjnhxhcmtpotziybniyhxlrxzqumq.jpeg", "alt": "GPT-5-nano model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5-nano"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}, {"name": "websearch_reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "low"}, {"name": "reasoning_effort", "schema": {"enum": ["minimal", "low", "medium", "high"]}, "default_value": "minimal"}]}, {"id": "gpt-5-mini", "object": "model", "created": 1750886324513, "description": "GPT-5 mini is a small, fast & affordable model that matches or beats GPT-4.1 in many intelligence and vision-related tasks. Supports 400k tokens of context. Provides a 90% chat history cache discount.", "owned_by": "OpenAI", "root": "gpt-5-mini", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000002273", "completion": "0.0000018182", "image": null, "request": null, "input_cache_read": "0.0000000227", "input_cache_write": null}, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "GPT-5-mini", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3041-200-ueshdgoiiwjqdalhsqddlcujhfbzubrb.jpeg", "alt": "GPT-5-mini model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5-mini"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}, {"name": "websearch_reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "low"}, {"name": "reasoning_effort", "schema": {"enum": ["minimal", "low", "medium", "high"]}, "default_value": "minimal"}]}, {"id": "gemini-2.5-flash-lite", "object": "model", "created": 1750348180783, "description": "A lightweight Gemini 2.5 Flash reasoning model optimized for cost efficiency and low latency. Supports web search. Supports 1 million tokens of input context. Serves the latest `gemini-2.5-flash-lite-preview-09-2025` snapshot. For more complex queries, use https://poe.com/Gemini-2.5-Pro or https://poe.com/Gemini-2.5-Flash", "owned_by": "Google", "root": "gemini-2.5-flash-lite", "architecture": {"input_modalities": ["text", "image", "video", "audio"], "output_modalities": ["text"], "modality": "text,image,video,audio->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000000707", "completion": "0.0000002828", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 1024000, "max_output_tokens": 64000}, "context_length": 1024000, "metadata": {"display_name": "Gemini-2.5-Flash-Lite", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6020-200-frdcemsrroshgkgvrrvnrexbzfirnijo.jpeg", "alt": "Gemini-2.5-Flash-Lite model icon", "width": 200, "height": 200}, "url": "https://poe.com/gemini-2.5-flash-lite"}, "reasoning": {"budget": {"max_tokens": 24576, "min_tokens": 0}, "required": false, "supports_reasoning_effort": false}, "parameters": [{"name": "thinking_budget", "schema": {"type": "number", "minimum": 0, "maximum": 24576}, "default_value": 0, "description": "The maximum number of tokens to spend on thinking."}, {"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "gpt-5-codex", "object": "model", "created": 1758670845487, "description": "GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. It supports multimodal inputs such as images or screenshots for UI development and a 400k token context window.\n\nNote:\nWe recommend using GPT-5-Codex only for agentic and interactive coding use cases.\n\nOptional parameter:\nSet reasoning effort: Select from `minimal`, `low`, `medium`, `high`. Minimal reasoning effort is set by default", "owned_by": "OpenAI", "root": "gpt-5-codex", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000011364", "completion": "0.0000090909", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 400000, "max_output_tokens": 128000}, "context_length": 400000, "metadata": {"display_name": "GPT-5-Codex", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3047-200-hhoigayewqibyxyfiibwqvpwtujjxlvv.jpeg", "alt": "GPT-5-Codex model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-5-codex"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "grok-4-fast-non-reasoning", "object": "model", "created": 1758058214655, "description": "Grok 4 Fast Non-Reasoning is designed for fast, efficient tasks like content generation with a 2M token context window. Combining cutting-edge performance with cost-efficiency, it ensures high-quality results for simpler, everyday applications.", "owned_by": "XAI", "root": "grok-4-fast-non-reasoning", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.000000202", "completion": "0.0000005051", "image": null, "request": null, "input_cache_read": "0.0000000505", "input_cache_write": null}, "context_window": {"context_length": 2000000, "max_output_tokens": null}, "context_length": 2000000, "metadata": {"display_name": "Grok-4-Fast-Non-Reasoning", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6423573-200-ggwgnizxgkhvcotayupbjjtkejmhtdep.jpeg", "alt": "Grok-4-Fast-Non-Reasoning model icon", "width": 200, "height": 200}, "url": "https://poe.com/grok-4-fast-non-reasoning"}, "reasoning": null, "parameters": []}, {"id": "qwen-3-next-80b-think", "object": "model", "created": 1757556610505, "description": "The Qwen3-Next-80B-Think (with thinking mode enabled by default) is the next-generation foundation model released by Qwen, optimized for extreme context length and large-scale parameter efficiency, also known as \"Qwen3-Next-80B-A3B-Thinking.\" Despite its ultra-efficiency, it outperforms Qwen3-32B on downstream tasks - while requiring less than 1/10 of the inference cost. Moreover, it delivers over 10x higher inference throughput than Qwen3-32B when handling contexts longer than 32k tokens. This is the thinking version of https://poe.com/Qwen3-Next-80B, supports 65k tokens of context. \n\nOptional Parameters:\nUse additional input beside attachment button to manage the optional parameters:\n1. Enable/Disable Thinking - This will cause the model to think about the response before giving a final answer.\n\nTechnical Specifications:\nFile Support: PDF, DOC and XLSX files\nFile Attachment Limitation: Audio, video and image files\nContext Window: 65k tokens", "owned_by": "Novita AI", "root": "qwen-3-next-80b-think", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0030", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen-3-Next-80B-Think", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6407450-200-srepqohpmkzcozqfseocgjujkgbrddny.jpeg", "alt": "Qwen-3-Next-80B-Think model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen-3-next-80b-think"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "This will cause the model to think about the response before giving a final answer."}]}, {"id": "qwen3-next-80b", "object": "model", "created": 1757556042820, "description": "The Qwen3-Next-80B is the next-generation foundation model released by Qwen, optimized for extreme context length and large-scale parameter efficiency, also known as \"Qwen3-Next-80B-A3B.\" Despite its ultra-efficiency, it outperforms Qwen3-32B on downstream tasks - while requiring less than 1/10 of the training cost.\nMoreover, it delivers over 10x higher inference throughput than Qwen3-32B when handling contexts longer than 32k tokens. \n\nOptional parameters:\nEnable thinking about the response before giving a final answer: toggle it `off`, otherwise it is `on`  by default.\n\nNote:\nThis is the non-thinking version of https://poe.com/Qwen3-Next-80B-Think; supports 65k tokens of context.", "owned_by": "Novita AI", "root": "qwen3-next-80b", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0024", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3-Next-80B", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6407422-200-pzgrwhzwpgskzhvkhspdewiyyboufxuk.jpeg", "alt": "Qwen3-Next-80B model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3-next-80b"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "This will cause the model to think about the response before giving a final answer."}]}, {"id": "deepseek-v3.2-exp", "object": "model", "created": 1759164328100, "description": "DeepSeek-V3.2-Exp is an experimental model introducing the groundbreaking DeepSeek Sparse Attention (DSA) mechanism for enhanced long-context processing efficiency.\n\nBuilt on V3.1-Terminus, DSA achieves fine-grained sparse attention while maintaining identical output quality. This delivers substantial computational efficiency improvements without compromising accuracy.\n\nComprehensive benchmarks confirm V3.2-Exp matches V3.1-Terminus performance, proving efficiency gains don't sacrifice capability. As both a powerful tool and research platform, it establishes new paradigms for efficient long-context AI processing.\n\nOptional Parameters:\nUse additional input beside attachment button to manage the optional parameters:\n1. Enable/Disable Thinking - This will cause the model to think about the response before giving a final answer.\n\nTechnical Specifications:\n\nFile Support: Text, Markdown and PDF files\nContext window: 160k tokens", "owned_by": "Novita AI", "root": "deepseek-v3.2-exp", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0039", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "DeepSeek-V3.2-Exp", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6460300-200-pnsvtoldsobnuowitojgcvpkjjogaxpk.jpeg", "alt": "DeepSeek-V3.2-Exp model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepseek-v3.2-exp"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "This will cause the model to think about the response before giving a final answer."}]}, {"id": "nova-pro-1.0", "object": "model", "created": 1733715164341, "description": "Amazon Nova Pro 1.0 is a highly capable multimodal foundation model from Amazon Nova, offering a strong balance of accuracy, speed, and cost for processing text, images, and video. Its context window is 300,000 tokens, which enables handling very large inputs (including up to ~30 minutes of video input) in a single request.\n\nOptional parameter:\nLatency Optimized Inference to enable faster inference at a higher cost. It is `off` by default.\nNote that if enabled, costs may increase. Check the rate card for more information.", "owned_by": "EmpirioLabs AI", "root": "nova-pro-1.0", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Nova-Pro-1.0", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5389590-200-vegkdcsupcryqvnirxtllbfkvsqhmxjv.jpeg", "alt": "Nova-Pro-1.0 model icon", "width": 200, "height": 200}, "url": "https://poe.com/nova-pro-1.0"}, "reasoning": null, "parameters": [{"name": "enable_latency_optimized", "schema": {"type": "boolean"}, "default_value": false, "description": "Enables faster inference at higher cost."}]}, {"id": "nova-premier-1.0", "object": "model", "created": 1757959733022, "description": "Note: This model will be retired on September 14, 2026\nThe Amazon Nova Premier 1.0 model is Amazon\u2019s most capable foundation model, able to handle extremely long contexts (\u2248\u202f1 million tokens) and multimodal inputs like text, images, and video while excelling at complex, multi\u2011step tasks across tools and data sources. \nIt supports chain\u2011of\u2011thought style reasoning and breaks down problems into intermediate steps before arriving at an answer, improving coherence and accuracy.\n\nOptional parameter:\nEnable thinking about the response before giving a final answer: toggle it `off`, otherwise it is `on` by default.", "owned_by": "EmpirioLabs AI", "root": "nova-premier-1.0", "architecture": {"input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "modality": "text,image,video->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000030303", "completion": "0.0000151515", "image": null, "request": null, "input_cache_read": "0.0000016667", "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Nova-Premier-1.0", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6420137-200-hisjdivnqbcsnphixafergqmkdpzieqw.jpeg", "alt": "Nova-Premier-1.0 model icon", "width": 200, "height": 200}, "url": "https://poe.com/nova-premier-1.0"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Enable chain-of-thought reasoning."}]}, {"id": "grok-4-fast-reasoning", "object": "model", "created": 1758058244361, "description": "Grok 4 Fast Reasoning delivers exceptional performance for tasks requiring logical thinking and problem-solving. With a 2M token context window and state-of-the-art cost-efficiency, it handles complex reasoning tasks with accuracy and speed, making advanced AI capabilities accessible to more users.", "owned_by": "XAI", "root": "grok-4-fast-reasoning", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.000000202", "completion": "0.0000005051", "image": null, "request": null, "input_cache_read": "0.0000000505", "input_cache_write": null}, "context_window": {"context_length": 2000000, "max_output_tokens": null}, "context_length": 2000000, "metadata": {"display_name": "Grok-4-Fast-Reasoning", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6423574-200-abwqldpghfsdrphuhpltkxbegfrdzavv.jpeg", "alt": "Grok-4-Fast-Reasoning model icon", "width": 200, "height": 200}, "url": "https://poe.com/grok-4-fast-reasoning"}, "reasoning": null, "parameters": []}, {"id": "nova-micro-1.0", "object": "model", "created": 1733714662051, "description": "Amazon Nova Micro is a text-only foundation model in the Amazon Nova family, designed for ultra\u2011low latency and very low cost, optimized for tasks like summarization, translation, and interactive chat. It supports a context window of 128,000 tokens, enabling handling of large text inputs in a single request.", "owned_by": "EmpirioLabs AI", "root": "nova-micro-1.0", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000000404", "completion": "0.0000001616", "image": null, "request": null, "input_cache_read": "0.0000000222", "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Nova-Micro-1.0", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5389559-200-ndlbiqdnxlqsttihcubiwziedgoiittj.jpeg", "alt": "Nova-Micro-1.0 model icon", "width": 200, "height": 200}, "url": "https://poe.com/nova-micro-1.0"}, "reasoning": null, "parameters": []}, {"id": "nova-lite-1.0", "object": "model", "created": 1733713614756, "description": "Amazon Nova Lite is a low\u2011cost multimodal foundation model from Amazon that can process text, images, and video and is optimized for speed and affordability. It offers a context window of 300,000 tokens, allowing handling of very large inputs in a single request (including up to ~30 minutes of video).", "owned_by": "EmpirioLabs AI", "root": "nova-lite-1.0", "architecture": {"input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "modality": "text,image,video->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000000697", "completion": "0.0000002828", "image": null, "request": null, "input_cache_read": "0.0000000383", "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Nova-Lite-1.0", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5389486-200-qqqaqlmrfqfcunlwwutanazrvoolueqf.jpeg", "alt": "Nova-Lite-1.0 model icon", "width": 200, "height": 200}, "url": "https://poe.com/nova-lite-1.0"}, "reasoning": null, "parameters": []}, {"id": "minimax-m2", "object": "model", "created": 1761655367061, "description": "MiniMax-M2 redefines efficiency for agents. It's a compact, fast, and cost-effective MoE model (230 billion total parameters with 10 billion active parameters) built for elite performance in coding and agentic tasks, all while maintaining powerful general intelligence. With just 10 billion activated parameters, MiniMax-M2 provides the sophisticated, end-to-end tool use performance expected from today's leading models, but in a streamlined form factor that makes deployment and scaling easier than ever.\n\nTechnical Specifications\n\nFile Support: Text, Markdown and PDF files\nContext window: 200k tokens", "owned_by": "Novita AI", "root": "minimax-m2", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0033", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Minimax-M2", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6537104-200-btaglblcbpevqelhbgtgxfacucpssuzs.jpeg", "alt": "Minimax-M2 model icon", "width": 200, "height": 200}, "url": "https://poe.com/minimax-m2"}, "reasoning": null, "parameters": []}, {"id": "hunyuan-image-3", "object": "model", "created": 1764454998989, "description": "Hunyuan Image 3.0 is Tencent\u2019s next\u2011generation open\u2011source text-to-image model that uses a large multimodal Mixture-of-Experts architecture to unify image understanding and generation in one system. It produces high-fidelity, often photorealistic images with strong prompt adherence, multilingual text rendering, and intelligent world-knowledge reasoning that can enrich sparse prompts with appropriate visual details.\n\nNote: Uploading attachments is not supported. \n\nParameter controls available:\n1. Image Settings\n   Size / Aspect Ratio\n   - Default: 1024x1024 (Square 1:1)\n   -  768x1024 (Portrait 3:4)\n   -  1024x768 (Landscape 4:3)\n   -  1024x1536 (Tall Portrait 2:3)\n   -  1536x1024 (Wide Landscape 3:2)\n   -  512x512 (Small Square 1:1)\n\n   Quantity\n   -  number of images to generate. select from 1 to 4. (default: 1)\n\n   Quality & Generation\n   - Inference steps. Number of denoising steps for quality, select from 10 to 50. (default: 28, higher = better quality but slower)\n   - Guidance scale. Set to how closely to follow prompt, select from 1.0 to 20. (default: 7.5)\n\n   Customization\n   - Negative prompt. Type things to avoid in generated images\n   - Seed. Random seed number for reproducible generation with fixed seed (e.g., 42)", "owned_by": "EmpirioLabs AI", "root": "hunyuan-image-3", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Hunyuan-Image-3", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6628990-200-ikihqazvenuwawsukbrvhycckgluukmh.jpeg", "alt": "Hunyuan-Image-3 model icon", "width": 200, "height": 200}, "url": "https://poe.com/hunyuan-image-3"}, "reasoning": null, "parameters": [{"name": "size", "schema": {"enum": ["1024x1024", "768x1024", "1024x768", "1024x1536", "1536x1024", "512x512"]}, "default_value": "1024x1024", "description": "Dimensions of the generated image."}, {"name": "num_images", "schema": {"type": "number", "minimum": 1, "maximum": 4}, "default_value": 1, "description": "Number of images to generate (1-4)."}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "", "description": "Things to avoid in the generated image."}, {"name": "num_inference_steps", "schema": {"type": "number", "minimum": 10, "maximum": 50}, "default_value": 28, "description": "Number of denoising steps (higher = better quality, slower)."}, {"name": "guidance_scale", "schema": {"type": "number", "minimum": 1.0, "maximum": 20.0}, "default_value": 7.5, "description": "How closely to follow the prompt."}, {"name": "seed", "schema": {"type": "string"}, "default_value": "", "description": "Random seed for reproducible generation (integer)."}]}, {"id": "kling-image-o1", "object": "model", "created": 1764675160909, "description": "Kling Image O1 image generation and image editing bot. Send up to 10 images to use as a reference, and refer to each image with $image1, $image2, etc. in the prompt to specify interactions. \n\nOptional parameters:\nSet aspect ratio. Select from (21:9, 16:9, 4:3, 1:1, 3:4, 9:16). It is set to 16:9 aspect ratio as default.\nSet Resolution. Select from (1K, 2K). It is set to 1K resolution as default.\n\nNotes:\nSupports jpeg, png, heic, webp images.", "owned_by": "fal", "root": "kling-image-o1", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Kling-Image-O1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6635808-200-rpyhbjjjtdrcayjhfrcjvixzxfpffyna.jpeg", "alt": "Kling-Image-O1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/kling-image-o1"}, "reasoning": null, "parameters": [{"name": "resolution", "schema": {"enum": ["1K", "2K"]}, "default_value": "1K", "description": "Image resolution"}, {"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "auto"]}, "default_value": "auto"}]}, {"id": "kling-2.6-pro", "object": "model", "created": 1764786565451, "description": "Generate high-quality videos with native audio from text and images using Kling 2.6 Pro. \n\nOptional parameters:\n- Negative prompt. Type things to avoid in generated images\n- CFG Scale. To send a classifier-free guidance scale between 0.0 and 1.0. This is set to 0.5 as default\n- Set aspect ratio. Select from (16:9, 1:1, 9:16). It is set to 16:9 aspect ratio as default.\n- Set Duration. Select from (5 seconds or 10 seconds) to specify video length in seconds. Set to 5 seconds as default.\n- Silent Mode. Toggle `on` to use silent mode for video generation. This will generate a video without audio, decreasing the cost.", "owned_by": "fal", "root": "kling-2.6-pro", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": ["/v1/videos"], "pricing": null, "context_window": {"context_length": 256, "max_output_tokens": null}, "context_length": 256, "metadata": {"display_name": "Kling-2.6-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6639547-200-rgytkpcmmujqmveqojrmiyobcqoyhymy.jpeg", "alt": "Kling-2.6-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/kling-2.6-pro"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "1:1", "9:16"]}, "default_value": "16:9"}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "blur, distort, and low quality"}, {"name": "cfg_scale", "schema": {"type": "number", "minimum": 0.0, "maximum": 1.0}, "default_value": 0.5, "description": "Classifer Guidance Scale for generation."}, {"name": "duration", "schema": {"enum": ["5", "10"]}, "default_value": "5", "description": "Video duration in seconds"}, {"name": "silent", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to use silent mode for video generation. This will generate a video without audio, decreasing the cost."}]}, {"id": "flux-2-pro", "object": "model", "created": 1764085507021, "description": "Flux.2 [Pro] is Black Forest Labs' state-of-the-art model with multi-reference support, fine-grained text rendering, and other features. Supports structured JSON prompts, and allows use of hex colour codes within the prompt for precise colouring.  Send images (Up to 8 images) in jpeg/png/webp format for editing. Total megapixels (input + output) should not exceed 9 megapixels.\n\nOptional parameter:\nSet aspect ratio. Select from (16:9, 4:3, 1:1, 3:4, 9:16). It is set to 4:3 aspect ratio as default.", "owned_by": "fal", "root": "flux-2-pro", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "FLUX-2-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6617199-200-izgeccajgtwsteggpjqemffleqasubrr.jpeg", "alt": "FLUX-2-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-2-pro"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "flux-2-flex", "object": "model", "created": 1764085409921, "description": "Flux.2 [Flex] is Black Forest Lab's latest model, with Multi-Reference Support, Fine-grained text rendering, and other features. Supports structured JSON prompts, and allows use of hex color codes within the prompt for precise coloring.\nSend images in jpeg/png/webp format for editing. Total megapixels (input + output) should not exceed 14 megapixels.\n\nOptional parameters:\nSet aspect ratio. Select from (16:9, 4:3, 1:1, 3:4, 9:16). It is set to 4:3 aspect ratio as default.", "owned_by": "fal", "root": "flux-2-flex", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "FLUX-2-Flex", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6617190-200-gdwhqnerakvztudzrbjpgynelkhjkuab.jpeg", "alt": "FLUX-2-Flex model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-2-flex"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "flux-2-dev", "object": "model", "created": 1764084262252, "description": "Open-weight image gen (32B) model, derived from the FLUX.2 base model. The most powerful open-weight image generation and editing model available today, combining text-to-image synthesis and image editing with multiple input images in a single checkpoint.\n\nOptional parameters:\nSet aspect ratio. Select from (16:9, 4:3, 1:1, 3:4, 9:16). It is set to 4:3 aspect ratio as default.", "owned_by": "fal", "root": "flux-2-dev", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "FLUX-2-Dev", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6617135-200-hfexvrdcdgdfmcyshdetghojdopomoqh.jpeg", "alt": "FLUX-2-Dev model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-2-dev"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "mistral-medium-3.1", "object": "model", "created": 1758398334743, "description": "Mistral Medium 3.1 is a high-performance, enterprise-grade language model that delivers strong reasoning, coding, and STEM capabilities. It supports hybrid, on-prem, and in-VPC deployments, offering competitive accuracy and easy integration across cloud environments. Context Length: 131k", "owned_by": "EmpirioLabs AI", "root": "mistral-medium-3.1", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000005253", "completion": "0.0000026263", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Mistral-Medium-3.1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6435763-200-qbwqniiwyzudzgkszewklvxvvbztrjcr.jpeg", "alt": "Mistral-Medium-3.1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/mistral-medium-3.1"}, "reasoning": null, "parameters": []}, {"id": "exa-answer", "object": "model", "created": 1764188987964, "description": "Get a quick LLM-style answer to a question informed by Exa search results. \n\nFor more in-depth results, consider using the following endpoint: https://poe.com/Exa-Research\n\nSupported file type upload: PDF, TXT, PNG, JPG, JPEG\nAudio and video file upload is not supported.\n\nParameter Controls Available:\n- Include source text snippets. Toggle `on` to show text snippets under each source citation. This is set to `off` by default.", "owned_by": "EmpirioLabs AI", "root": "exa-answer", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Exa-Answer", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6621159-200-wpchsfaskzxpxvnzggpohstrfjjxcgqv.jpeg", "alt": "Exa-Answer model icon", "width": 200, "height": 200}, "url": "https://poe.com/exa-answer"}, "reasoning": null, "parameters": [{"name": "text", "schema": {"type": "boolean"}, "default_value": false, "description": "Show short text snippets from sources under each citation."}]}, {"id": "exa-search", "object": "model", "created": 1764132329592, "description": "Utilize Exa's technology for searching web pages, finding similar web pages, crawling, and more.\nNote: This endpoint does not return an LLM-style response (visit the following if you want an LLM-style response: https://poe.com/Exa-Answer or https://poe.com/Exa-Research). File upload is not supported. \n\nParameter Controls Available:\n1. Operation Mode\n   - Default: Web Search\n   - Find Similar pages. For finding similar pages.\n   - Get page contents. For getting page contents.\n   - Code search. For code search.\n\n2. Search Settings (search operation)\n   - Search Type: Select from Auto (Intelligent), Instant (Sub-150ms), Neural (Embeddings), Deep Search (Exa 2.1) and Fast (Streamlined). Default: Auto (Intelligent)\n   - Show Full Content. Toggle to display full page content in results\n   - Include domains. Include comma-separated domains to include\n   - Include text. Input text that must appear (up to 5 words)\n   - Exclude text. Input text that must NOT appear (up to 5 words)\n  \n3. Common Search Settings (search & similar operations)\n   - Number of results: Select from 1 to 100 to set number of results to return. This is set to 10 by default.\n   - Category Filter: All Categories, Company, Research Paper, News, PDF, Github, Tweet, Personal Site, LinkedIn Profile, Financial Report. This is set to None by default\n   - Exclude domains. Include comma-separated domains to exclude\n\n4. Date Filters (search operation)\n   - Start Crawl Date. Results crawled after this date (ISO 8601)\n   - End Crawl Date. Results crawled before this date (ISO 8601)\n   - Start Published Date. Content published after this date (ISO 8601)\n   - End Published Date. Content published before this date (ISO 8601)\n\n5. Content Options (search, similar, & contents operations)\n   - Return Text. Toggle to fetch page text content (default: on)\n   - Max Characters. Set number to limit text length (empty = unlimited)\n   - Include HTML Tags. Toggle `on` to preserve HTML structure. (default: off)\n   - Return Highlights. Toggle `on` to get AI-selected key snippets. (default: off)\n   - Sentences per highlight. Set sentences per highlight from 1 to 10. (default: 3)\n   - Highlights per page. Set highlights per result from 1 to 10. (default: 3)\n   - Highlights query. Set text to guide highlight selection\n   - Return Summary. Toggle `on` to get AI-generated summaries. (default: off)\n   - Summary query. Set text to guide summary generation\n\n6. Advanced Options (search, similar, & contents operations)\n   - Livecrawl Mode: Fallback (Cache first), Never (Cache only), Always (Fresh Only), Preferred (Fresh Preferred). Default: Fallback\n   - Subpages to crawl. Set number of linked subpages to crawl from 0 to 10. (default: 0)\n   - Subpage Target. Set text to find specific subpages matching keyword\n\n7. Code Search Controls (code operation)\n   - `--code_tokens Response Length. Set maximum length of code search results. Select from Dynamic (Optimal), 5000 tokens (Standard), 10000 tokens (Extended), 20000 tokens (Maximum). This is set to Dynamic as default.", "owned_by": "EmpirioLabs AI", "root": "exa-search", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Exa-Search", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6618908-200-btxsxymfvapwkqgprofctgjokqhxvdxy.jpeg", "alt": "Exa-Search model icon", "width": 200, "height": 200}, "url": "https://poe.com/exa-search"}, "reasoning": null, "parameters": [{"name": "operation", "schema": {"enum": ["search", "similar", "contents", "code"]}, "default_value": "search", "description": "Select the type of search you want to perform"}, {"name": "search_type", "schema": {"enum": ["auto", "instant", "neural", "deep", "fast"]}, "default_value": "auto", "description": "Choose the search algorithm"}, {"name": "num_results", "schema": {"type": "number", "minimum": 1, "maximum": 100}, "default_value": 10, "description": "How many similar pages to find"}, {"name": "category", "schema": {"enum": ["", "company", "research paper", "news", "pdf", "github", "tweet", "personal site", "linkedin profile", "financial report"]}, "default_value": "", "description": "Filter similar pages by type"}, {"name": "show_content", "schema": {"type": "boolean"}, "default_value": true, "description": "Display complete page content in results"}, {"name": "include_domains", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated domains to include (e.g., arxiv.org, github.com)"}, {"name": "exclude_domains", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated domains to exclude"}, {"name": "include_text", "schema": {"type": "string"}, "default_value": "", "description": "Text that must appear (up to 5 words)"}, {"name": "exclude_text", "schema": {"type": "string"}, "default_value": "", "description": "Text that must NOT appear (up to 5 words)"}, {"name": "start_crawl_date", "schema": {"type": "string"}, "default_value": "", "description": "Results crawled after this date (ISO 8601)"}, {"name": "end_crawl_date", "schema": {"type": "string"}, "default_value": "", "description": "Results crawled before this date (ISO 8601)"}, {"name": "start_published_date", "schema": {"type": "string"}, "default_value": "", "description": "Content published after this date (ISO 8601)"}, {"name": "end_published_date", "schema": {"type": "string"}, "default_value": "", "description": "Content published before this date (ISO 8601)"}, {"name": "return_text", "schema": {"type": "boolean"}, "default_value": true, "description": "Fetch page text content"}, {"name": "text_max_chars", "schema": {"type": "string"}, "default_value": "", "description": "Limit text length (empty = unlimited)"}, {"name": "include_html_tags", "schema": {"type": "boolean"}, "default_value": false, "description": "Preserve HTML structure"}, {"name": "return_highlights", "schema": {"type": "boolean"}, "default_value": false, "description": "Get AI-selected key snippets"}, {"name": "highlights_sentences", "schema": {"type": "number", "minimum": 1, "maximum": 10}, "default_value": 3, "description": "Sentences in each highlight"}, {"name": "highlights_per_url", "schema": {"type": "number", "minimum": 1, "maximum": 10}, "default_value": 3, "description": "Number of highlights per result"}, {"name": "highlights_query", "schema": {"type": "string"}, "default_value": "", "description": "Guide highlight selection"}, {"name": "return_summary", "schema": {"type": "boolean"}, "default_value": false, "description": "Get AI-generated summaries"}, {"name": "summary_query", "schema": {"type": "string"}, "default_value": "", "description": "Guide summary generation"}, {"name": "livecrawl", "schema": {"enum": ["fallback", "never", "always", "preferred"]}, "default_value": "fallback", "description": "When to fetch fresh content"}, {"name": "subpages", "schema": {"type": "number", "minimum": 0, "maximum": 10}, "default_value": 0, "description": "Number of linked subpages to fetch"}, {"name": "subpage_target", "schema": {"type": "string"}, "default_value": "", "description": "Keyword to find specific subpages"}, {"name": "code_tokens", "schema": {"enum": ["dynamic", "5000", "10000", "20000"]}, "default_value": "dynamic", "description": "Maximum length of code search results"}]}, {"id": "exa-research", "object": "model", "created": 1764196282185, "description": "Create an asynchronous research task that explores the web, gathers sources, synthesizes findings, and returns results with citations.\n\nNote: Responses may take several minutes to complete depending on complexity.\n\nSupported file type upload: PDF, TXT, PNG, JPG, JPEG\nAudio and video file upload is not supported.\n\nParameter Controls Available:\nModel Selection\n   - `exa research` (Standard, default)\n   - `exa research pro` (Deepest, highest quality)\n   - `exa research fast` (Fastest, lightest)", "owned_by": "EmpirioLabs AI", "root": "exa-research", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Exa-Research", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6621333-200-btbdlssilclodaosxcuaqwggdnqvlifm.jpeg", "alt": "Exa-Research model icon", "width": 200, "height": 200}, "url": "https://poe.com/exa-research"}, "reasoning": null, "parameters": [{"name": "model", "schema": {"enum": ["exa-research", "exa-research-pro", "exa-research-fast"]}, "default_value": "exa-research", "description": "Select the Exa research model."}]}, {"id": "nova-lite-2", "object": "model", "created": 1764827272207, "description": "Amazon Nova 2 Lite is a fast, cost-effective multimodal reasoning model from Amazon that can process text, images, documents, and video, designed for everyday workloads like chatbots, document processing, and business automation. It offers a 1 million token context window, enabling very large, complex inputs in a single request, including long documents and extended video clips (~90 minutes).\n\nNotes: \n- Video file uploads are limited to ~1GB. Also note that reasoning traces are not exposed from AWS.\n- Supported file types: JPEG, PNG, GIF, WEBP, PDF, DOCX, TXT, MP4, MOV, MKV, WebM, FLV, MPEG, MPG, WMV, 3GP\n\nParameter controls available:\n- Enable Extended thinking. Enable step-by-step reasoning (default: on).\n- Set reasoning effort: Select from  low (faster), medium (balanced) , high (deep analysis). Default: medium (balanced)", "owned_by": "EmpirioLabs AI", "root": "nova-lite-2", "architecture": {"input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "modality": "text,image,video->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000003838", "completion": "0.0000031919", "image": null, "request": null, "input_cache_read": "0.0000002111", "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Nova-Lite-2", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6640726-200-ndgdrjlscsycabknxryewozpnkerfrta.jpeg", "alt": "Nova-Lite-2 model icon", "width": 200, "height": 200}, "url": "https://poe.com/nova-lite-2"}, "reasoning": null, "parameters": [{"name": "enable_reasoning", "schema": {"type": "boolean"}, "default_value": true, "description": "Enable step-by-step reasoning."}, {"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium", "description": "Depth of analysis."}]}, {"id": "gpt-oss-120b-t", "object": "model", "created": 1754415494029, "description": "OpenAI's GPT-OSS-120B delivers sophisticated chain-of-thought reasoning capabilities in a fully open model. Built with community feedback and released under Apache 2.0, this 120B parameter model provides transparency, customization, and deployment flexibility for organizations requiring complete data security & privacy control.", "owned_by": "Together AI", "root": "gpt-oss-120b-t", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0015", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "GPT-OSS-120B-T", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6296670-200-cviogrqtllylqonxwpdaanmsuldaesyl.jpeg", "alt": "GPT-OSS-120B-T model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-oss-120b-t"}, "reasoning": null, "parameters": []}, {"id": "gpt-oss-20b-t", "object": "model", "created": 1754495737130, "description": "OpenAI's GPT-OSS-20B provides powerful chain-of-thought reasoning in an efficient 20B parameter model. Designed for single-GPU deployment while maintaining sophisticated reasoning capabilities, this Apache 2.0 licensed model offers the perfect balance of performance and resource efficiency for diverse applications.", "owned_by": "Together AI", "root": "gpt-oss-20b-t", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.00045", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "GPT-OSS-20B-T", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6299609-200-enarjfukkdmfvqhltcohzkxhyqjwmzvm.jpeg", "alt": "GPT-OSS-20B-T model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-oss-20b-t"}, "reasoning": null, "parameters": []}, {"id": "amazon-nova-reel-1.1", "object": "model", "created": 1757629656513, "description": "Amazon Nova Reel 1.1 is an advanced AI video generation model that creates up to 2-minute multi-shot videos from text and optional image prompts, offering improved video quality, latency, and visual consistency compared to its predecessor.", "owned_by": "EmpirioLabs AI", "root": "amazon-nova-reel-1.1", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Amazon-Nova-Reel-1.1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6410095-200-rdqodkbcitopgrvwtdqcajdlsefmlrky.jpeg", "alt": "Amazon-Nova-Reel-1.1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/amazon-nova-reel-1.1"}, "reasoning": null, "parameters": [{"name": "duration", "schema": {"type": "number", "minimum": 6, "maximum": 120}, "default_value": 6, "description": "Select the length of the video (multiple of 6 seconds). Longer videos take more time to generate."}, {"name": "fps", "schema": {"enum": ["24"]}, "default_value": "24", "description": "Fixed at 24 FPS"}, {"name": "dimension", "schema": {"enum": ["1280x720"]}, "default_value": "1280x720", "description": "Fixed at 1280x720 (16:9)"}, {"name": "seed", "schema": {"type": "string"}, "default_value": "", "description": "Seed value for generation consistency (0-2147483646). Leave blank for random."}, {"name": "manual_mode", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable to provide separate prompts for each shot in the main text box (one per line, no overall prompt). Images are optional and can be mixed per shot."}, {"name": "image_shots", "schema": {"type": "string"}, "default_value": "", "description": "Specify shot numbers (1 to duration/6) for image assignment using a comma-separated list (e.g., '1,3' for shots 1 and 3). Upload exactly that many 1280x720 images. Images are assigned in upload order to the listed shots (first image to the lowest number, etc.). If left blank and images are uploaded, they will be assigned to the first N shots where N is the number of images (if N <= duration/6), or to all shots if N equals duration/6."}]}, {"id": "amazon-nova-canvas", "object": "model", "created": 1757741443323, "description": "Note: This model will be retired on September 30, 2026\nAmazon Nova Canvas is a high-quality image\u2010generation model that creates and edits images from text or image inputs\u2014offering features like inpainting/outpainting, virtual try\u2011on, style controls, and background removal\u2014all with built\u2011in customization.", "owned_by": "EmpirioLabs AI", "root": "amazon-nova-canvas", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Amazon-Nova-Canvas", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6413707-200-ehrflxbyvrmjfvebtathkvouhbpqlsew.jpeg", "alt": "Amazon-Nova-Canvas model icon", "width": 200, "height": 200}, "url": "https://poe.com/amazon-nova-canvas"}, "reasoning": null, "parameters": [{"name": "task_type", "schema": {"enum": ["TEXT_IMAGE", "IMAGE_VARIATION", "INPAINTING", "OUTPAINTING", "BACKGROUND_REMOVAL", "COLOR_GUIDED_GENERATION", "VIRTUAL_TRY_ON"]}, "default_value": "TEXT_IMAGE", "description": "Select the generation task."}, {"name": "quality", "schema": {"enum": ["standard", "premium"]}, "default_value": "standard", "description": "Generation quality."}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "", "description": "Elements to avoid in generation (optional)."}, {"name": "number_of_images", "schema": {"type": "number", "minimum": 1, "maximum": 5}, "default_value": 1, "description": "Number of images to generate (1-5)."}, {"name": "size_scale", "schema": {"enum": ["small", "large"]}, "default_value": "small", "description": "Choose resolution scale (affects pricing and max dimensions)."}, {"name": "aspect_ratio", "schema": {"enum": ["1:1", "3:4", "2:3", "9:16", "1:2", "1:3", "1:4", "4:3", "3:2", "16:9", "2:1", "3:1", "4:1"]}, "default_value": "1:1", "description": "Select image proportions."}, {"name": "cfg_scale", "schema": {"type": "number", "minimum": 1.0, "maximum": 20.0}, "default_value": 7.0, "description": "Prompt adherence (1.0-20.0)."}, {"name": "seed", "schema": {"type": "string"}, "default_value": "", "description": "Random seed (0-2147483647, blank for random)."}, {"name": "similarity_strength", "schema": {"type": "number", "minimum": 0.2, "maximum": 1.0}, "default_value": 0.7, "description": "How similar to input image (0.2-1.0)."}, {"name": "outpainting_mode", "schema": {"enum": ["DEFAULT", "PRECISE"]}, "default_value": "DEFAULT", "description": "Outpainting mode."}, {"name": "mask_prompt", "schema": {"type": "string"}, "default_value": "", "description": "Describe area to outpaint (e.g., 'edges'). If blank, defaults to 'edges'. Upload mask image as second attachment for precise control."}, {"name": "inpaint_mask_prompt", "schema": {"type": "string"}, "default_value": "", "description": "Describe area to inpaint (e.g., 'background', 'the cat'). Provide this OR upload mask image (black=replace, white=keep) as second attachment."}, {"name": "colors", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated hex colors (required, e.g., #FF0000,#00FF00). Upload a reference image for additional style/color guidance."}, {"name": "mask_type", "schema": {"enum": ["GARMENT", "PROMPT", "IMAGE"]}, "default_value": "GARMENT", "description": "Upload order: 1st = Person, 2nd = Garment. Select how to specify placement area below."}, {"name": "garment_class", "schema": {"enum": ["UPPER_BODY", "LOWER_BODY", "FOOTWEAR", "FULL_BODY"]}, "default_value": "UPPER_BODY", "description": "ONLY USE when Mask Type is 'Garment'. IGNORE for other mask types."}, {"name": "tryon_mask_prompt", "schema": {"type": "string"}, "default_value": "", "description": "ONLY USE when Mask Type is 'Text Prompt'. Describe where to place garment. Leave EMPTY for other mask types."}]}, {"id": "kimi-k2", "object": "model", "created": 1754618326493, "description": "Kimi K2-Instruct-0905 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities.\n\nKey Features:\n- Large-Scale Training: Pre-trained a 1T parameter MoE model on 15.5T tokens with zero training instability.\n- MuonClip Optimizer: We apply the Muon optimizer to an unprecedented scale, and develop novel optimization techniques to resolve instabilities while scaling up.\n- Agentic Intelligence: Specifically designed for tool use, reasoning, and autonomous problem-solving.\n\nTechnical Specifications\n\nFile Support: Attachments not supported\nContext window: 256k tokens", "owned_by": "Novita AI", "root": "kimi-k2", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0064", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Kimi-K2", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6304162-200-iagcsmuhwjsvgsksgfdgkxbczdeomjwx.jpeg", "alt": "Kimi-K2 model icon", "width": 200, "height": 200}, "url": "https://poe.com/kimi-k2"}, "reasoning": null, "parameters": []}, {"id": "kimi-k2.5-tog", "object": "model", "created": 1752510412371, "description": "Kimi K2.5 is an advanced mixture-of-experts (MoE) language model that builds on the K2 architecture with enhanced reasoning, coding, and long-context capabilities. With tens of billions of activated parameters and over a trillion total parameters, Kimi K2.5 is trained using optimized large-scale training techniques to deliver stronger performance across complex problem-solving, frontier knowledge, and agentic workflows, while improving efficiency, stability, and real-world applicability.", "owned_by": "Together AI", "root": "kimi-k2.5-tog", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.011", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Kimi-K2.5-Tog", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6222659-200-dtzpfzdczquckepesthegangtuhrfuqx.jpeg", "alt": "Kimi-K2.5-Tog model icon", "width": 200, "height": 200}, "url": "https://poe.com/kimi-k2.5-tog"}, "reasoning": null, "parameters": []}, {"id": "kimi-k2-instruct", "object": "model", "created": 1752519798608, "description": "Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities. Uses the latest September 5th, 2025 snapshot. The updated version has improved coding abilities, agentic tool use, and a longer (256K) context window.", "owned_by": "Fireworks AI", "root": "kimi-k2-instruct", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0061", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Kimi-K2-Instruct", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6223040-200-ovvvgxrlashsplbjdozqnkuyropwugzp.jpeg", "alt": "Kimi-K2-Instruct model icon", "width": 200, "height": 200}, "url": "https://poe.com/kimi-k2-instruct"}, "reasoning": null, "parameters": []}, {"id": "pika-v1.5-effects", "object": "model", "created": 1765555623083, "description": "Apply surprising, mind blowing effects to your photo with Pika-v1.5 Effects. Attach an image and be amazed by the effects like \"cakeify,\" \"crush\" and \"crumble\", open the parameter controls shelf for a full list of effects.\n\nFull list of effects:\nCake-ify, Crumble, Crush, Decapitate, Deflate, Dissolve, Explode, Eye-pop, Inflate, Levitate, Melt, Peel, Poke, Squish, Ta-da, Tear\n\nOptional parameters:\n- Seed. Random seed number for reproducible generation with fixed seed\n- Negative prompt. Type things to avoid in generated images", "owned_by": "fal", "root": "pika-v1.5-effects", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Pika-v1.5-Effects", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6664398-200-zwmsvcahqehasuqjztxejzokyceapdfa.jpeg", "alt": "Pika-v1.5-Effects model icon", "width": 200, "height": 200}, "url": "https://poe.com/pika-v1.5-effects"}, "reasoning": null, "parameters": [{"name": "effect", "schema": {"enum": ["Cake-ify", "Crumble", "Crush", "Decapitate", "Deflate", "Dissolve", "Explode", "Eye-pop", "Inflate", "Levitate", "Melt", "Peel", "Poke", "Squish", "Ta-da", "Tear"]}, "default_value": "Cake-ify"}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": ""}, {"name": "seed", "schema": {"type": "string"}, "description": "Seed to generate the video."}]}, {"id": "glm-4.5", "object": "model", "created": 1753966903844, "description": "The GLM-4.5 series models are foundation models designed for intelligent agents. GLM-4.5 has 355 billion total parameters with 32 billion active parameters, while GLM-4.5-Air adopts a more compact design with 106 billion total parameters and 12 billion active parameters. GLM-4.5 models unify reasoning, coding, and intelligent agent capabilities to meet the complex demands of intelligent agent applications. \n\nTechnical Specifications\n\nFile Support: PDF and Markdown files\nContext window: 128k tokens", "owned_by": "Novita AI", "root": "glm-4.5", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0058", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "GLM-4.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6280607-200-uswkwoveiefpllrgyqtttkrcnkjpplzc.jpeg", "alt": "GLM-4.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/glm-4.5"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "This will cause the model to think about the response before giving a final answer."}]}, {"id": "deepseek-v3.1-n", "object": "model", "created": 1755623272928, "description": "DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. Compared to the previous version, this upgrade brings improvements in multiple aspects:\n\n- Hybrid thinking mode: One model supports both thinking mode and non-thinking mode by changing the chat template.\n- Smarter tool calling: Through post-training optimization, the model's performance in tool usage and agent tasks has significantly improved.\n- Higher thinking efficiency: DeepSeek-V3.1-Think achieves comparable answer quality to DeepSeek-R1-0528, while responding more quickly.\n\nTechnical Specifications\n\nFile Support: Attachments not supported\nContext window: 128k tokens", "owned_by": "Novita AI", "root": "deepseek-v3.1-n", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0058", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "DeepSeek-V3.1-N", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6341293-200-wsgcvajyrdrokiwigoigrvzildyuehqx.jpeg", "alt": "DeepSeek-V3.1-N model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepseek-v3.1-n"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "This will cause the model to think about the response before giving a final answer."}]}, {"id": "claude-sonnet-4", "object": "model", "created": 1747860708348, "description": "Claude Sonnet 4 from Anthropic, supports customizable thinking budget (up to 61,440k tokens) and 1M context window.", "owned_by": "Anthropic", "root": "claude-sonnet-4", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/messages", "/v1/responses", "/v1/chat/completions"], "pricing": {"prompt": "0.0000025758", "completion": "0.0000128788", "image": null, "request": null, "input_cache_read": "0.0000002576", "input_cache_write": "0.0000032197"}, "context_window": {"context_length": 983040, "max_output_tokens": 64000}, "context_length": 983040, "metadata": {"display_name": "Claude-Sonnet-4", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-1031-200-dqlngpsimloscmetbgexlnisyaklljys.jpeg", "alt": "Claude-Sonnet-4 model icon", "width": 200, "height": 200}, "url": "https://poe.com/claude-sonnet-4"}, "reasoning": {"budget": {"max_tokens": 61440, "min_tokens": 0}, "required": false, "supports_reasoning_effort": false}, "parameters": [{"name": "thinking_budget", "schema": {"type": "number", "minimum": 0, "maximum": 61440}, "default_value": 0, "description": "The maximum number of tokens to spend on thinking."}, {"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "claude-opus-4", "object": "model", "created": 1747863925397, "description": "Claude Opus 4 from Anthropic, supports customizable thinking budget (up to 30k tokens) and 200k context window.", "owned_by": "Anthropic", "root": "claude-opus-4", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/messages", "/v1/responses", "/v1/chat/completions"], "pricing": {"prompt": "0.0000128788", "completion": "0.0000643939", "image": null, "request": null, "input_cache_read": "0.0000012879", "input_cache_write": "0.0000160985"}, "context_window": {"context_length": 192512, "max_output_tokens": 28672}, "context_length": 192512, "metadata": {"display_name": "Claude-Opus-4", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-1033-200-bqqpqvkbaixytifzkimwnygkjptszmhh.jpeg", "alt": "Claude-Opus-4 model icon", "width": 200, "height": 200}, "url": "https://poe.com/claude-opus-4"}, "reasoning": {"budget": {"max_tokens": 26672, "min_tokens": 0}, "required": false, "supports_reasoning_effort": false}, "parameters": [{"name": "thinking_budget", "schema": {"type": "number", "minimum": 0, "maximum": 26672}, "default_value": 0, "description": "The maximum number of tokens to spend on thinking."}, {"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "o4-mini", "object": "model", "created": 1744826580331, "description": "o4-mini provides high intelligence on a variety of tasks and domains, including science, math, and coding at an affordable price point. \n\nThis bot supports 200k tokens of input context and 100k tokens of output context.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "OpenAI", "root": "o4-mini", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.000001", "completion": "0.000004", "image": null, "request": null, "input_cache_read": "0.00000025", "input_cache_write": null}, "context_window": {"context_length": 200000, "max_output_tokens": 100000}, "context_length": 200000, "metadata": {"display_name": "o4-mini", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3039-200-mvatmlmzjhrjxzhjgonqxrjuaieprsec.jpeg", "alt": "o4-mini model icon", "width": 200, "height": 200}, "url": "https://poe.com/o4-mini"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "gpt-4o", "object": "model", "created": 1715641234752, "description": "OpenAI's GPT-4o answers user prompts in a natural, engaging & tailored writing with strong overall world knowledge. Uses GPT-Image-1 to create and edit images conversationally. For fine-grained image generation control (e.g. image quality), use https://poe.com/GPT-Image-1. Supports context window of 128k tokens.", "owned_by": "OpenAI", "root": "gpt-4o", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": null, "context_window": {"context_length": 128000, "max_output_tokens": 8192}, "context_length": 128000, "metadata": {"display_name": "GPT-4o", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3015-200-orplgzxujhsekrpxvdagmkdsrhnvbhmv.jpeg", "alt": "GPT-4o model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-4o"}, "reasoning": null, "parameters": []}, {"id": "o3-pro", "object": "model", "created": 1749588430571, "description": "o3-pro is a well-rounded and powerful model across domains, with more capability than https://poe.com/o3 at the cost of higher price and lower speed. It is especially capable at math, science, coding, visual reasoning tasks, technical writing, and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images. \n\nOptional parameters:\nSet reasoning effort: Select from `low`, `medium`, `high`. Medium reasoning effort is set by default.", "owned_by": "OpenAI", "root": "o3-pro", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000181818", "completion": "0.0000727273", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 200000, "max_output_tokens": 100000}, "context_length": 200000, "metadata": {"display_name": "o3-pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3040-200-khprhxeahktuihupubqvghtxryzuevng.jpeg", "alt": "o3-pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/o3-pro"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "o4-mini-deep-research", "object": "model", "created": 1750982713340, "description": "Deep Research from OpenAI powered by the o4-mini model, can search through extensive web information to answer complex, nuanced research questions in various domains such as finance, consulting, and science.", "owned_by": "OpenAI", "root": "o4-mini-deep-research", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000018182", "completion": "0.0000072727", "image": null, "request": null, "input_cache_read": "0.0000004545", "input_cache_write": null}, "context_window": {"context_length": 200000, "max_output_tokens": 100000}, "context_length": 200000, "metadata": {"display_name": "o4-mini-deep-research", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3043-200-dfycqlshgvzrlctwmynzjuzifapbssqr.jpeg", "alt": "o4-mini-deep-research model icon", "width": 200, "height": 200}, "url": "https://poe.com/o4-mini-deep-research"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": false}, "parameters": []}, {"id": "grok-3", "object": "model", "created": 1744341886555, "description": "xAI's February 2025 flagship release representing nearly state-of-the-art performance in several reasoning/problem solving domains. The API doesn't yet support reasoning mode for Grok 3, but does for https://poe.com/Grok-3-Mini; this bot also doesn't have access to the X data feed. Supports 131k tokens of context, uses Grok 2 for native vision.", "owned_by": "XAI", "root": "grok-3", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000030303", "completion": "0.0000151515", "image": null, "request": null, "input_cache_read": "0.0000007576", "input_cache_write": null}, "context_window": {"context_length": 131072, "max_output_tokens": null}, "context_length": 131072, "metadata": {"display_name": "Grok-3", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5902949-200-llugsqihwhqcxkotnbqvjmouimubqbhw.jpeg", "alt": "Grok-3 model icon", "width": 200, "height": 200}, "url": "https://poe.com/grok-3"}, "reasoning": null, "parameters": []}, {"id": "grok-3-mini", "object": "model", "created": 1744388431404, "description": "xAI's February 2025 release with strong performance across many domains but at a more affordable price point. Supports reasoning with a configurable reasoning effort level, and 131k tokens of context; doesn't have access to the X data feed.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "XAI", "root": "grok-3-mini", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.000000303", "completion": "0.0000005051", "image": null, "request": null, "input_cache_read": "0.0000000758", "input_cache_write": null}, "context_window": {"context_length": 131072, "max_output_tokens": null}, "context_length": 131072, "metadata": {"display_name": "Grok-3-Mini", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5905373-200-cqlxjcvgpjkegqykecrqecshyodmbodq.jpeg", "alt": "Grok-3-Mini model icon", "width": 200, "height": 200}, "url": "https://poe.com/grok-3-mini"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "low"}]}, {"id": "o3", "object": "model", "created": 1744826529075, "description": "o3 provides state-of-the-art intelligence on a variety of tasks and domains, including science, math, and coding. This bot uses medium reasoning effort by default but low, medium & high are also selectable; supports 200k tokens of input context and 100k tokens of output context.\n\nOptional parameters:\nSet reasoning effort: Select from `low`, `medium`, `high`. Medium reasoning effort is set by default.", "owned_by": "OpenAI", "root": "o3", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000018182", "completion": "0.0000072727", "image": null, "request": null, "input_cache_read": "0.0000004545", "input_cache_write": null}, "context_window": {"context_length": 200000, "max_output_tokens": 100000}, "context_length": 200000, "metadata": {"display_name": "o3", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3035-200-ubhqbtreuahrhqpnnlmflhmhewugjuri.jpeg", "alt": "o3 model icon", "width": 200, "height": 200}, "url": "https://poe.com/o3"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "o3-deep-research", "object": "model", "created": 1750982619753, "description": "Deep Research from OpenAI powered by the o3 model, can search through extensive web information to answer complex, nuanced research questions in various domains such as finance, consulting, and science.", "owned_by": "OpenAI", "root": "o3-deep-research", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000090909", "completion": "0.0000363636", "image": null, "request": null, "input_cache_read": "0.0000022727", "input_cache_write": null}, "context_window": {"context_length": 200000, "max_output_tokens": 100000}, "context_length": 200000, "metadata": {"display_name": "o3-deep-research", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3042-200-ildlccliteslnjispehtkombrrfdnfyn.jpeg", "alt": "o3-deep-research model icon", "width": 200, "height": 200}, "url": "https://poe.com/o3-deep-research"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": false}, "parameters": []}, {"id": "deepseek-v3.1-t", "object": "model", "created": 1735963694067, "description": "DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. Compared to the previous version, this upgrade brings improvements in multiple aspects: Hybrid thinking mode: One model supports both thinking mode and non-thinking mode by changing the chat template. Smarter tool calling: Through post-training optimization, the model's performance in tool usage and agent tasks has significantly improved. Higher thinking efficiency: DeepSeek-V3.1-Think achieves comparable answer quality to DeepSeek-R1-0528, while responding more quickly.", "owned_by": "Together AI", "root": "deepseek-v3.1-t", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.013", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 160000, "max_output_tokens": null}, "context_length": 160000, "metadata": {"display_name": "DeepSeek-V3.1-T", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5503541-200-hpgnhrxndnnpmzsdokmrhbukpzmloyhu.jpeg", "alt": "DeepSeek-V3.1-T model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepseek-v3.1-t"}, "reasoning": null, "parameters": []}, {"id": "deepseek-v3.1", "object": "model", "created": 1735687236887, "description": "DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. We have expanded our dataset by collecting additional long documents and substantially extending both training phases. The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens. Additionally, DeepSeek-V3.1 is trained using the UE8M0 FP8 scale data format to ensure compatibility with microscaling data formats.", "owned_by": "Fireworks AI", "root": "deepseek-v3.1", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0091", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 160000, "max_output_tokens": null}, "context_length": 160000, "metadata": {"display_name": "DeepSeek-V3.1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5492287-200-lqkukggutjovzbeysnxlnuvnjpxrjaff.jpeg", "alt": "DeepSeek-V3.1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepseek-v3.1"}, "reasoning": null, "parameters": []}, {"id": "deepseek-v3.1-tm", "object": "model", "created": 1758553230099, "description": "DeepSeek-V3.1-Terminus preserves all original model capabilities while resolving key user-reported issues, including:\n- Language consistency: Significantly reducing mixed Chinese-English output and eliminating abnormal character occurrences\n- Agent performance: Enhanced optimization of both Code Agent and Search Agent functionality\n\nNotes:\nContext window: 128k tokens.\nThe bot does not accept attachment\n\nOptional parameters:\nEnable thinking about the response before giving a final answer: toggle it `off`, otherwise it is `on`  by default.", "owned_by": "Novita AI", "root": "deepseek-v3.1-tm", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0058", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "DeepSeek-V3.1-TM", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6441507-200-tdwfzdoyqgaqxwesqiarawfkcnbduydn.jpeg", "alt": "DeepSeek-V3.1-TM model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepseek-v3.1-tm"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "This will cause the model to think about the response before giving a final answer."}]}, {"id": "gpt-4.1", "object": "model", "created": 1744675047923, "description": "OpenAI\u2019s GPT-4.1 significantly improves on past models in terms of its coding skills, long context (1M tokens), and improved instruction following. Supports native vision, and generally has more intelligence than GPT-4o. Provides a 75% chat history cache discount.", "owned_by": "OpenAI", "root": "gpt-4.1", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000018182", "completion": "0.0000072727", "image": null, "request": null, "input_cache_read": "0.0000004545", "input_cache_write": null}, "context_window": {"context_length": 1047576, "max_output_tokens": 32768}, "context_length": 1047576, "metadata": {"display_name": "GPT-4.1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3036-200-rlewrfohktigvsdroihtuswkgkdkmzmd.jpeg", "alt": "GPT-4.1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-4.1"}, "reasoning": null, "parameters": []}, {"id": "gpt-4.1-mini", "object": "model", "created": 1744675260112, "description": "GPT-4.1 mini is a small, fast & affordable model that matches or beats GPT-4o in many intelligence and vision-related tasks. Supports 1M tokens of context.", "owned_by": "OpenAI", "root": "gpt-4.1-mini", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000003636", "completion": "0.0000014545", "image": null, "request": null, "input_cache_read": "0.0000000909", "input_cache_write": null}, "context_window": {"context_length": 1047576, "max_output_tokens": 32768}, "context_length": 1047576, "metadata": {"display_name": "GPT-4.1-mini", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3037-200-ugzqbmdibsoxojbdujllgcuaiurzwxfn.jpeg", "alt": "GPT-4.1-mini model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-4.1-mini"}, "reasoning": null, "parameters": []}, {"id": "gpt-4.1-nano", "object": "model", "created": 1744675276376, "description": "GPT-4.1 nano is an extremely fast and cheap model, ideal for text/vision summarization/categorization tasks. Supports native vision and 1M input tokens of context.", "owned_by": "OpenAI", "root": "gpt-4.1-nano", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000000909", "completion": "0.0000003636", "image": null, "request": null, "input_cache_read": "0.0000000227", "input_cache_write": null}, "context_window": {"context_length": 1047576, "max_output_tokens": 32768}, "context_length": 1047576, "metadata": {"display_name": "GPT-4.1-nano", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3038-200-lvpkowqgtxhvabqtsqsvyjfrllwyasxg.jpeg", "alt": "GPT-4.1-nano model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-4.1-nano"}, "reasoning": null, "parameters": []}, {"id": "claude-sonnet-3.7", "object": "model", "created": 1739926818142, "description": "Claude Sonnet 3.7 is a hybrid reasoning model, producing near-instant responses or extended, step-by-step thinking. \n\nSupports a 200k token context window.", "owned_by": "Anthropic", "root": "claude-sonnet-3.7", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/messages", "/v1/responses", "/v1/chat/completions"], "pricing": {"prompt": "0.0000025758", "completion": "0.0000128788", "image": null, "request": null, "input_cache_read": "0.0000002576", "input_cache_write": "0.0000032197"}, "context_window": {"context_length": 196608, "max_output_tokens": 128000}, "context_length": 196608, "metadata": {"display_name": "Claude-Sonnet-3.7", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-1025-200-gsfiobtsgpgsuxwalsjhntdnueguwdfq.jpeg", "alt": "Claude-Sonnet-3.7 model icon", "width": 200, "height": 200}, "url": "https://poe.com/claude-sonnet-3.7"}, "reasoning": {"budget": {"max_tokens": 61440, "min_tokens": 0}, "required": false, "supports_reasoning_effort": false}, "parameters": [{"name": "thinking_budget", "schema": {"type": "number", "minimum": 0, "maximum": 61440}, "default_value": 0, "description": "The maximum number of tokens to spend on thinking."}, {"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "claude-haiku-3.5", "object": "model", "created": 1727818578813, "description": "The latest generation of Anthropic's fastest model. Claude Haiku 3.5 has fast speeds and improved instruction following. ", "owned_by": "Anthropic", "root": "claude-haiku-3.5", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/messages", "/v1/responses", "/v1/chat/completions"], "pricing": {"prompt": "0.0000006869", "completion": "0.0000034343", "image": null, "request": null, "input_cache_read": "0.0000000687", "input_cache_write": "0.0000008586"}, "context_window": {"context_length": 189096, "max_output_tokens": 8192}, "context_length": 189096, "metadata": {"display_name": "Claude-Haiku-3.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-1021-200-nqsflsfgrznqhvvypcvhjhqwbeifxzqg.jpeg", "alt": "Claude-Haiku-3.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/claude-haiku-3.5"}, "reasoning": null, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "gemini-2.0-flash", "object": "model", "created": 1733958136993, "description": "Gemini 2.0 Flash is Google's most popular model yet with enhanced performance and blazingly fast response times; supports web search grounding so can intelligently answer questions related to recent events. Notably, 2.0 Flash even outperforms 1.5 Pro on key benchmarks, at twice the speed. Supports 1 million tokens of input context.", "owned_by": "Google", "root": "gemini-2.0-flash", "architecture": {"input_modalities": ["text", "image", "video", "audio"], "output_modalities": ["text"], "modality": "text,image,video,audio->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000001061", "completion": "0.0000004242", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 990000, "max_output_tokens": 8192}, "context_length": 990000, "metadata": {"display_name": "Gemini-2.0-Flash", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6015-200-smomjwuhsyujjfiojlpbnicawrpajwff.jpeg", "alt": "Gemini-2.0-Flash model icon", "width": 200, "height": 200}, "url": "https://poe.com/gemini-2.0-flash"}, "reasoning": null, "parameters": [{"name": "web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable web search and real-time information access."}]}, {"id": "gemini-2.0-flash-lite", "object": "model", "created": 1738780480313, "description": "Gemini 2.0 Flash Lite is a new model variant from Google that is our most cost-efficient model yet, and often considered a spiritual successor to Gemini 1.5 Flash in terms of capability, context window size and cost. Does not support web search (if you need search, we recommend using https://poe.com/Gemini-2.0-Flash), supports 1 million tokens of input context.", "owned_by": "Google", "root": "gemini-2.0-flash-lite", "architecture": {"input_modalities": ["text", "image", "video", "audio"], "output_modalities": ["text"], "modality": "text,image,video,audio->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.000000053", "completion": "0.0000002121", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 990000, "max_output_tokens": 8192}, "context_length": 990000, "metadata": {"display_name": "Gemini-2.0-Flash-Lite", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6016-200-baymucdmamvwgedldlqdqhxefjpnozed.jpeg", "alt": "Gemini-2.0-Flash-Lite model icon", "width": 200, "height": 200}, "url": "https://poe.com/gemini-2.0-flash-lite"}, "reasoning": null, "parameters": []}, {"id": "qwen3-max", "object": "model", "created": 1758038838064, "description": "Qwen3-Max is a major update to the Qwen3 series, delivering significant improvements in reasoning, instruction following, and multilingual support. It provides higher accuracy in complex tasks like coding and math, along with reduced hallucinations and better performance on open-ended questions.\nThis model is served by Alibaba Cloud Int. from Singapore.", "owned_by": "EmpirioLabs AI", "root": "qwen3-max", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3-Max", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6422979-200-dpdrztqmhacukpubulsefhgcjtwnppfm.jpeg", "alt": "Qwen3-Max model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3-max"}, "reasoning": null, "parameters": [{"name": "enable_web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Allow the model to search the web. Model decides when/if to search."}]}, {"id": "gpt-oss-120b", "object": "model", "created": 1754470272746, "description": "OpenAI introduces the GPT-OSS-120B, an open-weight reasoning model available under the Apache 2.0 license and OpenAI GPT-OSS usage policy. Developed with feedback from the open-source community, this text-only model is compatible with OpenAI Responses API and is designed to be used within agentic workflows with strong instruction following, tool use like web search and Python code execution, and reasoning capabilities.\n\nThe GPT-OSS-120B model achieves near-parity with OpenAI o4-mini on core reasoning benchmarks, while running efficiently on a single 80 GB GPU. This model also performs strongly on tool use, few-shot function calling, CoT reasoning (as seen in results on the Tau-Bench agentic evaluation suite) and HealthBench (even outperforming proprietary models like OpenAI o1 and GPT\u20114o). \n\nTechnical Specifications\n\nFile Support: Attachments not supported\nContext window: 128k tokens", "owned_by": "Novita AI", "root": "gpt-oss-120b", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0012", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "GPT-OSS-120B", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6298672-200-crppmcgxbwmfzsauuilljrxgbyimadge.jpeg", "alt": "GPT-OSS-120B model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-oss-120b"}, "reasoning": null, "parameters": []}, {"id": "gpt-oss-20b", "object": "model", "created": 1754470883542, "description": "OpenAI introduces the GPT-OSS-20B, an open-weight reasoning model available under the Apache 2.0 license and OpenAI GPT-OSS usage policy. Developed with feedback from the open-source community, this text-only model is compatible with OpenAI Responses API and is designed to be used within agentic workflows with strong instruction following, tool use like web search and Python code execution, and reasoning capabilities.\n\nThe GPT-OSS-20B model delivers similar results to OpenAI o3\u2011mini on common benchmarks and can run on edge devices with just 16 GB of memory, making it ideal for on-device use cases, local inference, or rapid iteration without costly infrastructure. This model also performs strongly on tool use, few-shot function calling, CoT reasoning (as seen in results on the Tau-Bench agentic evaluation suite) and HealthBench (even outperforming proprietary models like OpenAI o1 and GPT\u20114o). \n\nTechnical Specifications\n\nFile Support: Attachments not supported\nContext window: 128k tokens", "owned_by": "Novita AI", "root": "gpt-oss-20b", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.00045", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "GPT-OSS-20B", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6298697-200-sdbapzjmgsagpiqgnorgclxbieqtbxkf.jpeg", "alt": "GPT-OSS-20B model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-oss-20b"}, "reasoning": null, "parameters": []}, {"id": "gpt-oss-120b-cs", "object": "model", "created": 1754490145525, "description": "World\u2019s fastest inference for GPT OSS 120B with Cerebras. OpenAI's GPT-OSS-120B delivers sophisticated chain-of-thought reasoning capabilities in a fully open model. The bot does not accept video, ppt, docx and excel files.", "owned_by": "CerebrasAI", "root": "gpt-oss-120b-cs", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000003535", "completion": "0.0000007576", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "GPT-OSS-120B-CS", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6299377-200-ffqmlqigvwmqzddozfuvcrwcjrbmaeax.jpeg", "alt": "GPT-OSS-120B-CS model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-oss-120b-cs"}, "reasoning": null, "parameters": []}, {"id": "openai-gpt-oss-120b", "object": "model", "created": 1754416223840, "description": "GPT-OSS-120b is a high-performance, open-weight language model designed for production-grade, general-purpose use cases. It fits on a single H100 GPU, making it accessible without requiring multi-GPU infrastructure. Trained on the Harmony response format, it excels at complex reasoning and supports configurable reasoning effort, full chain-of-thought transparency for easier debugging and trust, and native agentic capabilities for function calling, tool use, and structured outputs.", "owned_by": "Fireworks AI", "root": "openai-gpt-oss-120b", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0015", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "OpenAI-GPT-OSS-120B", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6296706-200-hqprzeqbszunkonufrhjrftothfoahwd.jpeg", "alt": "OpenAI-GPT-OSS-120B model icon", "width": 200, "height": 200}, "url": "https://poe.com/openai-gpt-oss-120b"}, "reasoning": null, "parameters": []}, {"id": "openai-gpt-oss-20b", "object": "model", "created": 1754418551040, "description": "GPT-OSS-20B is a compact, open-weight language model optimized for low-latency and resource-constrained environments, including local and edge deployments. It shares the same Harmony training foundation and capabilities as 120B, with faster inference and easier deployment that is ideal for specialized or offline use cases, fast responsive performance, chain-of-thought output, and agentic workflows.", "owned_by": "Fireworks AI", "root": "openai-gpt-oss-20b", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.00076", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "OpenAI-GPT-OSS-20B", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6296775-200-iksohrpuhacrawqwtgxleroqgdelzopg.jpeg", "alt": "OpenAI-GPT-OSS-20B model icon", "width": 200, "height": 200}, "url": "https://poe.com/openai-gpt-oss-20b"}, "reasoning": null, "parameters": []}, {"id": "qwen-3-coder-next-t", "object": "model", "created": 1770340255128, "description": "Qwen3-Coder-Next-FP8 is an open-weight language model designed specifically for coding agents and local development. It features the following key enhancements:\n\nSuper Efficient with Significant Performance: With only 3B activated parameters (80B total parameters), it achieves performance comparable to models with 10\u201320x more active parameters, making it highly cost-effective for agent deployment.\nAdvanced Agentic Capabilities: Through an elaborate training recipe, it excels at long-horizon reasoning, complex tool usage, and recovery from execution failures, ensuring robust performance in dynamic coding tasks.\nVersatile Integration with Real-World IDE: Its 256k context length, combined with adaptability to various scaffold templates, enables seamless integration with different CLI/IDE platforms (e.g., Claude Code, Qwen Code, Qoder, Kilo, Trae, Cline, etc.), supporting diverse development environments.", "owned_by": "Together AI", "root": "qwen-3-coder-next-t", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0061", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen-3-Coder-Next-T", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6789205-200-gyanjfnrzhbndfbvtnuckdegndpswzqd.jpeg", "alt": "Qwen-3-Coder-Next-T model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen-3-coder-next-t"}, "reasoning": null, "parameters": []}, {"id": "qwen3-max-n", "object": "model", "created": 1762329665354, "description": "Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It delivers higher accuracy in math, coding, logic, and science tasks, follows complex instructions in Chinese and English more reliably, reduces hallucinations, and produces higher-quality responses for open-ended Q&A, writing, and conversation. The model supports over 100 languages with stronger translation and commonsense reasoning, and is optimized for retrieval-augmented generation (RAG) and tool calling, though it does not include a dedicated \u201cthinking\u201d mode.\n\nFile Support: Text, Markdown and PDF files\nContext window: 256k tokens", "owned_by": "Novita AI", "root": "qwen3-max-n", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.023", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3-Max-N", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6557773-200-qgjeaazcaodzcztgsqeejzzsbmrypzfa.jpeg", "alt": "Qwen3-Max-N model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3-max-n"}, "reasoning": null, "parameters": []}, {"id": "qwen3-vl-235b-a22b-t", "object": "model", "created": 1758695878297, "description": "Qwen3-VL is the most advanced vision-language model in the Qwen series, offering enhanced text understanding, visual reasoning, spatial perception, and agent capabilities. It supports Dense/MoE architectures and Instruct/Thinking editions for versatile deployment.\n\nKey Features:\n- Visual Agent: Operates GUIs, recognizes elements, invokes tools, and completes tasks.\n- Coding Boost: Generates Draw.io, HTML, CSS, and JS from images/videos.\n- Spatial Perception: Enables 2D/3D reasoning with strong object positioning and occlusion analysis.\n- Long Context: Processes up to 1M tokens for books or long videos.\n- Multimodal Reasoning: Excels in STEM, math, causal analysis, and evidence-based answers.\n- Visual Recognition: Recognizes a wide range of objects, landmarks, and more.\n- OCR: Supports 32 languages with improved performance in challenging conditions.\n- Text-Vision Fusion: Achieves seamless, unified comprehension.\n\nIdeal for multimodal reasoning, spatial analysis, and integrated text-vision tasks.\n\nTechnical Specifications\n\nFile Support: Image, Video, PDF and Markdown files\nContext window: 128k tokens", "owned_by": "Novita AI", "root": "qwen3-vl-235b-a22b-t", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0048", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3-VL-235B-A22B-T", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6446093-200-qepmianxgcktttzrozmgqwqibqaxoisi.jpeg", "alt": "Qwen3-VL-235B-A22B-T model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3-vl-235b-a22b-t"}, "reasoning": null, "parameters": []}, {"id": "qwen3-vl-235b-a22b-i", "object": "model", "created": 1758695977113, "description": "This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.\n\nAvailable in Dense and MoE architectures that scale from edge to cloud, with Instruct and reasoning\u2011enhanced Thinking editions for flexible, on\u2011demand deployment.\n\nKey Enhancements:\nVisual Agent: Operates PC/mobile GUIs\u2014recognizes elements, understands functions, invokes tools, completes tasks.\n\nVisual Coding Boost: Generates Draw.io/HTML/CSS/JS from images/videos.\n\nAdvanced Spatial Perception: Judges object positions, viewpoints, and occlusions; provides stronger 2D grounding and enables 3D grounding for spatial reasoning and embodied AI.\n\nLong Context & Video Understanding: Native 256K context, expandable to 1M; handles books and hours-long video with full recall and second-level indexing.\n\nEnhanced Multimodal Reasoning: Excels in STEM/Math\u2014causal analysis and logical, evidence-based answers.\n\nUpgraded Visual Recognition: Broader, higher-quality pretraining is able to \"recognize everything\"\u2014celebrities, anime, products, landmarks, flora/fauna, etc.\n\nExpanded OCR: Supports 32 languages (up from 19); robust in low light, blur, and tilt; better with rare/ancient characters and jargon; improved long-document structure parsing.\n\nText Understanding on par with pure LLMs: Seamless text\u2013vision fusion for lossless, unified comprehension.\n\nTechnical Specifications\n\nFile Support: Image, Video, PDF and Markdown files\nContext window: 128k tokens", "owned_by": "Novita AI", "root": "qwen3-vl-235b-a22b-i", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0036", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3-VL-235B-A22B-I", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6446097-200-suqbguevrwbaiplsgcxzikskvmfrvrsm.jpeg", "alt": "Qwen3-VL-235B-A22B-I model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3-vl-235b-a22b-i"}, "reasoning": null, "parameters": []}, {"id": "qwen-3-235b-2507-t", "object": "model", "created": 1745978851479, "description": "Qwen3 235B A22B 2507, currently the best instruct model (non-reasoning) among both closed and open source models. It excels in instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage. It is also great at multilingual tasks and supports a long context window (262k).", "owned_by": "Together AI", "root": "qwen-3-235b-2507-t", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0019", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 40960, "max_output_tokens": null}, "context_length": 40960, "metadata": {"display_name": "Qwen-3-235B-2507-T", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5971116-200-cbawxztjotzcaortaqilmdcudsmyooal.jpeg", "alt": "Qwen-3-235B-2507-T model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen-3-235b-2507-t"}, "reasoning": null, "parameters": []}, {"id": "qwen3-coder-480b-t", "object": "model", "created": 1753465729255, "description": "Qwen3\u2011Coder\u2011480B is a state of the art mixture\u2011of\u2011experts (MoE) code\u2011specialized language model with 480\u202fbillion total parameters and 35\u202fbillion activated parameters. Qwen3\u2011Coder delivers exceptional performance across code generation, function calling, tool use, and long\u2011context reasoning. It natively supports up to 262,144\u2011token context windows, making it ideal for large repository and multi\u2011file coding tasks.", "owned_by": "Together AI", "root": "qwen3-coder-480b-t", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.017", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3-Coder-480B-T", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6257951-200-wakoffcrovfqenyarstziqehaktvwyue.jpeg", "alt": "Qwen3-Coder-480B-T model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3-coder-480b-t"}, "reasoning": null, "parameters": []}, {"id": "qwen3-coder-480b-n", "object": "model", "created": 1755222889121, "description": "Qwen3-Coder-480B-A35B-Instruct delivers Claude Sonnet-comparable performance on agentic coding and browser tasks while supporting 256K-1M token long-context processing and multi-platform agentic coding capabilities. \n\nTechnical Specifications\n\nFile Support: Attachments not supported\nContext window: 256k tokens", "owned_by": "Novita AI", "root": "qwen3-coder-480b-n", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0073", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3-Coder-480B-N", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6328432-200-qcywlhewoplcouamjycaobqvttwzamyl.jpeg", "alt": "Qwen3-Coder-480B-N model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3-coder-480b-n"}, "reasoning": null, "parameters": []}, {"id": "qwen3-235b-a22b-di", "object": "model", "created": 1746004656402, "description": "Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support.\n\nSupports 32k tokens of input context and 8k tokens of output context. Quantization: FP8.", "owned_by": "DeepInfra", "root": "qwen3-235b-a22b-di", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0019", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 32000, "max_output_tokens": null}, "context_length": 32000, "metadata": {"display_name": "Qwen3-235B-A22B-DI", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5972218-200-opylaawgkyzvdvtpntebszciqksfhvmg.jpeg", "alt": "Qwen3-235B-A22B-DI model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3-235b-a22b-di"}, "reasoning": null, "parameters": []}, {"id": "qwen3-235b-a22b-n", "object": "model", "created": 1754050170519, "description": "It is optimized for general-purpose text generation, including instruction following, logical reasoning, math, code, and tool usage. The model supports a native 262K context length and does not implement \"thinking mode\" (<think> blocks). The Bot does not currently support attachments.\nThis feature the following key enhancements:\n- Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage.\n- Substantial gains in long-tail knowledge coverage across multiple languages.\n- Markedly better alignment with user preferences in subjective and open-ended tasks, enabling more helpful responses and higher-quality text generation.\n- Enhanced capabilities in 256K long-context understanding.\n\nTechnical Specifications\n\nFile Support: Attachments not supported\nContext window: 128k tokens", "owned_by": "Novita AI", "root": "qwen3-235b-a22b-n", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0018", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3-235B-A22B-N", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6284556-200-yxrdtewfectwxtdufxerldiiihymwvpj.jpeg", "alt": "Qwen3-235B-A22B-N model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3-235b-a22b-n"}, "reasoning": null, "parameters": []}, {"id": "magistral-medium-2509-thinking", "object": "model", "created": 1750288555644, "description": "Magistral Medium 2509 (thinking) by EmpirioLabs.\nMagistral is Mistral's first reasoning model. It is ideal for general purpose use requiring longer thought processing and better accuracy than with non-reasoning LLMs. From legal research and financial forecasting to software development and creative storytelling \u2014 this model solves multi-step challenges where transparency and precision are critical. Context Window: 40,000k\nSupported file type uploads: PDF, XLSX, TXT, PNG, JPG, JPEG", "owned_by": "EmpirioLabs AI", "root": "magistral-medium-2509-thinking", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000026263", "completion": "0.0000065657", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Magistral-Medium-2509-Thinking", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6140563-200-vjgowpstnsgwapnoktgwnfwentlahfys.jpeg", "alt": "Magistral-Medium-2509-Thinking model icon", "width": 200, "height": 200}, "url": "https://poe.com/magistral-medium-2509-thinking"}, "reasoning": null, "parameters": []}, {"id": "o1", "object": "model", "created": 1734482114732, "description": "OpenAI's o1 is designed to reason before it responds and provides world-class capabilities on complex tasks (e.g. science, coding, and math). Improving upon o1-preview and with higher reasoning effort, it is also capable of reasoning through images and supports 200k tokens of input context. By default, uses reasoning effort of medium, but low, medium & high are also selectable.", "owned_by": "OpenAI", "root": "o1", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000136364", "completion": "0.0000545455", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 200000, "max_output_tokens": 100000}, "context_length": 200000, "metadata": {"display_name": "o1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3028-200-qywuixrbfqpjaemrljbwhfsyitacfuyu.jpeg", "alt": "o1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/o1"}, "reasoning": {"budget": null, "required": true, "supports_reasoning_effort": true}, "parameters": [{"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "o1-pro", "object": "model", "created": 1742413231833, "description": "OpenAI\u2019s o1-pro highly capable reasoning model, tailored for complex, compute- or context-heavy tasks, dedicating additional thinking time to deliver more accurate, reliable answers. For less costly, complex tasks, https://poe.com/o3-mini is recommended.\n\nOptional parameters:\nSet reasoning effort: Select from low, medium, high. Medium reasoning effort is set by default.", "owned_by": "OpenAI", "root": "o1-pro", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["web_search", "tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0001363636", "completion": "0.0005454545", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 200000, "max_output_tokens": 100000}, "context_length": 200000, "metadata": {"display_name": "o1-pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3034-200-fskzuhwuhdogaegmljtxmyivdiweckps.jpeg", "alt": "o1-pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/o1-pro"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "cartesia-ink-whisper", "object": "model", "created": 1757628728993, "description": "Transcribe audio files using Speech-to-Text with the Cartesia Ink Whisper model.\n\nSelect the Language of your audio file. Default is English (en).\n\nSupported Languages:\nEnglish (en)\nChinese (zh)\nGerman (de)\nSpanish (es)\nRussian (ru)\nKorean (ko)\nFrench (fr)\nJapanese (ja)\nPortuguese (pt)\nTurkish (tr)\nPolish (pl)\nCatalan (ca)\nDutch (nl)\nArabic (ar)\nSwedish (sv)\nItalian (it)\nIndonesian (id)\nHindi (hi)\nFinnish (fi)\nVietnamese (vi)\nHebrew (he)\nUkrainian (uk)\nGreek (el)\nMalay (ms)\nCzech (cs)\nRomanian (ro)\nDanish (da)\nHungarian (hu)\nTamil (ta)\nNorwegian (no)\nThai (th)\nUrdu (ur)\nCroatian (hr)\nBulgarian (bg)\nLithuanian (lt)\nLatin (la)\nMaori (mi)\nMalayalam (ml)\nWelsh (cy)\nSlovak (sk)\nTelugu (te)\nPersian (fa)\nLatvian (lv)\nBengali (bn)\nSerbian (sr)\nAzerbaijani (az)\nSlovenian (sl)\nKannada (kn)\nEstonian (et)\nMacedonian (mk)\nBreton (br)\nBasque (eu)\nIcelandic (is)\nArmenian (hy)\nNepali (ne)\nMongolian (mn)\nBosnian (bs)\nKazakh (kk)\nAlbanian (sq)\nSwahili (sw)\nGalician (gl)\nMarathi (mr)\nPunjabi (pa)\nSinhala (si)\nKhmer (km)\nShona (sn)\nYoruba (yo)\nSomali (so)\nAfrikaans (af)\nOccitan (oc)\nGeorgian (ka)\nBelarusian (be)\nTajik (tg)\nSindhi (sd)\nGujarati (gu)\nAmharic (am)\nYiddish (yi)\nLao (lo)\nUzbek (uz)\nFaroese (fo)\nHaitian Creole (ht)\nPashto (ps)\nTurkmen (tk)\nNynorsk (nn)\nMaltese (mt)\nSanskrit (sa)\nLuxembourgish (lb)\nMyanmar (my)\nTibetan (bo)\nTagalog (tl)\nMalagasy (mg)\nAssamese (as)\nTatar (tt)\nHawaiian (haw)\nLingala (ln)\nHausa (ha)\nBashkir (ba)\nJavanese (jw)\nSundanese (su)\nCantonese (yue)\n", "owned_by": "Cartesia AI", "root": "cartesia-ink-whisper", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Cartesia-Ink-Whisper", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6410080-200-vssrgpvbdzkrslybdiuvfyrqhhqefyun.jpeg", "alt": "Cartesia-Ink-Whisper model icon", "width": 200, "height": 200}, "url": "https://poe.com/cartesia-ink-whisper"}, "reasoning": null, "parameters": [{"name": "language", "schema": {"enum": ["en", "zh", "de", "es", "ru", "ko", "fr", "ja", "pt", "tr", "pl", "ca", "nl", "ar", "sv", "it", "id", "hi", "fi", "vi", "he", "uk", "el", "ms", "cs", "ro", "da", "hu", "ta", "no", "th", "ur", "hr", "bg", "lt", "la", "mi", "ml", "cy", "sk", "te", "fa", "lv", "bn", "sr", "az", "sl", "kn", "et", "mk", "br", "eu", "is", "hy", "ne", "mn", "bs", "kk", "sq", "sw", "gl", "mr", "pa", "si", "km", "sn", "yo", "so", "af", "oc", "ka", "be", "tg", "sd", "gu", "am", "yi", "lo", "uz", "fo", "ht", "ps", "tk", "nn", "mt", "sa", "lb", "my", "bo", "tl", "mg", "as", "tt", "haw", "ln", "ha", "ba", "jw", "su", "yue"]}, "default_value": "en"}]}, {"id": "gpt-4o-mini", "object": "model", "created": 1721338046069, "description": "This intelligent small model from OpenAI is significantly smarter, cheaper, and just as fast as GPT-3.5 Turbo.", "owned_by": "OpenAI", "root": "gpt-4o-mini", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000001364", "completion": "0.0000005455", "image": null, "request": null, "input_cache_read": "0.0000000682", "input_cache_write": null}, "context_window": {"context_length": 124096, "max_output_tokens": 4096}, "context_length": 124096, "metadata": {"display_name": "GPT-4o-mini", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3017-200-qeuixcziorfxpvkkkhzrmnljeukoxcpx.jpeg", "alt": "GPT-4o-mini model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-4o-mini"}, "reasoning": null, "parameters": []}, {"id": "qwen3-max-preview", "object": "model", "created": 1763943732422, "description": "Qwen3-Max-Preview shows substantial gains over the 2.5 series in overall capability, with significant enhancements in Chinese-English text understanding, complex instruction following, handling of subjective open-ended tasks, multilingual ability, and tool invocation; model knowledge hallucinations are reduced.\n\nParameter controls available:\n1. Thinking Mode\n   - Enable thinking about the response before giving a final answer: toggle it `on`, otherwise it is `off` by default.\n  \n2. Code Interpreter\n   - Toggle it `on` to enable code interpreter. It is `off` by default.\n   - Lets the model write and execute Python code for calculations, data analysis, and visualizations", "owned_by": "EmpirioLabs AI", "root": "qwen3-max-preview", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": "0.0000010909", "completion": "0.0000048485", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3-Max-Preview", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6610885-200-tazaxvqidlsqmpmehibzlsxqvhjmldsi.jpeg", "alt": "Qwen3-Max-Preview model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3-max-preview"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Model thinks step-by-step before responding (recommended for complex tasks)."}, {"name": "enable_code_interpreter", "schema": {"type": "boolean"}, "default_value": false, "description": "Allow the model to write and execute Python code."}]}, {"id": "o3-mini", "object": "model", "created": 1738356284517, "description": "o3-mini is OpenAI's reasoning model, providing high intelligence on a variety of tasks and domains, including science, math, and coding. This bot uses medium reasoning effort by default but low, medium & high can be selected; supports 200k tokens of input context and 100k tokens of output context.\n\nOptional parameters:\nSet reasoning effort: Select from `low`, `medium`, `high`. Medium reasoning effort is set by default.", "owned_by": "OpenAI", "root": "o3-mini", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.000001", "completion": "0.000004", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 200000, "max_output_tokens": 100000}, "context_length": 200000, "metadata": {"display_name": "o3-mini", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3029-200-nuviihlnpoospinftbtoydhhwqdbneoi.jpeg", "alt": "o3-mini model icon", "width": 200, "height": 200}, "url": "https://poe.com/o3-mini"}, "reasoning": {"budget": null, "required": false, "supports_reasoning_effort": true}, "parameters": [{"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium"}]}, {"id": "o3-mini-high", "object": "model", "created": 1738356365479, "description": "o3-mini-high is OpenAI's most recent reasoning model with reasoning_effort set to high, providing frontier intelligence on most tasks. Like other models in the o-series, it is designed to excel at science, math, and coding tasks. Supports 200k tokens of input context and 100k tokens of output context.", "owned_by": "OpenAI", "root": "o3-mini-high", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.000001", "completion": "0.000004", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 200000, "max_output_tokens": 100000}, "context_length": 200000, "metadata": {"display_name": "o3-mini-high", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3030-200-akjqmkenwvalmhjyxbdvdfquyiijvqud.jpeg", "alt": "o3-mini-high model icon", "width": 200, "height": 200}, "url": "https://poe.com/o3-mini-high"}, "reasoning": {"budget": null, "required": true, "supports_reasoning_effort": false}, "parameters": []}, {"id": "llama-3.1-8b-di", "object": "model", "created": 1740488781419, "description": "The smallest and fastest model from Meta's Llama 3.1 family. This open-source language model excels in multilingual dialogue, outperforming numerous industry benchmarks for both closed and open-source conversational AI systems.  All data you submit to this bot is governed by the Poe privacy policy and is only sent to DeepInfra, a US-based company.\n\nInput token limit 128k, output token limit 8k. Quantization: FP16 (official).", "owned_by": "DeepInfra", "root": "llama-3.1-8b-di", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.00030", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "Llama-3.1-8B-DI", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5709972-200-wleptqcrnhpussgxjcaypcwlpvsoqype.jpeg", "alt": "Llama-3.1-8B-DI model icon", "width": 200, "height": 200}, "url": "https://poe.com/llama-3.1-8b-di"}, "reasoning": null, "parameters": []}, {"id": "mistral-medium-3", "object": "model", "created": 1750801647375, "description": "Mistral Medium 3 is a powerful, cost-efficient language model offering top-tier reasoning and multimodal performance. Context Window: 130k", "owned_by": "EmpirioLabs AI", "root": "mistral-medium-3", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Mistral-Medium-3", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6158501-200-hsbmitghmqhmguuukhwfqbqxyxuloxas.jpeg", "alt": "Mistral-Medium-3 model icon", "width": 200, "height": 200}, "url": "https://poe.com/mistral-medium-3"}, "reasoning": null, "parameters": []}, {"id": "mistral-medium", "object": "model", "created": 1703096777397, "description": "Mistral AI's medium-sized model. Supports a context window of 32k tokens (around 24,000 words) and is stronger than Mixtral-8x7b and Mistral-7b on benchmarks across the board.", "owned_by": "Mistral", "root": "mistral-medium", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": ["/v1/chat/completions"], "pricing": {"prompt": "0.0000027273", "completion": "0.0000081818", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": 4096}, "context_length": 128000, "metadata": {"display_name": "Mistral-Medium", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-7009-200-wxkbzvleprmbkslrrqmnswcikmnhgvvw.jpeg", "alt": "Mistral-Medium model icon", "width": 200, "height": 200}, "url": "https://poe.com/mistral-medium"}, "reasoning": null, "parameters": []}, {"id": "llama-3.3-70b-fw", "object": "model", "created": 1733508651951, "description": "Meta's Llama 3.3 70B Instruct, hosted by Fireworks AI. Llama 3.3 70B is a new open source model that delivers leading performance and quality across text-based use cases such as synthetic data generation at a fraction of the inference cost, improving over Llama 3.1 70B.", "owned_by": "Fireworks AI", "root": "llama-3.3-70b-fw", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0042", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "Llama-3.3-70B-FW", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5379817-200-irrblruyfudfcmtomljzvfdiauybqncm.jpeg", "alt": "Llama-3.3-70B-FW model icon", "width": 200, "height": 200}, "url": "https://poe.com/llama-3.3-70b-fw"}, "reasoning": null, "parameters": []}, {"id": "llama-3.3-70b", "object": "model", "created": 1733509126023, "description": "Llama 3.3 70B \u2013 with similar performance as Llama 3.1 405B while being faster and much smaller! Llama 3.3 70B is a new open source model that delivers leading performance and quality across text-based use cases such as synthetic data generation at a fraction of the inference cost, improving over Llama 3.1 70B.", "owned_by": "Together AI", "root": "llama-3.3-70b", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0039", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 131072, "max_output_tokens": null}, "context_length": 131072, "metadata": {"display_name": "Llama-3.3-70B", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5379836-200-dukgytytdbcbadvciccwxroveytrecrd.jpeg", "alt": "Llama-3.3-70B model icon", "width": 200, "height": 200}, "url": "https://poe.com/llama-3.3-70b"}, "reasoning": null, "parameters": []}, {"id": "deepseek-prover-v2", "object": "model", "created": 1747979752008, "description": "DeepSeek-Prover-V2 is an open-source large language model specifically designed for formal theorem proving in Lean 4. The model builds on a recursive theorem proving pipeline powered by the company's DeepSeek-V3 foundation model.", "owned_by": "EmpirioLabs AI", "root": "deepseek-prover-v2", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "DeepSeek-Prover-V2", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6048662-200-eivjrrvoetaxhntxfwcoevquazzbalie.jpeg", "alt": "DeepSeek-Prover-V2 model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepseek-prover-v2"}, "reasoning": null, "parameters": []}, {"id": "deepseek-v3.2-fw", "object": "model", "created": 1737499802568, "description": "Model from DeepSeek that harmonizes high computational efficiency with superior reasoning and agent performance.\n\nFile Support: Image (JPG, JPEG, PNG, HEIC), Other File Types (PDF, PYTHON, XLSX)", "owned_by": "Fireworks AI", "root": "deepseek-v3.2-fw", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.018", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 160000, "max_output_tokens": null}, "context_length": 160000, "metadata": {"display_name": "DeepSeek-V3.2-FW", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5572780-200-bhemyabdqrnfamjozebtwmiqecuxmhfl.jpeg", "alt": "DeepSeek-V3.2-FW model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepseek-v3.2-fw"}, "reasoning": null, "parameters": []}, {"id": "deepseek-r1-di", "object": "model", "created": 1740487208576, "description": "Top open-source reasoning LLM rivaling OpenAI's o1 model; delivers top-tier performance across math, code, and reasoning tasks at a fraction of the cost. All data you provide this bot will not be used in training, and is sent only to DeepInfra, a US-based company. Bot does not accept attachment.\n\nSupports 64k tokens of input context and 8k tokens of output context. Quantization: FP8 (official).", "owned_by": "DeepInfra", "root": "deepseek-r1-di", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0061", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 64000, "max_output_tokens": null}, "context_length": 64000, "metadata": {"display_name": "DeepSeek-R1-DI", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5709851-200-ncgvevamqnhuykdyksagzdekopkxkaan.jpeg", "alt": "DeepSeek-R1-DI model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepseek-r1-di"}, "reasoning": null, "parameters": []}, {"id": "deepseek-r1-n", "object": "model", "created": 1754049641148, "description": "The DeepSeek-R1 (latest Snapshot model DeepSeek-R1-0528) model features enhanced reasoning and inference capabilities through optimized algorithms and increased computational resources. It excels in mathematics, programming, and logic, with performance nearing top-tier models like o3 and Gemini 2.5 Pro. This bot does not accept attachments. \n\nTechnical Specifications\n\nFile Support: Attachments not supported\nContext window: 160k tokens", "owned_by": "Novita AI", "root": "deepseek-r1-n", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0061", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "DeepSeek-R1-N", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6284530-200-tpxynvduxppvtmkhvexfevakxrswbmma.jpeg", "alt": "DeepSeek-R1-N model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepseek-r1-n"}, "reasoning": null, "parameters": []}, {"id": "llama-3.3-70b-n", "object": "model", "created": 1754050595700, "description": "The Meta Llama 3.3 multilingual large language model (LLM) is an instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks. \n\nTechnical Specifications\n\nFile Support: Attachments not supported\nContext window: 128k tokens", "owned_by": "Novita AI", "root": "llama-3.3-70b-n", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0014", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Llama-3.3-70B-N", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6284572-200-znnhtgbdaltjqhhwypkunlmzpcqgoafi.jpeg", "alt": "Llama-3.3-70B-N model icon", "width": 200, "height": 200}, "url": "https://poe.com/llama-3.3-70b-n"}, "reasoning": null, "parameters": []}, {"id": "llama-3.1-8b-cs", "object": "model", "created": 1747179273060, "description": "World\u2019s fastest inference for Llama 3.1 8B with Cerebras. This Llama 8B instruct-tuned version is fast and efficient. The Llama 3.1 8B is an instruction tuned text only model, optimized for multilingual dialogue use cases. It has demonstrated strong performance compared to leading closed-source models in human evaluations.", "owned_by": "CerebrasAI", "root": "llama-3.1-8b-cs", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.000000101", "completion": "0.000000101", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "Llama-3.1-8B-CS", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6016634-200-emjkhajuhloiqepnypioyzkpdhsvnicz.jpeg", "alt": "Llama-3.1-8B-CS model icon", "width": 200, "height": 200}, "url": "https://poe.com/llama-3.1-8b-cs"}, "reasoning": null, "parameters": []}, {"id": "gpt-researcher", "object": "model", "created": 1735901906014, "description": "GPT Researcher is an agent that conducts deep research on any topic and generates a comprehensive report with citations. GPT Researcher is powered by Tavily's search engine.\n\nGPTR is based on the popular open source project: https://github.com/assafelovic/gpt-researcher -- by integrating Tavily search, it is optimized for curation and ranking of trusted research sources. Learn more at https://gptr.dev or https://tavily.com", "owned_by": "GPT Researcher", "root": "gpt-researcher", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "GPT-Researcher", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5501226-200-wjbtjvlxkclsqobnmeolhcesjktjuzdg.jpeg", "alt": "GPT-Researcher model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-researcher"}, "reasoning": null, "parameters": []}, {"id": "web-search", "object": "model", "created": 1694131444821, "description": "Web-enabled assistant bot that searches the internet to inform its responses. Particularly good for queries regarding up-to-date information or specific facts. Powered by Gemini 2.5 Flash-Lite.\nThis bot does not support attachments. ", "owned_by": "Poe", "root": "web-search", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Web-Search", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-2254704-200-qzclbtuxtlnlkgqjjcfqfziyxncqehra.jpeg", "alt": "Web-Search model icon", "width": 200, "height": 200}, "url": "https://poe.com/web-search"}, "reasoning": null, "parameters": []}, {"id": "gpt-4o-search", "object": "model", "created": 1741720622451, "description": "OpenAI's fine-tuned model for searching the web for real-time information. For less expensive messages, consider https://poe.com/GPT-4o-mini-Search. Uses medium search context size, currently in preview, supports 128k tokens of context. Does not support image search.", "owned_by": "OpenAI", "root": "gpt-4o-search", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000022727", "completion": "0.0000090909", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": 8192}, "context_length": 128000, "metadata": {"display_name": "GPT-4o-Search", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3032-200-ecgvxxmyufqqghfmsmqgshptxyhfwqap.jpeg", "alt": "GPT-4o-Search model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-4o-search"}, "reasoning": null, "parameters": []}, {"id": "gpt-4o-mini-search", "object": "model", "created": 1741724009166, "description": "OpenAI's fine-tuned model for searching the web for real-time information. For higher-performance, consider https://poe.com/GPT-4o-Search. Uses medium search context size, currently in preview, supports 128k tokens of context. Does not support image search.", "owned_by": "OpenAI", "root": "gpt-4o-mini-search", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000001364", "completion": "0.0000005455", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": 8192}, "context_length": 128000, "metadata": {"display_name": "GPT-4o-mini-Search", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3033-200-srkxpgounxxwqqlpisfqoznobupohbjs.jpeg", "alt": "GPT-4o-mini-Search model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-4o-mini-search"}, "reasoning": null, "parameters": []}, {"id": "reka-research", "object": "model", "created": 1750919363394, "description": "Reka Research is a state-of-the-art agentic AI that answers complex questions by browsing the web. It excels at synthesizing information from multiple sources, performing work that usually takes hours in minutes", "owned_by": "Reka AI", "root": "reka-research", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Reka-Research", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6163035-200-yzioepxfsnyoouhzlpaubuvbarbvclob.jpeg", "alt": "Reka-Research model icon", "width": 200, "height": 200}, "url": "https://poe.com/reka-research"}, "reasoning": null, "parameters": []}, {"id": "perplexity-sonar", "object": "model", "created": 1737790362317, "description": "Sonar by Perplexity is a cutting-edge AI model that delivers real-time, web-connected search results with accurate citations. It's designed to provide up-to-date information and customizable search sources, making it a powerful tool for integrating AI search into various applications. Context Length: 127k \n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "perplexity-sonar", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": {"context_length": 127000, "max_output_tokens": null}, "context_length": 127000, "metadata": {"display_name": "Perplexity-Sonar", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5585796-200-yvdacuxsdyietfdvzkczcwfwpdogeivt.jpeg", "alt": "Perplexity-Sonar model icon", "width": 200, "height": 200}, "url": "https://poe.com/perplexity-sonar"}, "reasoning": null, "parameters": [{"name": "search_context_size", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium", "description": "Higher context gives better answers but increases the base fee."}, {"name": "search_mode", "schema": {"enum": ["default", "academic", "sec"]}, "default_value": "default", "description": "Filter search results by source type."}, {"name": "search_domain_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated domains. Exclude with '-'. Max 20."}, {"name": "search_language_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated ISO 639-1 language codes (2 letters). Max 10."}, {"name": "search_after_date", "schema": {"type": "string"}, "default_value": "", "description": "Use exact publication date (mutually exclusive with Recency)."}, {"name": "search_before_date", "schema": {"type": "string"}, "default_value": "", "description": "Use exact publication date (mutually exclusive with Recency)."}, {"name": "search_recency_filter", "schema": {"enum": ["none", "day", "week", "month", "year"]}, "default_value": "none", "description": "Relative to today. Cannot be combined with specific dates."}, {"name": "last_updated_after_filter", "schema": {"type": "string"}, "default_value": ""}, {"name": "last_updated_before_filter", "schema": {"type": "string"}, "default_value": ""}, {"name": "country", "schema": {"type": "string"}, "default_value": "", "description": "Two-letter ISO 3166-1 country code."}, {"name": "region", "schema": {"type": "string"}, "default_value": "", "description": "State/Province name (e.g., California, \u00cele-de-France)."}, {"name": "city", "schema": {"type": "string"}, "default_value": "", "description": "City name (e.g., San Francisco, Paris)."}, {"name": "latitude", "schema": {"type": "string"}, "default_value": "", "description": "Must be provided with Longitude and Country."}, {"name": "longitude", "schema": {"type": "string"}, "default_value": "", "description": "Must be provided with Latitude and Country."}, {"name": "return_images", "schema": {"type": "boolean"}, "default_value": false, "description": "Include images in search results."}, {"name": "image_domain_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated domains for images. Exclude with '-'. Max 10."}, {"name": "image_format_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated formats: gif, jpg, png, webp"}, {"name": "return_videos", "schema": {"type": "boolean"}, "default_value": false, "description": "Include videos in search results."}]}, {"id": "linkup-deep-search", "object": "model", "created": 1755390159000, "description": "Linkup Deep Search is an AI-powered search bot that continues to search iteratively if it hasn't found sufficient information on the first attempt. Results are slower compared to its Standard search counterpart, but often yield to more comprehensive results.\nLinkup's technology ranks #1 globally for factual accuracy, achieving state-of-the-art scores on OpenAI\u2019s SimpleQA benchmark. \n\nNotes:\nContext Window: 100k\nAudio/video files are not supported at this time. \n\nParameter controls available: \n1. Domain control. To search only within specific domains select `Include only these domains`, To exclude domains from the search result select `Exclude these domains`. \n2. Prioritize Domains. To give higher priority on search\n3. Date Range: Set `from date` and `to date` to select date range search. Use YYYY-MM-DD date format\n4. Content Option: Toggle `include image` to include relevant images on search and set `image count` (up to 45) to display specific number of images to display.\n5. Citation options: Toggle enable inline citation to include inline citations in the response text (Default: `on`). Toggle include sources list to include a list of sources in the response (Default: `on`)\n\nLearn more: https://www.linkup.so/", "owned_by": "EmpirioLabs AI", "root": "linkup-deep-search", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Linkup-Deep-Search", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6333679-200-emcqirwpgszncxiqdbgklaeamflvockg.jpeg", "alt": "Linkup-Deep-Search model icon", "width": 200, "height": 200}, "url": "https://poe.com/linkup-deep-search"}, "reasoning": null, "parameters": [{"name": "domain_filter_mode", "schema": {"enum": ["None", "Include", "Exclude"]}, "default_value": "None", "description": "Choose to include or exclude domains (only one mode at a time)"}, {"name": "include_domains", "schema": {"type": "string"}, "default_value": "", "description": "Search only within these domains (one per line). Leave empty to search all domains."}, {"name": "exclude_domains", "schema": {"type": "string"}, "default_value": "", "description": "Exclude these domains from search results (one per line)"}, {"name": "prioritize_domains", "schema": {"type": "string"}, "default_value": "", "description": "Give higher priority to these domains (one per line)"}, {"name": "from_date", "schema": {"type": "string"}, "default_value": "", "description": "Start date for search results (YYYY-MM-DD format)"}, {"name": "to_date", "schema": {"type": "string"}, "default_value": "", "description": "End date for search results (YYYY-MM-DD format)"}, {"name": "include_images", "schema": {"type": "boolean"}, "default_value": false, "description": "Include relevant images in search results (may increase search times)"}, {"name": "image_count", "schema": {"type": "number", "minimum": 1, "maximum": 45}, "default_value": 6, "description": "How many images to display (when Include Images is enabled). More images = longer processing time."}, {"name": "enable_inline_citations", "schema": {"type": "boolean"}, "default_value": true, "description": "Include inline citations in the response text"}, {"name": "include_sources", "schema": {"type": "boolean"}, "default_value": true, "description": "Include a list of sources in the response"}]}, {"id": "linkup-standard", "object": "model", "created": 1755298530796, "description": "Linkup Standard is an AI-powered search bot that provides detailed overviews and answers sourced from the web, helping you find high-quality information quickly and accurately. Results are faster compared to its Deep search counterpart. Context Window: 100k\nLinkup's technology ranks #1 globally for factual accuracy, achieving state-of-the-art scores on OpenAI\u2019s SimpleQA benchmark. Audio/video files are not supported at this time.\n\nParameter controls available: \n1. Domain control. To search only within specific domains select `Include only these domains`, To exclude domains from the search result select `Exclude these domains`.\n2. Prioritize Domains. To give higher priority on search\n3. Date Range: Set `from date` and `to date` to select date range search. Use YYYY-MM-DD date format\n4. Content Option: Toggle `include image` to include relevant images on search and set `image count` (up to 45) to display specific number of images to display.\n5. Citation options: Toggle enable inline citation to include inline citations in the response text (Default: `on`). Toggle include sources list to include a list of sources in the response (Default: `on`)\n\nLearn more: https://www.linkup.so/", "owned_by": "EmpirioLabs AI", "root": "linkup-standard", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Linkup-Standard", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6331295-200-bhadatkswnyjhxeioylmnscjdonziozd.jpeg", "alt": "Linkup-Standard model icon", "width": 200, "height": 200}, "url": "https://poe.com/linkup-standard"}, "reasoning": null, "parameters": [{"name": "domain_filter_mode", "schema": {"enum": ["None", "Include", "Exclude"]}, "default_value": "None", "description": "Choose to include or exclude domains (only one mode at a time)"}, {"name": "include_domains", "schema": {"type": "string"}, "default_value": "", "description": "Search only within these domains (one per line). Leave empty to search all domains."}, {"name": "exclude_domains", "schema": {"type": "string"}, "default_value": "", "description": "Exclude these domains from search results (one per line)"}, {"name": "prioritize_domains", "schema": {"type": "string"}, "default_value": "", "description": "Give higher priority to these domains (one per line)"}, {"name": "from_date", "schema": {"type": "string"}, "default_value": "", "description": "Start date for search results (YYYY-MM-DD format)"}, {"name": "to_date", "schema": {"type": "string"}, "default_value": "", "description": "End date for search results (YYYY-MM-DD format)"}, {"name": "include_images", "schema": {"type": "boolean"}, "default_value": false, "description": "Include relevant images in search results (may increase search times)"}, {"name": "image_count", "schema": {"type": "number", "minimum": 1, "maximum": 45}, "default_value": 6, "description": "How many images to display (when Include Images is enabled). More images = longer processing time."}, {"name": "enable_inline_citations", "schema": {"type": "boolean"}, "default_value": true, "description": "Include inline citations in the response text"}, {"name": "include_sources", "schema": {"type": "boolean"}, "default_value": true, "description": "Include a list of sources in the response"}]}, {"id": "perplexity-pro-search", "object": "model", "created": 1763705720172, "description": "Perplexity Pro Search turns Sonar Pro into a full agentic researcher that autonomously chains web searches, and fetches full pages while streaming its live reasoning. It dynamically adapts its strategy for complex queries, far beyond standard Sonar Pro's single search. \n\nParameter controls available:\n1. Search Configuration\n   - Search Context Size (low, medium, high] adjusts search depth (affects cost and comprehensiveness)\n   - Stream mode full switches from concise reasoning display to traditional streaming\n\n2. Content Filtering\n   - Search mode academic restricts results to academic sources\n   - Search mode sec limits to SEC filings only\n   - Search domain filter example.com,nasa.gov` includes only specified domains (max 20)\n   - Search domain filter -pinterest.com,-spam.com` excludes domains (prefix with `-`)\n   - Search language filter e.g.`en,fr,de` filters by ISO 639-1 language codes (max 10, two-letter codes)\n\n3. Date and Recency Filters\n   - Search recency filter (day, week, month, year) filters by relative time from today\n   - Search after date `MM/DD/YYYY` and `Search before date `MM/DD/YYYY` for exact publication dates\n   - Note: Specific dates and recency filters are mutually exclusive (dates take priority)\n   - Last updated after filter `MM/DD/YYYY` and Last updated before filter `MM/DD/YYYY` filter by last modified date\n\n4. Location-Based Search\n   - Country e.g `US` sets two-letter ISO 3166-1 country code for localized results\n   - Region e.g. `California` specifies state/province (requires country)\n   - City e.g. \"San Francisco\" narrows to city level (requires country)\n   - Latitude -37.7749 Longitude -122.4194 for precise coordinate-based search (requires country)\n\n5. Media Results\n   - Return images includes images in search results with inline previews\n   - Image domain filter wikimedia.org,-getty.com` filters image sources (max 10, prefix `-` to exclude)\n   - Image format filter e.g. jpg,png,webp restricts to specific formats (gif, jpg, png, webp supported)\n   - Return videos includes embedded video previews (YouTube videos render as iframes)", "owned_by": "EmpirioLabs AI", "root": "perplexity-pro-search", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Perplexity-Pro-Search", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6602576-200-qlyismyqhqddkbzjqqvywnfimrgzitls.jpeg", "alt": "Perplexity-Pro-Search model icon", "width": 200, "height": 200}, "url": "https://poe.com/perplexity-pro-search"}, "reasoning": null, "parameters": [{"name": "search_context_size", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium", "description": "Higher context gives better answers but increases the base fee."}, {"name": "stream_mode", "schema": {"enum": ["concise", "full"]}, "default_value": "concise", "description": "Concise mode shows real-time reasoning steps. Full mode is traditional streaming."}, {"name": "search_mode", "schema": {"enum": ["default", "academic", "sec"]}, "default_value": "default", "description": "Filter search results by source type."}, {"name": "search_domain_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated domains. Exclude with '-'. Max 20."}, {"name": "search_language_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated ISO 639-1 language codes (2 letters). Max 10."}, {"name": "search_after_date", "schema": {"type": "string"}, "default_value": "", "description": "Use exact publication date (mutually exclusive with Recency)."}, {"name": "search_before_date", "schema": {"type": "string"}, "default_value": "", "description": "Use exact publication date (mutually exclusive with Recency)."}, {"name": "search_recency_filter", "schema": {"enum": ["none", "day", "week", "month", "year"]}, "default_value": "none", "description": "Relative to today. Cannot be combined with specific dates."}, {"name": "last_updated_after_filter", "schema": {"type": "string"}, "default_value": ""}, {"name": "last_updated_before_filter", "schema": {"type": "string"}, "default_value": ""}, {"name": "country", "schema": {"type": "string"}, "default_value": "", "description": "Two-letter ISO 3166-1 country code."}, {"name": "region", "schema": {"type": "string"}, "default_value": "", "description": "State/Province name (e.g., California, \u00cele-de-France)."}, {"name": "city", "schema": {"type": "string"}, "default_value": "", "description": "City name (e.g., San Francisco, Paris)."}, {"name": "latitude", "schema": {"type": "string"}, "default_value": "", "description": "Must be provided with Longitude and Country."}, {"name": "longitude", "schema": {"type": "string"}, "default_value": "", "description": "Must be provided with Latitude and Country."}, {"name": "return_images", "schema": {"type": "boolean"}, "default_value": false, "description": "Include images in search results."}, {"name": "image_domain_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated domains for images. Exclude with '-'. Max 10."}, {"name": "image_format_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated formats: gif, jpg, png, webp"}, {"name": "return_videos", "schema": {"type": "boolean"}, "default_value": false, "description": "Include videos in search results."}]}, {"id": "perplexity-sonar-pro", "object": "model", "created": 1737790959209, "description": "Sonar Pro by Perplexity is an advanced AI model that enhances real-time, web-connected search capabilities with double the citations and a larger context window. It's designed for complex queries, providing in-depth, nuanced answers and extended extensibility, making it ideal for enterprises and developers needing robust search solutions. Context Length: 200k (max output token limit of 8k)", "owned_by": "EmpirioLabs AI", "root": "perplexity-sonar-pro", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": {"context_length": 200000, "max_output_tokens": null}, "context_length": 200000, "metadata": {"display_name": "Perplexity-Sonar-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5585825-200-kokfosnmiptycsigormmrwmmulfmhgnn.jpeg", "alt": "Perplexity-Sonar-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/perplexity-sonar-pro"}, "reasoning": null, "parameters": [{"name": "search_context_size", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium", "description": "Higher context gives better answers but increases the base fee."}, {"name": "search_mode", "schema": {"enum": ["default", "academic", "sec"]}, "default_value": "default", "description": "Filter search results by source type."}, {"name": "search_domain_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated domains. Exclude with '-'. Max 20."}, {"name": "search_language_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated ISO 639-1 language codes (2 letters). Max 10."}, {"name": "search_after_date", "schema": {"type": "string"}, "default_value": "", "description": "Use exact publication date (mutually exclusive with Recency)."}, {"name": "search_before_date", "schema": {"type": "string"}, "default_value": "", "description": "Use exact publication date (mutually exclusive with Recency)."}, {"name": "search_recency_filter", "schema": {"enum": ["none", "day", "week", "month", "year"]}, "default_value": "none", "description": "Relative to today. Cannot be combined with specific dates."}, {"name": "last_updated_after_filter", "schema": {"type": "string"}, "default_value": ""}, {"name": "last_updated_before_filter", "schema": {"type": "string"}, "default_value": ""}, {"name": "country", "schema": {"type": "string"}, "default_value": "", "description": "Two-letter ISO 3166-1 country code."}, {"name": "region", "schema": {"type": "string"}, "default_value": "", "description": "State/Province name (e.g., California, \u00cele-de-France)."}, {"name": "city", "schema": {"type": "string"}, "default_value": "", "description": "City name (e.g., San Francisco, Paris)."}, {"name": "latitude", "schema": {"type": "string"}, "default_value": "", "description": "Must be provided with Longitude and Country."}, {"name": "longitude", "schema": {"type": "string"}, "default_value": "", "description": "Must be provided with Latitude and Country."}, {"name": "return_images", "schema": {"type": "boolean"}, "default_value": false, "description": "Include images in search results."}, {"name": "image_domain_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated domains for images. Exclude with '-'. Max 10."}, {"name": "image_format_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated formats: gif, jpg, png, webp"}, {"name": "return_videos", "schema": {"type": "boolean"}, "default_value": false, "description": "Include videos in search results."}]}, {"id": "perplexity-sonar-rsn-pro", "object": "model", "created": 1739997380566, "description": "This model operates on the open-sourced uncensored R1-1776 model from Perplexity with web search capabilities. The Perplexity Sonar Rsn Pro Reasoning Model takes AI-powered answers to the next level, offering unmatched quality and precision. Outperforming leading search engines and LLMs, This model has demonstrated superior performance in the SimpleQA benchmark, making it the gold standard for high-quality answer generation. Context Length: 128k (max output token limit of 8k)", "owned_by": "EmpirioLabs AI", "root": "perplexity-sonar-rsn-pro", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "Perplexity-Sonar-Rsn-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5687780-200-wvpoacwobjhncfioefzshawjubtgssjc.jpeg", "alt": "Perplexity-Sonar-Rsn-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/perplexity-sonar-rsn-pro"}, "reasoning": null, "parameters": [{"name": "search_context_size", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium", "description": "Higher context gives better answers but increases the base fee."}, {"name": "search_mode", "schema": {"enum": ["default", "academic", "sec"]}, "default_value": "default", "description": "Filter search results by source type."}, {"name": "search_domain_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated domains. Exclude with '-'. Max 20."}, {"name": "search_language_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated ISO 639-1 language codes (2 letters). Max 10."}, {"name": "search_after_date", "schema": {"type": "string"}, "default_value": "", "description": "Use exact publication date (mutually exclusive with Recency)."}, {"name": "search_before_date", "schema": {"type": "string"}, "default_value": "", "description": "Use exact publication date (mutually exclusive with Recency)."}, {"name": "search_recency_filter", "schema": {"enum": ["none", "day", "week", "month", "year"]}, "default_value": "none", "description": "Relative to today. Cannot be combined with specific dates."}, {"name": "last_updated_after_filter", "schema": {"type": "string"}, "default_value": ""}, {"name": "last_updated_before_filter", "schema": {"type": "string"}, "default_value": ""}, {"name": "country", "schema": {"type": "string"}, "default_value": "", "description": "Two-letter ISO 3166-1 country code."}, {"name": "region", "schema": {"type": "string"}, "default_value": "", "description": "State/Province name."}, {"name": "city", "schema": {"type": "string"}, "default_value": "", "description": "City name."}, {"name": "latitude", "schema": {"type": "string"}, "default_value": "", "description": "Must be provided with Longitude and Country."}, {"name": "longitude", "schema": {"type": "string"}, "default_value": "", "description": "Must be provided with Latitude and Country."}, {"name": "return_images", "schema": {"type": "boolean"}, "default_value": false, "description": "Include images in search results."}, {"name": "image_domain_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated domains for images. Exclude with '-'. Max 10."}, {"name": "image_format_filter", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated formats: gif, jpg, png, webp"}, {"name": "return_videos", "schema": {"type": "boolean"}, "default_value": false, "description": "Include videos in search results (YouTube embeds)."}]}, {"id": "perplexity-deep-research", "object": "model", "created": 1740542141787, "description": "Perplexity Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers information. This enables comprehensive report generation across domains like finance, technology, health, and current events. Context Length: 128k\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "perplexity-deep-research", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "Perplexity-Deep-Research", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5713235-200-nffkfdwpkxsrxhimceifpbbqldqbyqtg.jpeg", "alt": "Perplexity-Deep-Research model icon", "width": 200, "height": 200}, "url": "https://poe.com/perplexity-deep-research"}, "reasoning": null, "parameters": [{"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "high", "description": "Controls the computational effort. 'High' provides more thorough responses but increases costs."}, {"name": "search_mode", "schema": {"enum": ["default"]}, "default_value": "default", "description": "Filter search results by source type."}, {"name": "search_domain_filter", "schema": {"type": "string"}, "description": "Comma-separated domains. Exclude with '-'."}, {"name": "search_after_date_filter", "schema": {"type": "string"}}, {"name": "search_before_date_filter", "schema": {"type": "string"}}, {"name": "last_updated_after_filter", "schema": {"type": "string"}}, {"name": "last_updated_before_filter", "schema": {"type": "string"}}, {"name": "country", "schema": {"type": "string"}, "default_value": "", "description": "Two-letter ISO 3166-1 country code. (Currently disabled)"}, {"name": "latitude", "schema": {"type": "string"}, "default_value": "", "description": "Must be provided with Longitude and Country. (Currently disabled)"}, {"name": "longitude", "schema": {"type": "string"}, "default_value": "", "description": "Must be provided with Latitude and Country. (Currently disabled)"}]}, {"id": "flux-pro-1.1-ultra", "object": "model", "created": 1731696606126, "description": "State-of-the-art image generation with four times the resolution of standard FLUX-1.1-pro. Best-in-class prompt adherence and pixel-perfect image detail. \n\nOptional parameters:\nSelect an aspect ratio. Valid aspect ratios are 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, & 9:21. \nRaw detail (no other arguments needed) for an overall less processed, everyday aesthetic. \nRedux image adherence. Image Adherence strength for Redux/Restyle.\n\nNotes: Send  an image to have this model reimagine/regenerate it via FLUX Redux", "owned_by": "fal", "root": "flux-pro-1.1-ultra", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": {"context_length": 250, "max_output_tokens": null}, "context_length": 250, "metadata": {"display_name": "FLUX-pro-1.1-ultra", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5273253-200-bnztxnyqyrqwmldpbipdybmafmboyyqm.jpeg", "alt": "FLUX-pro-1.1-ultra model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-pro-1.1-ultra"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "9:21"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}, {"name": "strength", "schema": {"type": "number", "minimum": 0.0, "maximum": 1.0}, "default_value": 0.25, "description": "Image Adherence strength for Redux/Restyle."}, {"name": "raw", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to enable raw photographic detail."}]}, {"id": "mistral-small-3.1", "object": "model", "created": 1742338142315, "description": "Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and vision tasks, including image analysis, programming, mathematical reasoning, and multilingual support across dozens of languages. Equipped with an extensive 128k token context window and optimized for efficient local inference, it supports use cases such as conversational agents, function calling, long-document comprehension, and privacy-sensitive deployments.", "owned_by": "EmpirioLabs AI", "root": "mistral-small-3.1", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Mistral-Small-3.1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5809275-200-pvgssxtijpqzadxjnnfhdevhyvczdyyq.jpeg", "alt": "Mistral-Small-3.1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/mistral-small-3.1"}, "reasoning": null, "parameters": []}, {"id": "sonic-3.0", "object": "model", "created": 1761174377362, "description": "Generates audio based on your prompt using the latest Cartesia's Sonic 3.0 text-to-speech model in your voice of choice.\nSupports 10k characters.\n\nYou can select a voice and language in option menu in the input bar.\n\nThe following voices are supported covering 42 languages (English, Arabic, Bengali, Bulgarian, Chinese, Croatian, Czech, Danish, Dutch, Finnish, French, Georgian, German, Greek, Gujarati, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Kannada, Korean, Malay, Malayalam, Marathi, Norwegian, Polish, Portuguese, Punjabi, Romanian, Russian, Slovak, Spanish, Swedish, Tagalog, Tamil, Telugu, Thai, Turkish, Ukrainian, Vietnamese):\n\n-- English --\nAriana\nKiefer\nTessa\nBrandon\nLinda - Conversational Guide\nRonald - Thinker\nBrooke - Big Sister\nKatie - Friendly Fixer\nJacqueline - Reassuring Agent\nCaroline - Southern Guide\n\n-- Arabic --\nAmira - Dreamy Whisperer\nOmar - High-Energy Presenter\n\n-- Bengali --\nPooja - Everyday Assistant\nRubel - City Guide\n\n-- Bulgarian --\nIvana - Instruction Provider\nGeorgi - Conversationalist\n\n-- Chinese --\nHua - Sunny Support\nYue - Gentle Woman\nTao - Lecturer\nLan - Instructor\n\n-- Croatian --\nPetra - Strict Lecturer\nIvan - Bar Companion\n\n-- Czech --\nJana - Crisp Conversationalist\nPetr - Pastor\n\n-- Danish --\nKatrine - Calm Caregiver\n\n-- Dutch --\nBram - Instructional\nDaan - Business Baritone\nSanne - Clear Companion\nLucas - Storyteller\n\n-- Finnish --\nHelmi - Warm Friend\nMikko - Narration Expert\n\n-- French --\nHelpful French Lady\nFrench Narrator Man\nCalm French Woman\nAntoine - Stern Man\n\n-- Georgian --\nLevan - Support Guide\nTamara - Support Specialist\n\n-- German --\nThomas - Anchor\nViktoria - Phone Conversationalist\nLukas - Professional\nLena - Muse\n\n-- Greek --\nDespina - Motherly Woman\nNikos - Radio Storyteller\n\n-- Gujarati --\nIsha - Learner\nAmit - Sports Student\n\n-- Hebrew --\nNoam - Broadcaster\n\n-- Hindi --\nArushi - Hinglish Speaker\nSunil - Official Announcer\nRiya - College Roommate\nAadhya - Soother\n\n-- Hungarian --\nGabor - Reassuring\nEszter - Customer Companion\n\n-- Indonesian --\nSiti - Ad Narrator\nAndi - Dynamic Presenter\n\n-- Italian --\nLiv - Casual Friend\nAlessandra - Melodic Guide\nFrancesca - Elegant Partner\nGiancarlo - Support Leader\n\n-- Japanese --\nYumiko - Friendly Agent\nEmi - Soft-Spoken Friend\nYuki - Calm Woman\nDaisuke - Businessman\n\n-- Kannada --\nPrakash - Instructor\nDivya - Joyful Narrator\n\n-- Korean --\nJihyun - Anchorwoman\nMimi - Show Stopper\nByungtae - Enforcer\nJiwoo - Service Specialist\n\n-- Malay --\nAisyah - Chat Partner\nFaiz - Family Guide\n\n-- Malayalam --\nLatha - Friendly Host\n\n-- Marathi --\nSuresh - Instruction\nAnika - Enthusiastic Seller\n\n-- Norwegian --\nLars - Casual Conversationalist\n\n-- Polish --\nTomek - Casual Companion\nWojciech - Documentarian\nPiotr - Corporate Lead\nKatarzyna - Melodic Storyteller\n\n-- Portuguese --\nLuana - Public Speaker\nFelipe - Casual Talker\nAna Paula - Marketer\nBeatriz - Support Guide\n\n-- Punjabi --\nGurpreet - Companion\nJaspreet - Commercial Woman\n\n-- Romanian --\nAndrada - Steady Speaker\nAndrei - Conversationalist Guy\n\n-- Russian --\nTatiana - Friendly Storyteller\nNatalya - Soothing Guide\nIrina - Poetic\nSergei - Expressive Narrator\n\n-- Slovak --\nKatarina - Friendly Sales\nPeter - Narrator Man\n\n-- Spanish --\nPedro - Formal Speaker\nDaniela - Relaxed Woman\nFran - Confident Young Professional\nIsabel - Teacher\n\n-- Swedish --\nFreja - Nordic Reader\nIngrid - Peaceful Guide\nAnders - Nordic Baritone\nCees - Nordic Narrator\n\n-- Tagalog --\nLuz - Casual Speaker\nAngelo - Calm Narrator\n\n-- Tamil --\nArun - Lively\nLakshmi - Everyday\n\n-- Telugu --\nSindhu - Conversational Partner\nVikram - Folk Narrator\n\n-- Thai --\nSomchai - Star\nSuda - Fortune Teller\n\n-- Turkish --\nEmre - Calming Speaker\nLeyla - Story Companion\nAzra - Service Specialist\nTaylan - Expressive\n\n-- Ukrainian --\nOleh - Professional Guy\n\n-- Vietnamese --\nMinh - Conversational Partner\nXia - Calm Companion", "owned_by": "Cartesia AI", "root": "sonic-3.0", "architecture": {"input_modalities": ["text"], "output_modalities": ["audio"], "modality": "text->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0061", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Sonic-3.0", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6522088-200-gfqmabnryxhkpxktjqjxhsgovqwdspxw.jpeg", "alt": "Sonic-3.0 model icon", "width": 200, "height": 200}, "url": "https://poe.com/sonic-3.0"}, "reasoning": null, "parameters": [{"name": "language", "schema": {"enum": ["ar", "bn", "bg", "zh", "hr", "cs", "da", "nl", "en", "fi", "fr", "ka", "de", "el", "gu", "he", "hi", "hu", "id", "it", "ja", "kn", "ko", "ms", "ml", "mr", "no", "pl", "pt", "pa", "ro", "ru", "sk", "es", "sv", "tl", "ta", "te", "th", "tr", "uk", "vi"]}, "default_value": "en"}, {"name": "voice", "schema": {"enum": ["ariana", "brandon", "brooke - big sister", "caroline - southern guide", "jacqueline - reassuring agent", "katie - friendly fixer", "kiefer", "linda - conversational guide", "ronald - thinker", "tessa", "amira - dreamy whisperer", "omar - high-energy presenter", "georgi - conversationalist", "ivana - instruction provider", "pooja - everyday assistant", "rubel - city guide", "jana - crisp conversationalist", "petr - pastor", "katrine - calm caregiver", "lena - muse", "lukas - professional", "thomas - anchor", "viktoria - phone conversationalist", "despina - motherly woman", "nikos - radio storyteller", "daniela - relaxed woman", "fran - confident young professional", "isabel - teacher", "pedro - formal speaker", "helmi - warm friend", "mikko - narration expert", "antoine - stern man", "calm french woman", "french narrator man", "helpful french lady", "amit - sports student", "isha - learner", "noam - broadcaster", "aadhya - soother", "arushi - hinglish speaker", "riya - college roommate", "sunil - official announcer", "ivan - bar companion", "petra - strict lecturer", "eszter - customer companion", "gabor - reassuring voice", "andi - dynamic presenter", "siti - ad narrator", "alessandra - melodic guide", "francesca - elegant partner", "giancarlo - support leader", "liv - casual friend", "daisuke - businessman", "emi - soft-spoken friend", "yuki - calm woman", "yumiko - friendly agent", "levan - support guide", "tamara - support specialist", "divya - joyful narrator", "prakash - instructor", "byungtae - enforcer", "jihyun - anchorwoman", "jiwoo - service specialist", "mimi - show stopper", "latha - friendly host", "anika - enthusiastic seller", "suresh - instruction voice", "aisyah - chat partner", "faiz - family guide", "bram - instructional voice", "daan - business baritone", "lucas - storyteller", "sanne - clear companion", "lars - casual conversationalist", "gurpreet - companion", "jaspreet - commercial woman", "katarzyna - melodic storyteller", "piotr - corporate lead", "tomek - casual companion", "wojciech - documentarian", "ana paula - marketer", "beatriz - support guide", "felipe - casual talker", "luana - public speaker", "andrada - steady speaker", "andrei - conversationalist guy", "irina - poetic voice", "natalya - soothing guide", "sergei - expressive narrator", "tatiana - friendly storyteller", "katarina - friendly sales", "peter - narrator man", "anders - nordic baritone", "cees - nordic narrator", "freja - nordic reader", "ingrid - peaceful guide", "arun - lively voice", "lakshmi - everyday voice", "sindhu - conversational partner", "vikram - folk narrator", "somchai - star", "suda - fortune teller", "angelo - calm narrator", "luz - casual speaker", "azra - service specialist", "emre - calming speaker", "leyla - story companion", "taylan - expressive voice", "oleh - professional guy", "minh - conversational partner", "xia - calm companion", "hua - sunny support", "lan - instructor", "tao - lecturer", "yue - gentle woman"]}}]}, {"id": "hailuo-music-v1.5", "object": "model", "created": 1758018191524, "description": "Generate music from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality, diverse musical compositions. \n\nNotes: \nSend the lyrics of the music over as your prompt. \nBoth prompt/lyrics and style must be sent over for best quality.\nThe prompt supports [intro][verse][chorus][bridge][outro] sections.\n\nOptional parameters:\nSet music style to set the style of the generated music - for example, rock and roll, hip-hop, etc.  ", "owned_by": "fal", "root": "hailuo-music-v1.5", "architecture": {"input_modalities": ["text"], "output_modalities": ["audio"], "modality": "text->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Hailuo-Music-v1.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6422177-200-ocastwbwossrvrdvworfhglqwlkicizt.jpeg", "alt": "Hailuo-Music-v1.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/hailuo-music-v1.5"}, "reasoning": null, "parameters": [{"name": "style", "schema": {"type": "string"}, "default_value": ""}]}, {"id": "elevenlabs-music", "object": "model", "created": 1756499655464, "description": "The ElevenLabs music model is a generative AI system designed to compose original music from text prompts. It allows creators to specify genres, moods, instruments, and structure, producing royalty-free tracks tailored to their needs. The model emphasizes speed, creative flexibility, and high-quality audio output, making it suitable for use in videos, podcasts, games, and other multimedia projects. This bot can produce songs with suggested lyrics based on general descriptions, exact lyrics if specified as such, or instrumental ones, all via prompting.\n\nOptional parameters:\nMusic length to set the length of the song in milliseconds (10,000 to 300,000 ms).\n\nNote: Prompt input cannot exceed 2,000 characters.", "owned_by": "ElevenLabs", "root": "elevenlabs-music", "architecture": {"input_modalities": ["text"], "output_modalities": ["audio"], "modality": "text->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": {"context_length": 2000, "max_output_tokens": null}, "context_length": 2000, "metadata": {"display_name": "ElevenLabs-Music", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6372089-200-yuwvwbjdljzmykjpdzbxizuqqgowdgzq.jpeg", "alt": "ElevenLabs-Music model icon", "width": 200, "height": 200}, "url": "https://poe.com/elevenlabs-music"}, "reasoning": null, "parameters": [{"name": "music_length_ms", "schema": {"type": "number", "minimum": 10000, "maximum": 300000}, "description": "The length of the song to generate in milliseconds."}]}, {"id": "whisper-v3-large-t", "object": "model", "created": 1756410173218, "description": "Whisper v3 Large is a state-of-the-art automatic speech recognition and translation model developed by OpenAI, offering 10\u201320% lower error rates than its predecessor, Whisper large-v2. It supports transcription and translation across numerous languages, with improvements in handling diverse audio inputs, including noisy conditions and long-form audio files.", "owned_by": "Together AI", "root": "whisper-v3-large-t", "architecture": {"input_modalities": ["text", "audio"], "output_modalities": ["audio"], "modality": "text,audio->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0030", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Whisper-V3-Large-T", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6369049-200-djrziwdxcgrbqczrgkmzlwxazvwmmcan.jpeg", "alt": "Whisper-V3-Large-T model icon", "width": 200, "height": 200}, "url": "https://poe.com/whisper-v3-large-t"}, "reasoning": null, "parameters": []}, {"id": "stable-audio-2.5", "object": "model", "created": 1756869275249, "description": "Stable Audio 2.5 generates high-quality audio up to 3 minutes long from text prompts, supporting text-to-audio, audio-to-audio transformations, and inpainting with customizable settings like duration, steps, CFG scale, and more. It is Ideal for music production, cinematic sound design, and remixing. \n\nNote: Audio-to-audio and inpaint modes require a prompt alongside an uploaded audio file for generation.\n\nParameter controls available:\n1. Basic\n   - Generation Mode: Text to Audio, Audio to Audio (Transform), Audio Inpaint (Edit Segment)\n   - Output format: WAV (high quality), MP3 (Compressed)\n\n2. Timing and Randomness \n   - Duration [1-190 seconds] controls how long generated audio is\n   - Seed [0-4294967294]' disables random seed generation. Use random seed must be toggled off to set.\n\n3. Advanced\n   - Cfg scale [1-25]: Higher = closer to prompt (recommended 7-15)\n   - Steps [4-8]`: Higher = better quality (recommended 6-8)\n\n4. Transformation control (only for audio-to-audio)\n   - Strength [0-1]`: How much to change/transform (0.3-0.7 typical)\n\n5. Inpainting control (only for audio-inpaint)\n   - Mask start time [seconds] start time of the uploaded audio to modify\n   - Mask end time [seconds] end time of the uploaded audio to modify", "owned_by": "EmpirioLabs AI", "root": "stable-audio-2.5", "architecture": {"input_modalities": ["text", "audio"], "output_modalities": ["audio"], "modality": "text,audio->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Stable-Audio-2.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6383502-200-kmmicmzcxmbyzqzvootjeaaznwvsjaey.jpeg", "alt": "Stable-Audio-2.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/stable-audio-2.5"}, "reasoning": null, "parameters": [{"name": "mode", "schema": {"enum": ["text-to-audio", "audio-to-audio", "audio-inpaint"]}, "default_value": "text-to-audio", "description": "Choose the audio generation method"}, {"name": "output_format", "schema": {"enum": ["mp3", "wav"]}, "default_value": "mp3", "description": "Select the audio file format"}, {"name": "strength", "schema": {"type": "number", "minimum": 0.01, "maximum": 1}, "default_value": 1, "description": "How much to transform the input audio (1 = complete transformation, 0 = identical to input)"}, {"name": "mask_start", "schema": {"type": "number", "minimum": 0, "maximum": 190}, "default_value": 30, "description": "Start of the segment to replace"}, {"name": "mask_end", "schema": {"type": "number", "minimum": 0, "maximum": 190}, "default_value": 190, "description": "End of the segment to replace"}, {"name": "duration", "schema": {"type": "number", "minimum": 1, "maximum": 190}, "default_value": 190, "description": "Length of the generated audio (up to 190 seconds)"}, {"name": "random_seed", "schema": {"type": "boolean"}, "default_value": true, "description": "Use a random seed for varied results each time"}, {"name": "seed", "schema": {"type": "string"}, "default_value": "0", "description": "Enter a specific seed value for reproducibility (0-4294967294)"}, {"name": "steps", "schema": {"type": "number", "minimum": 4, "maximum": 8}, "default_value": 8, "description": "Number of sampling steps (higher = potentially better quality but slower)"}, {"name": "cfg_scale", "schema": {"type": "number", "minimum": 1, "maximum": 25}, "default_value": 1, "description": "How strictly to follow the prompt (higher = closer to prompt, lower = more creative)"}]}, {"id": "stable-audio-2.0", "object": "model", "created": 1756880177270, "description": "Stable Audio 2.0 generates audio up to 3 minutes long from text prompts, supporting text-to-audio and audio-to-audio transformations with customizable settings like duration, steps, CFG scale, and more. It is ideal for creative professionals seeking detailed and extended outputs from simple prompts.\n\nNote: Audio-to-audio mode requires a prompt alongside an uploaded audio file for generation.\n\nParameter controls available:\n1. Basic\n- Generation Mode: Text to Audio, Audio to Audio (Transform)\n- Output format: WAV (high quality), MP3 (Compressed)\n\n2. Timing and Randomness\n- Duration [1-190 seconds] controls how long generated audio is\n- Seed [0-4294967294]' disables random seed generation. Use random seed must be toggled off to set.\n\n3. Advanced\n- Cfg scale [1-25]: Higher = closer to prompt (recommended 7-15)\n- Steps [4-8]`: Higher = better quality (recommended 6-8)\n\n4. Transformation control (only for audio-to-audio)\n- Strength [0-1]`: How much to change/transform (0.3-0.7 typical)", "owned_by": "EmpirioLabs AI", "root": "stable-audio-2.0", "architecture": {"input_modalities": ["text", "audio"], "output_modalities": ["audio"], "modality": "text,audio->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Stable-Audio-2.0", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6383917-200-riplheayeyibttxnjsvsruvlepwbgxzr.jpeg", "alt": "Stable-Audio-2.0 model icon", "width": 200, "height": 200}, "url": "https://poe.com/stable-audio-2.0"}, "reasoning": null, "parameters": [{"name": "mode", "schema": {"enum": ["text-to-audio", "audio-to-audio"]}, "default_value": "text-to-audio", "description": "Choose the audio generation method"}, {"name": "output_format", "schema": {"enum": ["mp3", "wav"]}, "default_value": "mp3", "description": "Select the audio file format"}, {"name": "strength", "schema": {"type": "number", "minimum": 0, "maximum": 1}, "default_value": 1, "description": "How much to transform the input audio (1 = complete transformation, 0 = identical to input)"}, {"name": "duration", "schema": {"type": "number", "minimum": 1, "maximum": 190}, "default_value": 190, "description": "Length of the generated audio (up to 190 seconds)"}, {"name": "random_seed", "schema": {"type": "boolean"}, "default_value": true, "description": "Use a random seed for varied results each time"}, {"name": "seed", "schema": {"type": "string"}, "default_value": "0", "description": "Enter a specific seed value for reproducibility (0-4294967294)"}, {"name": "steps", "schema": {"type": "number", "minimum": 30, "maximum": 100}, "default_value": 50, "description": "Number of sampling steps (higher = potentially better quality but slower, affects cost)"}, {"name": "cfg_scale", "schema": {"type": "number", "minimum": 1, "maximum": 25}, "default_value": 7, "description": "How strictly to follow the prompt (higher = closer to prompt, lower = more creative)"}]}, {"id": "hailuo-speech-02", "object": "model", "created": 1749503032615, "description": "Generate speech from text prompts using the MiniMax Speech-02 model. \n\nOptional parameters:\nHD mode. Toggle on for higher quality output with a higher price. \nSet Speed. Set from 0.5 to 2. Default: 1.\nSet Volume. Set from 0 to 10. Default: 1.\nSet Pitch. Set from -12 to 12. Default: 0.\nSet Emotion. Select from happy, sad, angry, fearful, disgusted, surprised and fearful. Default: None.\nSet Language boost. Select language available. Default. None.\nSet Voice for the audio generation. Default: Wise Woman.\n\nPlease check the UI for allowed values for each parameter.", "owned_by": "fal", "root": "hailuo-speech-02", "architecture": {"input_modalities": ["text"], "output_modalities": ["audio"], "modality": "text->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Hailuo-Speech-02", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6107517-200-wlzwxrviyosrqxwsjvjwyuohkavdjukk.jpeg", "alt": "Hailuo-Speech-02 model icon", "width": 200, "height": 200}, "url": "https://poe.com/hailuo-speech-02"}, "reasoning": null, "parameters": [{"name": "hd", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to enable hd mode, generating audio slower at a higher cost, but with higher quality."}, {"name": "speed", "schema": {"type": "number", "minimum": 0.5, "maximum": 2.0}, "default_value": 1}, {"name": "volume", "schema": {"type": "number", "minimum": 0, "maximum": 10}, "default_value": 1}, {"name": "pitch", "schema": {"type": "number", "minimum": -12, "maximum": 12}, "default_value": 0}, {"name": "emotion", "schema": {"enum": ["None", "happy", "sad", "angry", "fearful", "disgusted", "surprised", "neutral"]}, "default_value": "None", "description": "Emotion of the generated audio."}, {"name": "language", "schema": {"enum": ["Chinese", "Chinese,Yue", "English", "Arabic", "Russian", "Spanish", "French", "Portuguese", "German", "Turkish", "Dutch", "Ukrainian", "Vietnamese", "Indonesian", "Japanese", "Italian", "Korean", "Thai", "Polish", "Romanian", "Greek", "Czech", "Finnish", "Hindi", "auto"]}, "default_value": "auto", "description": "Language performance boost for the audio to be generated."}, {"name": "voice", "schema": {"enum": ["Wise_Woman", "Friendly_Person", "Inspirational_girl", "Deep_Voice_Man", "Calm_Woman", "Casual_Guy", "Lively_Girl", "Patient_Man", "Young_Knight", "Determined_Man", "Lovely_Girl", "Decent_Boy", "Imposing_Manner", "Elegant_Man", "Abbess", "Sweet_Girl_2", "Exuberant_Girl"]}, "default_value": "Wise_Woman", "description": "Voice for the audio to be generated."}]}, {"id": "elevenlabs-v2.5-turbo", "object": "model", "created": 1730153913289, "description": "ElevenLabs' leading text-to-speech technology converts your text into natural-sounding speech, using the Turbo v2.5 model. Simply send a text prompt, and the bot will generate audio using your choice of available voices. If you link a URL or a PDF, it will do its best to read it aloud to you. The overall default voice is Jessica, an American-English female.\n\nOptional parameters:\nVoice Name. (e.g. \"Hello world --voice Eric\") to customize the voice used. \nLanguage. Language ISO-639-1 code to your message if you notice pronunciation errors; table of ISO-639-1 codes here: https://en.wikipedia.org/wiki/List_of_ISO_639_language_codes (e.g. zh for Chinese, es for Spanish, hi for Hindi)\n\nThe following voices are supported and recommended for each language:\n\nEnglish -- Sarah, George, River, Matilda, Will, Jessica, Brian, Lily, Monika Sogam\nChinese -- James Gao, Martin Li, Will, River\nSpanish -- David Martin, Will, Efrayn, Alejandro, Sara Martin, Regina Martin\nHindi -- Ranga, Niraj, Liam, Raju, Leo, Manu, Vihana Huja, Kanika, River, Monika Sogam, Muskaan, Saanu, Riya, Devi\nArabic -- Bill, Mo Wiseman, Haytham, George, Mona, Sarah, Sana, Laura\nGerman -- Bill, Otto, Leon Stern, Mila, Emilia, Lea, Leonie\nIndonesian -- Jessica, Putra, Mahaputra\nPortuguese -- Will, Muhammad, Onildo, Lily, Jessica, Alice\nVietnamese -- Bill, Liam, Trung Caha, Van Phuc, Ca Dao, Trang, Jessica, Alice, Matilda\nFilipino -- Roger, Brian, Alice, Matilda\nFrench -- Roger, Louis, Emilie\nSwedish -- Will, Chris, Jessica, Charlotte\nTurkish -- Cavit Pancar, Sohbet Adami, Belma, Sultan, Mahidevran\nRomanian -- Eric, Bill, Brian, Charlotte, Lily\nItalian -- Carmelo, Luca, Alice, Lily\nPolish -- Robert, Rob, Eric, Pawel, Lily, Alice\nNorwegian -- Chris, Charlotte\nCzech -- Pawel\nFinnish -- Callum, River\nHungarian -- Brian, Sarah\nJapanese -- Alice\n\nPrompt input cannot exceed 40,000 characters.", "owned_by": "ElevenLabs", "root": "elevenlabs-v2.5-turbo", "architecture": {"input_modalities": ["text"], "output_modalities": ["audio"], "modality": "text->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "ElevenLabs-v2.5-Turbo", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5176044-200-ixsrhozcvbrhrvwgdxghshtrqpjjashv.jpeg", "alt": "ElevenLabs-v2.5-Turbo model icon", "width": 200, "height": 200}, "url": "https://poe.com/elevenlabs-v2.5-turbo"}, "reasoning": null, "parameters": [{"name": "language", "schema": {"enum": ["en", "zh", "es", "hi", "ar", "de", "id", "pt", "vi", "tl", "fr", "sv", "tr", "ro", "it", "pl", "no", "cs", "fi", "hu", "ja"]}, "default_value": "en"}, {"name": "voice", "schema": {"enum": ["Sarah", "George", "River", "Matilda", "Will", "Jessica", "Brian", "Lily", "Monika Sogam", "Hope", "James", "James Gao", "Martin Li", "David Martin", "Efrayn", "Alejandro", "Sara Martin", "Regina Martin", "Ranga", "Niraj", "Liam", "Raju", "Leo", "Manu", "Vihana Huja", "Kanika", "Muskaan", "Saanu", "Riya", "Devi", "Bill", "Mo Wiseman", "Haytham", "Mona", "Sana", "Laura", "Otto", "Leon Stern", "Mila", "Emilia", "Lea", "Leonie", "Putra", "Mahaputra", "Muhammad", "Onildo", "Alice", "Trung Caha", "Van Phuc", "Ca Dao", "Trang", "Roger", "Louis", "Emilie", "Chris", "Charlotte", "Cavit Pancar", "Sohbet Adami", "Belma", "Sultan", "Mahidevran", "Eric", "Carmelo", "Luca", "Robert", "Rob", "Pawel", "Callum"]}}]}, {"id": "gemini-2.5-flash-tts", "object": "model", "created": 1758667568690, "description": "Gemini\u20112.5\u2011Flash\u2011TTS is Google\u2019s low\u2010latency text\u2011to\u2011speech model that converts text input into audio output, supporting both single\u2011 and multi\u2011speaker voices with controllable style, accent, and expressive tone \u2014 ideal for applications like podcasts, audiobooks, and conversational voice systems.\n\nNotes:\n- Text and style prompt limited to 4,000 bytes each (8,000 bytes combined)\n- Max output duration: approximately 10 minutes\n- Multi-speaker requires SpeakerName: text format (example: Alice: Hi! Bob: Hello, must be on new lines)\n- The model auto-detects the input language. The Language setting is a hint to help choose the right voice/accent, the model may override it if the text is in a different language.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "gemini-2.5-flash-tts", "architecture": {"input_modalities": ["text"], "output_modalities": ["audio"], "modality": "text->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Gemini-2.5-Flash-TTS", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6445232-200-mqnemyjcsgiwxzrqnetfmasoplizeiis.jpeg", "alt": "Gemini-2.5-Flash-TTS model icon", "width": 200, "height": 200}, "url": "https://poe.com/gemini-2.5-flash-tts"}, "reasoning": null, "parameters": [{"name": "mode", "schema": {"enum": ["single", "multi"]}, "default_value": "single", "description": "Choose between single speaker or conversation mode"}, {"name": "language", "schema": {"enum": ["ar-EG", "bn-BD", "nl-NL", "en-IN", "en-US", "fr-FR", "de-DE", "hi-IN", "id-ID", "it-IT", "ja-JP", "ko-KR", "mr-IN", "pl-PL", "pt-BR", "ro-RO", "ru-RU", "es-ES", "ta-IN", "te-IN", "th-TH", "tr-TR", "uk-UA", "vi-VN", "af-ZA", "sq-AL", "am-ET", "ar-001", "hy-AM", "az-AZ", "eu-ES", "be-BY", "bg-BG", "my-MM", "ca-ES", "ceb-PH", "cmn-CN", "cmn-TW", "hr-HR", "cs-CZ", "da-DK", "en-AU", "en-GB", "et-EE", "fil-PH", "fi-FI", "fr-CA", "gl-ES", "ka-GE", "el-GR", "gu-IN", "ht-HT", "he-IL", "hu-HU", "is-IS", "jv-JV", "kn-IN", "kok-IN", "lo-LA", "la-VA", "lv-LV", "lt-LT", "lb-LU", "mk-MK", "mai-IN", "mg-MG", "ms-MY", "ml-IN", "mn-MN", "ne-NP", "nb-NO", "nn-NO", "or-IN", "ps-AF", "fa-IR", "pt-PT", "pa-IN", "sr-RS", "sd-IN", "si-LK", "sk-SK", "sl-SI", "es-419", "es-MX", "sw-KE", "sv-SE", "ur-PK"]}, "default_value": "en-US", "description": "Language and region for speech synthesis"}, {"name": "output_format", "schema": {"enum": ["MP3", "WAV", "OGG", "ALAW", "MULAW"]}, "default_value": "WAV", "description": "Choose the audio file format"}, {"name": "voice", "schema": {"enum": ["Zephyr", "Puck", "Charon", "Kore", "Fenrir", "Leda", "Orus", "Aoede", "Callirrhoe", "Autonoe", "Enceladus", "Iapetus", "Umbriel", "Algieba", "Despina", "Erinome", "Algenib", "Rasalgethi", "Laomedeia", "Achernar", "Alnilam", "Schedar", "Gacrux", "Pulcherrima", "Achird", "Zubenelgenubi", "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat"]}, "default_value": "Charon", "description": "Voice for the first speaker"}, {"name": "voice2", "schema": {"enum": ["Zephyr", "Puck", "Charon", "Kore", "Fenrir", "Leda", "Orus", "Aoede", "Callirrhoe", "Autonoe", "Enceladus", "Iapetus", "Umbriel", "Algieba", "Despina", "Erinome", "Algenib", "Rasalgethi", "Laomedeia", "Achernar", "Alnilam", "Schedar", "Gacrux", "Pulcherrima", "Achird", "Zubenelgenubi", "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat"]}, "default_value": "Kore", "description": "Voice for the second speaker"}, {"name": "speaker1_name", "schema": {"type": "string"}, "default_value": "Speaker1", "description": "Name for first speaker (alphanumeric, no spaces)"}, {"name": "speaker2_name", "schema": {"type": "string"}, "default_value": "Speaker2", "description": "Name for second speaker (alphanumeric, no spaces)"}, {"name": "speed", "schema": {"type": "number", "minimum": 0.25, "maximum": 2.0}, "default_value": 1.0, "description": "Speaking rate (0.25x slowest to 2.0x fastest)"}, {"name": "volume_gain", "schema": {"type": "number", "minimum": -96, "maximum": 16}, "default_value": 0, "description": "Adjust output volume in decibels (-96 to +16 dB)"}, {"name": "sample_rate", "schema": {"enum": ["8000", "16000", "22050", "24000", "44100", "48000"]}, "default_value": "24000", "description": "Audio sample rate in Hz (applies to all formats)"}, {"name": "style_prompt", "schema": {"type": "string"}, "default_value": "", "description": "Instructions for how to speak (tone, emotion, pace, accent). Supports audio tags like [whispers], [laughs], [excited], [sigh], [shouting], etc."}]}, {"id": "gemini-2.5-pro-tts", "object": "model", "created": 1758861500162, "description": "Gemini\u20112.5\u2011Pro\u2011TTS is Google\u2019s highest\u2011quality text\u2011to\u2011speech model preview, designed for complex workflows like podcasts, audiobooks, and customer support; it delivers expressive, accent\u2011 and style\u2011controllable single\u2011 or multi\u2011speaker speech, supporting over 23 languages, and built for state\u2011of\u2011the\u2011art output with the most powerful model architecture.\n\nNotes:\n- Text and style prompt limited to 4,000 bytes each (8,000 bytes combined)\n- Max output duration: approximately 10 minutes\n- Multi-speaker requires SpeakerName: text format (example: Alice: Hi! Bob: Hello, must be on new lines)\n- The model auto-detects the input language. The Language setting is a hint to help choose the right voice/accent, the model may override it if the text is in a different language.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "gemini-2.5-pro-tts", "architecture": {"input_modalities": ["text"], "output_modalities": ["audio"], "modality": "text->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Gemini-2.5-Pro-TTS", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6451759-200-umglnxqtuzjaxusqhtpkeletxatkjifl.jpeg", "alt": "Gemini-2.5-Pro-TTS model icon", "width": 200, "height": 200}, "url": "https://poe.com/gemini-2.5-pro-tts"}, "reasoning": null, "parameters": [{"name": "mode", "schema": {"enum": ["single", "multi"]}, "default_value": "single", "description": "Choose between single speaker or conversation mode"}, {"name": "language", "schema": {"enum": ["ar-EG", "bn-BD", "nl-NL", "en-IN", "en-US", "fr-FR", "de-DE", "hi-IN", "id-ID", "it-IT", "ja-JP", "ko-KR", "mr-IN", "pl-PL", "pt-BR", "ro-RO", "ru-RU", "es-ES", "ta-IN", "te-IN", "th-TH", "tr-TR", "uk-UA", "vi-VN", "af-ZA", "sq-AL", "am-ET", "ar-001", "hy-AM", "az-AZ", "eu-ES", "be-BY", "bg-BG", "my-MM", "ca-ES", "ceb-PH", "cmn-CN", "cmn-TW", "hr-HR", "cs-CZ", "da-DK", "en-AU", "en-GB", "et-EE", "fil-PH", "fi-FI", "fr-CA", "gl-ES", "ka-GE", "el-GR", "gu-IN", "ht-HT", "he-IL", "hu-HU", "is-IS", "jv-JV", "kn-IN", "kok-IN", "lo-LA", "la-VA", "lv-LV", "lt-LT", "lb-LU", "mk-MK", "mai-IN", "mg-MG", "ms-MY", "ml-IN", "mn-MN", "ne-NP", "nb-NO", "nn-NO", "or-IN", "ps-AF", "fa-IR", "pt-PT", "pa-IN", "sr-RS", "sd-IN", "si-LK", "sk-SK", "sl-SI", "es-419", "es-MX", "sw-KE", "sv-SE", "ur-PK"]}, "default_value": "en-US", "description": "Language and region for speech synthesis"}, {"name": "output_format", "schema": {"enum": ["WAV", "MP3", "OGG", "ALAW", "MULAW"]}, "default_value": "WAV", "description": "Choose the audio file format"}, {"name": "voice", "schema": {"enum": ["Zephyr", "Puck", "Charon", "Kore", "Fenrir", "Leda", "Orus", "Aoede", "Callirrhoe", "Autonoe", "Enceladus", "Iapetus", "Umbriel", "Algieba", "Despina", "Erinome", "Algenib", "Rasalgethi", "Laomedeia", "Achernar", "Alnilam", "Schedar", "Gacrux", "Pulcherrima", "Achird", "Zubenelgenubi", "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat"]}, "default_value": "Charon", "description": "Voice for the first speaker"}, {"name": "voice2", "schema": {"enum": ["Zephyr", "Puck", "Charon", "Kore", "Fenrir", "Leda", "Orus", "Aoede", "Callirrhoe", "Autonoe", "Enceladus", "Iapetus", "Umbriel", "Algieba", "Despina", "Erinome", "Algenib", "Rasalgethi", "Laomedeia", "Achernar", "Alnilam", "Schedar", "Gacrux", "Pulcherrima", "Achird", "Zubenelgenubi", "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat"]}, "default_value": "Kore", "description": "Voice for the second speaker"}, {"name": "speaker1_name", "schema": {"type": "string"}, "default_value": "Speaker1", "description": "Name for first speaker (alphanumeric, no spaces)"}, {"name": "speaker2_name", "schema": {"type": "string"}, "default_value": "Speaker2", "description": "Name for second speaker (alphanumeric, no spaces)"}, {"name": "speed", "schema": {"type": "number", "minimum": 0.25, "maximum": 2.0}, "default_value": 1.0, "description": "Speaking rate (0.25x slowest to 2.0x fastest)"}, {"name": "volume_gain", "schema": {"type": "number", "minimum": -96, "maximum": 16}, "default_value": 0, "description": "Adjust output volume in decibels (-96 to +16 dB)"}, {"name": "sample_rate", "schema": {"enum": ["8000", "16000", "22050", "24000", "44100", "48000"]}, "default_value": "24000", "description": "Audio sample rate in Hz (applies to all formats)"}, {"name": "style_prompt", "schema": {"type": "string"}, "default_value": "", "description": "Instructions for how to speak (tone, emotion, pace, accent). Supports audio tags like [whispers], [laughs], [excited], [sigh], [shouting], etc."}]}, {"id": "orpheus-tts", "object": "model", "created": 1743698312235, "description": "Orpheus TTS is a state-of-the-art, Llama-based Speech-LLM designed for high-quality, empathetic text-to-speech generation. Send a text prompt to voice it. \n\nOptional parameters:\nChoose from one of the available voices (`tara`, `leah`, `jess`, `leo`, `dan`,`mia`, `zac`, `zoe`). Officially supported sound effects are: <laugh>, <chuckle>, <sigh>, <cough>, <sniffle>, <groan>, <yawn>, <gasp>, and <giggle>.", "owned_by": "fal", "root": "orpheus-tts", "architecture": {"input_modalities": ["text"], "output_modalities": ["audio"], "modality": "text->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Orpheus-TTS", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5874226-200-vccszdzxczobwzdvtdjhopgfydteomxu.jpeg", "alt": "Orpheus-TTS model icon", "width": 200, "height": 200}, "url": "https://poe.com/orpheus-tts"}, "reasoning": null, "parameters": [{"name": "voice", "schema": {"enum": ["tara", "leah", "jess", "leo", "dan", "mia", "zac", "zoe"]}, "default_value": "tara"}, {"name": "temperature", "schema": {"type": "number", "minimum": 0, "maximum": 2.0}, "default_value": 0.7, "description": "Temperature for generation. Higher temperature results in more creative or unusual outputs. Default: 0.7"}, {"name": "repetition_penalty", "schema": {"type": "number", "minimum": 1.1, "maximum": 2.0}, "default_value": 1.2, "description": "Required for stable outputs. Default: 1.2"}]}, {"id": "deepgram-nova-3", "object": "model", "created": 1753875390474, "description": "Transcribe audio files using Speech-to-Text technology with the Deepgram Nova-3 model, featuring multi-language support and advanced customizable settings.\n\n[1] Basic Features: \n- Generate PDF to generate a PDF file of the transcription. This is disabled by default \n- Diarize to identify different speakers in the audio. This will automatically enable utterances. This is disabled by default.\n- Smart format to set automatic format text for improved readability including punctuation and paragraphs. This feature is enabled by default.\n\n[2] Advanced Features:\n-Dictation to convert spoken commands for punctuation into their respective marks (e.g., 'period' becomes '.'). This will automatically enable punctuation. This is disabled by default.\n- Measurements to format spoken measurement units into abbreviations. This is disabled by default\n- Profanity filter to replace profanity with asterisks. This is disabled by default.\n- Redact PCI to redact payment card information. This is disabled by default.\n- Redact PII to redact personally identifiable information. This is disabled by default.\n- Utterances to segment speech into meaningful semantic units. This is disabled by default.\n- Paragraphs. This feature split audio into paragraphs to improve transcript readability. This will automatically enable punctuation. This is enabled by default.\n- Punctuate. This feature add punctuation and capitalization to your transcript. This is enabled by default.\n- Numerals. This feature convert numbers from written format to numerical format. This is enabled by default.\n\n[3] Languages Supported:\nAuto-detect (Default)\nEnglish\nSpanish\nFrench\nGerman\nItalian\nPortuguese\nJapanese\nChinese\nHindi\nRussian\nDutch\n\n[4] Key Terms. Enter important terms to improve recognition accuracy, separated by commas. English only, Limited to 500 tokens total.", "owned_by": "EmpirioLabs AI", "root": "deepgram-nova-3", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Deepgram-Nova-3", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6277257-200-asijdsoxwaghejcjphfjoaavxbcfhuqn.jpeg", "alt": "Deepgram-Nova-3 model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepgram-nova-3"}, "reasoning": null, "parameters": [{"name": "smart_format", "schema": {"type": "boolean"}, "default_value": true, "description": "Auto punctuation & paragraphs"}, {"name": "generate_pdf", "schema": {"type": "boolean"}, "default_value": false, "description": "Attach a PDF of the transcript"}, {"name": "diarize", "schema": {"type": "boolean"}, "default_value": false, "description": "Identify different speakers"}, {"name": "language", "schema": {"enum": ["auto", "en", "es", "fr", "de", "it", "pt", "ja", "zh", "hi", "ru", "nl"]}, "default_value": "auto", "description": "Select language (or auto-detect)"}, {"name": "keyterm", "schema": {"type": "string"}, "default_value": "", "description": "Comma-separated terms (English only, \u2264 500 tokens total)."}, {"name": "paragraphs", "schema": {"type": "boolean"}, "default_value": true, "description": "Split into paragraphs (enables punctuation)."}, {"name": "punctuate", "schema": {"type": "boolean"}, "default_value": true, "description": "Add punctuation and capitalization"}, {"name": "dictation", "schema": {"type": "boolean"}, "default_value": false, "description": "Convert spoken 'period', 'comma', etc. to marks (enables punctuation)."}, {"name": "utterances", "schema": {"type": "boolean"}, "default_value": false, "description": "Segment speech into semantic units"}, {"name": "profanity_filter", "schema": {"type": "boolean"}, "default_value": false, "description": "Replace profanity with asterisks"}, {"name": "redact_pii", "schema": {"type": "boolean"}, "default_value": false, "description": "Redact personally identifiable information"}, {"name": "redact_pci", "schema": {"type": "boolean"}, "default_value": false, "description": "Redact payment card information"}, {"name": "numerals", "schema": {"type": "boolean"}, "default_value": true, "description": "Convert written numbers to digits"}, {"name": "measurements", "schema": {"type": "boolean"}, "default_value": false, "description": "Format measurement units as abbreviations"}]}, {"id": "unreal-speech-tts", "object": "model", "created": 1741061137514, "description": "Convert chats, URLs, and documents into natural speech. 8 Languages: English, Japanese, Chinese, Spanish, French, Hindi, Italian, Portuguese. Defaults to Voice: Sierra. Full list below:\n\nAmerican English\n- Male: Noah, Jasper, Caleb, Ronan, Ethan, Daniel, Zane, Rowan\n- Female: Autumn, Melody, Hannah, Emily, Ivy, Kaitlyn, Luna, Willow, Lauren, Sierra\n\nBritish English\n- Male: Benjamin, Arthur, Edward, Oliver\n- Female: Eleanor, Chloe, Amelia, Charlotte\n\nJapanese\n- Male: Haruto\n- Female: Sakura, Hana, Yuki, Rina\n\nChinese\n- Male: Wei, Jian, Hao, Sheng\n- Female: Mei, Lian, Ting, Jing\n\nSpanish\n- Male: Mateo, Javier\n- Female: Luc\u00eda\n\nFrench\n- Female: \u00c9lodie\n\nHindi\n- Male: Arjun, Rohan\n- Female: Ananya, Priya\n\nItalian\n- Male: Luca\n- Female: Giulia\n\nPortuguese\n- Male: Thiago, Rafael\n- Female: Camila", "owned_by": "Unreal Speech", "root": "unreal-speech-tts", "architecture": {"input_modalities": ["text"], "output_modalities": ["audio"], "modality": "text->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Unreal-Speech-TTS", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5743650-200-emwzqdznhebykdhtexgihqvbgkzcdeuo.jpeg", "alt": "Unreal-Speech-TTS model icon", "width": 200, "height": 200}, "url": "https://poe.com/unreal-speech-tts"}, "reasoning": null, "parameters": [{"name": "voice", "schema": {"enum": ["Maddie", "Autumn", "Melody", "Hannah", "Emily", "Ivy", "Kaitlyn", "Luna", "Willow", "Lauren", "Sierra", "Noah", "Jasper", "Caleb", "Ronan", "Ethan", "Daniel", "Zane", "Rowan", "Eleanor", "Chloe", "Amelia", "Charlotte", "Benjamin", "Arthur", "Edward", "Oliver", "Luc\u00eda", "Mateo", "Javier", "Ananya", "Priya", "Arjun", "Rohan", "Giulia", "Luca", "Sakura", "Hana", "Yuki", "Rina", "Haruto", "Camila", "Thiago", "Rafael", "Mei", "Lian", "Ting", "Jing", "Wei", "Jian", "Hao", "Sheng", "Liv", "Dan", "Zoe", "Will", "Scarlett", "Amy"]}, "default_value": "Sierra"}]}, {"id": "flux-2-max", "object": "model", "created": 1765899203651, "description": "Flux.2 [Max] is Black Forest Labs' latest, state-of-the-art model with multi-reference support, fine-grained text rendering, and other features. \n\nNotes:\nSupports structured JSON prompts, and allows use of hex colour codes within the prompt for precise colouring.  \nSend images (Up to 8 images) in jpeg/png/webp format for editing.\n\nOptional parameters:\n- Set aspect ratio. Select from (16:9, 4:3, 1:1, 3:4, 9:16). It is set to 4:3 aspect ratio as default.", "owned_by": "fal", "root": "flux-2-max", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Flux-2-Max", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6674160-200-nahluexaarjryhwvwqkelnicasrfcnmd.jpeg", "alt": "Flux-2-Max model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-2-max"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "z-image-lightning", "object": "model", "created": 1765570829013, "description": "Super-fast endpoint for Z-Image Turbo, hosted by fal.ai. Excels at portrait photos and realistic images.\n\nNotes:\nBot does not accept attachment.\n\nOptional parameters:\n- Set aspect ratio. Select from (16:9, 4:3, 1:1, 3:4, 9:16). It is set to 4:3 aspect ratio as default.", "owned_by": "fal", "root": "z-image-lightning", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Z-Image-Lightning", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6664821-200-wsiwwsiliplfrxkzfjqwypzgeehhptrt.jpeg", "alt": "Z-Image-Lightning model icon", "width": 200, "height": 200}, "url": "https://poe.com/z-image-lightning"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "flux-2-klein-4b-base", "object": "model", "created": 1768504764220, "description": "Text-to-image generation and image editing with Flux 2 [klein] 4B Base from Black Forest Labs. Enhanced realism, crisper text rendering within images, and native editing capabilities. Send up to 3 images (jpeg/ png/ webp) to use for image editing or as references.\n\nOptional parameters:\n- Set aspect ratio. Select from (16:9, 4:3, 1:1, 3:4, 9:16). It is set to 4:3 aspect ratio as default.", "owned_by": "fal", "root": "flux-2-klein-4b-base", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Flux-2-Klein-4B-Base", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6740755-200-uribhodytggctacxhoxoihhvhvfiebgz.jpeg", "alt": "Flux-2-Klein-4B-Base model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-2-klein-4b-base"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "flux-2-klein-9b-base", "object": "model", "created": 1768505118417, "description": "Text-to-image generation and image editing with Flux 2 [klein] 9B Base from Black Forest Labs. Enhanced realism, crisper text rendering within images, and native editing capabilities. Send up to 3 images (jpeg/ png/ webp) to use for image editing or as references.\n\nOptional parameters:\n- Set aspect ratio. Select from (16:9, 4:3, 1:1, 3:4, 9:16). It is set to 4:3 aspect ratio as default.", "owned_by": "fal", "root": "flux-2-klein-9b-base", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Flux-2-Klein-9B-Base", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6740766-200-ldxkgfywkjgbmlgtantgacbwprrtfxfj.jpeg", "alt": "Flux-2-Klein-9B-Base model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-2-klein-9b-base"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "imagen-4-ultra", "object": "model", "created": 1748061401435, "description": "DeepMind's May 2025 text-to-image model with exceptional prompt adherence, capable of generating images with great detail, rich lighting, and few distracting artifacts. \n\nThis bot does not support attachments\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Google", "root": "imagen-4-ultra", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.042", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 480, "max_output_tokens": null}, "context_length": 480, "metadata": {"display_name": "Imagen-4-Ultra", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6051951-200-kajxaarpcccqrjwpuccejnyirnuabsqo.jpeg", "alt": "Imagen-4-Ultra model icon", "width": 200, "height": 200}, "url": "https://poe.com/imagen-4-ultra"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "1:1"}]}, {"id": "imagen-4-fast", "object": "model", "created": 1750875079224, "description": "DeepMind's June 2025 text-to-image model with exceptional prompt adherence, capable of generating images with great detail, rich lighting, and few distracting artifacts. \n\nOptional parameters:\nAspect ratio of your image (1:1, 16:9, 9:16, 4:3, 3:4). \n\nNotes:\nNon-English input will be translated first. Serves the `imagen-4.0-fast-generate-preview-06-06` model from Google Vertex, and has a maximum input of 480 tokens.", "owned_by": "Google", "root": "imagen-4-fast", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.014", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 480, "max_output_tokens": null}, "context_length": 480, "metadata": {"display_name": "Imagen-4-Fast", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6161330-200-ixuugkwgqalsgtmyfjrozmxvxtvlxymh.jpeg", "alt": "Imagen-4-Fast model icon", "width": 200, "height": 200}, "url": "https://poe.com/imagen-4-fast"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "1:1"}]}, {"id": "flux-2-klein-4b", "object": "model", "created": 1768504648686, "description": "Text-to-image generation and Image Editing with Flux 2 [klein] 4B Distilled from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities. Send up to 3 images (jpeg/png/webp) to use for image editing or as references.\n\nOptional parameters:\nSet aspect ratio. Supported aspect ratios - 16:9, 4:3, 1:1, 3:4, 9:16", "owned_by": "fal", "root": "flux-2-klein-4b", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Flux-2-Klein-4B", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6740749-200-zhilgrkcomfmnwmuotyznzghgqetqpgi.jpeg", "alt": "Flux-2-Klein-4B model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-2-klein-4b"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "imagen-4", "object": "model", "created": 1747888192720, "description": "DeepMind's May 2025 text-to-image model with exceptional prompt adherence, capable of generating images with great detail, rich lighting, and few distracting artifacts. \n\nNotes:\nNon-English input will be translated first. Serves the `imagen-4.0-ultra-generate-05-20` model from Google Vertex, and has a maximum input of 480 tokens.\n\nThis bot supports optional parameters for additional customization.\n\nThis bot does not support attachments.", "owned_by": "Google", "root": "imagen-4", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.028", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 480, "max_output_tokens": null}, "context_length": 480, "metadata": {"display_name": "Imagen-4", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6044586-200-uluqupbgabopbnidjatntcaijsdyprtu.jpeg", "alt": "Imagen-4 model icon", "width": 200, "height": 200}, "url": "https://poe.com/imagen-4"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "1:1"}]}, {"id": "phoenix-1.0", "object": "model", "created": 1748565176146, "description": "High-fidelity image generation with strong prompt adherence, especially for long and detailed instructions. Phoenix is capable of rendering coherent text in a wide variety of contexts. Prompt enhance is on to see the full power of a long, detailed prompt, but it can be turned off for full control. Uses the Phoenix 1.0 Fast model for performant, high-quality generations.\n\nParameters:\n- Aspect Ratio (1:1, 3:2, 2:3, 9:16, 16:9)\n- Prompt Enhance (Enable the prompt for better image generation)\n- Style (Please see parameter control to identify available styles)\n\nImage generation prompts can be a maximum of 1500 characters.", "owned_by": "Leonardo AI", "root": "phoenix-1.0", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.017", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Phoenix-1.0", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6072135-200-tsyhnxahnxvchfbmymgqpnhivqcqlyxa.jpeg", "alt": "Phoenix-1.0 model icon", "width": 200, "height": 200}, "url": "https://poe.com/phoenix-1.0"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["1:1", "2:3", "3:2", "16:9", "9:16"]}, "default_value": "1:1"}, {"name": "use_prompt_enhance", "schema": {"type": "boolean"}, "default_value": true, "description": "Enable this to enhance the prompt for better image generation."}, {"name": "style", "schema": {"enum": ["3d-render", "bokeh", "cinematic", "cinematic-concept", "creative", "dynamic", "fashion", "graphic-design-pop-art", "graphic-design-vector", "hdr", "illustration", "macro", "minimalist", "moody", "none", "portrait", "pro-bw-photography", "pro-color-photography", "pro-film-photography", "portrait-fashion", "ray-traced", "sketch-bw", "sketch-color", "stock-photo", "vibrant"]}, "default_value": "dynamic", "description": "Select a style for the image generation."}]}, {"id": "dreamina-3.1", "object": "model", "created": 1754503266312, "description": "ByteDance's Dreamina 3.1 Text-to-Image showcases superior picture effects, with significant improvements in picture aesthetics, precise and diverse styles, and rich details. This model excels with  large prompts, please use large prompts in case you face Content Checker issues.\nThe model does not accept attachment. \n\nOptional parameters:\nAspect ratio. Valid aspect ratios are 16:9, 4:3, 1:1, 3:4, & 9:16.", "owned_by": "Bytedance", "root": "dreamina-3.1", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Dreamina-3.1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6299923-200-nwlnhkhclmdecplrziotdaoqljlmstzd.jpeg", "alt": "Dreamina-3.1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/dreamina-3.1"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "qwen-image", "object": "model", "created": 1754383747239, "description": "Qwen-Image is an image generation foundation model in the Qwen series that achieves significant advances in complex text rendering. Experiments show strong general capabilities in image generation, with exceptional performance in text rendering, especially for Chinese. Prompt input cannot exceed 2,000 characters.", "owned_by": "Novita AI", "root": "qwen-image", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.020", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen-Image", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6295291-200-cqtayibdqnsvhrpwmgdnovxrbzrzvfyh.jpeg", "alt": "Qwen-Image model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen-image"}, "reasoning": null, "parameters": [{"name": "size", "schema": {"enum": ["512*512", "768*768", "1024*1024", "1280*1280", "1536*1536", "1024*768", "768*1024", "1280*720", "720*1280", "1536*1024", "1024*1536"]}, "default_value": "1024*1024", "description": "Size of the generated image (width \u00d7 height)"}]}, {"id": "qwen-image-20b", "object": "model", "created": 1754502513609, "description": "Qwen-Image (20B) is an image generation foundation model in the Qwen series that achieves significant advances in complex text rendering. \n\nOptional parameters:\nAspect ratio. Valid aspect ratios are 16:9, 4:3, 1:1, 3:4, 9:16. \nNegative_prompt to set the negative prompt.", "owned_by": "fal", "root": "qwen-image-20b", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen-Image-20B", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6299895-200-tlxddnihnecmzuxolxkwsuerrpfiaznp.jpeg", "alt": "Qwen-Image-20B model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen-image-20b"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "blur, low resolution, poor quality"}]}, {"id": "hunyuan-image-2.1", "object": "model", "created": 1757535106819, "description": "Hunyuan Image 2.1 is a high quality, highly efficient text-to-image model. Send a prompt to generate an image. \n\nOptional parameters:\nAspect Ratio (one of `16:9`, `4:3`, `1:1`, `3:4`, `9:16`) to set the aspect ratio of the generated image.\nNegative prompt (examples: blur, low resolution, poor quality) to set negative prompt on the image generated.\n\nNotes: This bot does not accept attachment.", "owned_by": "fal", "root": "hunyuan-image-2.1", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Hunyuan-Image-2.1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6406694-200-qywjrlyiflluodbumfgghpmxiflpcxod.jpeg", "alt": "Hunyuan-Image-2.1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/hunyuan-image-2.1"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "blur, low resolution, poor quality"}]}, {"id": "svi-2.0-pro", "object": "model", "created": 1767577823164, "description": "Stable Video Infinity 2.0 Pro, powered by WAN 2.2, generates seamlessly extending, theoretically infinite-length videos from still images while maintaining consistent character IDs. It uses advanced temporal coherence and generative scene expansion to maintain visual consistency, allowing endless, smooth motion and evolving visuals without looping or abrupt transitions.\n\nThis model is hosted by EmpirioLabs.ai and is exclusive to the Poe platform.\n\nLearn more: https://stable-video-infinity.github.io/homepage/\n\nNotes: \n- Generations may take upwards of 45 minutes depending on the selected length.\n- If you are experiencing issues with slow motion, try adjusting the prompt to describe more consecutive motion per segment (ex. A knight stands in the rain, water dripping from his helmet as he clenches his fist, looks up toward the castle gates, takes a steadying breath, then turns and marches forward.).\n- Image-to-Video generations will likely yield superior results.\n- Supported image upload file types: .jpg, .jpeg, .png, .webp, .heic, .heif, .bmp, .tiff, .tif\n\nParameter controls available:\n1. Video Settings\n- Resolution. [832x480, 480x832, 720x1280, 1280x720]: Controls output dimensions (Default: 832x480)\n- Duration [18-121.5]: Estimated video length in seconds (Step 4.5)\n  - For 480p: Max 121.5s\n  - For 720p: Max 40.5s\n\n2. Advanced\n- Cfg [1.0-2.0]: Prompt adherence strength (Default: 1.0)\n- Negative prompt [text]`: Standard negative prompt included by default (e.g. \"vibrant tone, overexposed...\")\n\n3. Text-to-Video Settings\n- t2v quality [fast or quality]: Generation mode for text-to-video (Default: quality)", "owned_by": "EmpirioLabs AI", "root": "svi-2.0-pro", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "SVI-2.0-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6715628-200-zhtnfedmdjarymxeomlfkfgxlhovvljx.jpeg", "alt": "SVI-2.0-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/svi-2.0-pro"}, "reasoning": null, "parameters": [{"name": "resolution", "schema": {"enum": ["832x480", "480x832", "720x1280", "1280x720"]}, "default_value": "832x480"}, {"name": "duration", "schema": {"type": "number", "minimum": 18, "maximum": 40.5}, "default_value": 18, "description": "Estimated video length (max 40.5s for 720p)."}, {"name": "cfg", "schema": {"type": "number", "minimum": 1.0, "maximum": 2.0}, "default_value": 1.0, "description": "Prompt adherence strength."}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "vibrant tone, overexposed, static, blurry details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, still picture, messy background, three legs, background crowd, walking backwards"}, {"name": "t2v_quality", "schema": {"enum": ["fast", "quality"]}, "default_value": "quality", "description": "Generation mode (only applies when no image is uploaded)."}]}, {"id": "hunyuan-video-1.5", "object": "model", "created": 1765145930507, "description": "HunyuanVideo 1.5 is a 8.3B-parameter video generation model from Tencent that delivers high-quality, smooth text-to-video and image-to-video outputs. It supports native 720p (upscalable to 1080p) videos with strong motion coherence, detailed visuals, and robust bilingual prompt understanding and accurate in-video text rendering.\n\nThis model is hosted by EmpirioLabs.ai and is the only endpoint that supports 1080p upscaling alongside generations up to 10s and fully customizable aspect ratios. This is exclusive to the Poe platform.\n\nSupported file type uploads (for image-to-video): .jpg, .jpeg, .png, .webp, .heic, .heif, .bmp, .tiff, .tif\nNote: 1080p is limited to 5s generations.\n\nParameter controls available:\n1. Basic\n- Default: text-to-video (no mode needed)\n- If transforming uploaded image: image-to-video (auto-detected via attachment)\n- Resolution [480p, 720p, 1080p] (Default: 480p)\n- Aspect ratio [16:9, 4:3, 1:1, 9:16, 3:4] (Default: 16:9)\n\n2. Timing and Randomness\n- Duration [1-10 seconds] controls how long generated video is (Default: 5, 1080p limited to 5s)\n- Seed [integer] disables random seed generation\n\n3. Advanced\n- Cfg scale [1-20]: Higher = closer to prompt (Default: 6.0)\n- Steps [10-50]: Higher = better quality (Default: 25)\n- Negative prompt [text]`: Content to avoid", "owned_by": "EmpirioLabs AI", "root": "hunyuan-video-1.5", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Hunyuan-Video-1.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6650642-200-ilnnrwqdbcjjlktcxdwclqprxbfdejyh.jpeg", "alt": "Hunyuan-Video-1.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/hunyuan-video-1.5"}, "reasoning": null, "parameters": [{"name": "resolution", "schema": {"enum": ["480p", "720p", "1080p"]}, "default_value": "480p", "description": "Video quality. Higher resolution takes longer."}, {"name": "duration", "schema": {"type": "number", "minimum": 1, "maximum": 5}, "default_value": 5, "description": "Video length in seconds (Max 5s for 1080p)."}, {"name": "aspect_ratio", "schema": {"enum": ["16:9", "4:3", "1:1", "9:16", "3:4"]}, "default_value": "16:9", "description": "Video dimensions."}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "", "description": "Content to avoid."}, {"name": "cfg_scale", "schema": {"type": "number", "minimum": 1.0, "maximum": 20.0}, "default_value": 6.0, "description": "Prompt adherence strength."}, {"name": "steps", "schema": {"type": "number", "minimum": 10, "maximum": 50}, "default_value": 25, "description": "Denoising iterations."}, {"name": "seed", "schema": {"type": "string"}, "default_value": "", "description": "For reproducible results."}]}, {"id": "flux-2-flash", "object": "model", "created": 1767812649468, "description": "Superfast Open-weight image gen (at 32B parameters) model, derived from the FLUX.2 base model. Send up to 3 images (jpeg/png/webp) to use for image editing/ as references.\n\nOptional parameters:\nSet aspect ratio: 16:9, 4:3, 1:1, 3:4, 9:16", "owned_by": "fal", "root": "flux-2-flash", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Flux-2-Flash", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6722499-200-ywrdvxtwfnvagaapzhxsrzjcozknbjbd.jpeg", "alt": "Flux-2-Flash model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-2-flash"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "flux-2-turbo", "object": "model", "created": 1767812200237, "description": "Fast, open-weight image generation model (32B parameters), derived from the FLUX.2 base model. Send up to 3 images (jpeg/ png/ webp) to use for image editing or as references.\n\nOptional parameters:\nSet aspect ratio: 16:9, 4:3, 1:1, 3:4, 9:16", "owned_by": "fal", "root": "flux-2-turbo", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": {"context_length": 256, "max_output_tokens": null}, "context_length": 256, "metadata": {"display_name": "Flux-2-Turbo", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6722483-200-womrguyyqmigycdaauyvujwijaiimuew.jpeg", "alt": "Flux-2-Turbo model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-2-turbo"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "flux-kontext-max", "object": "model", "created": 1748526727201, "description": "FLUX.1 Kontext [max] is a new premium model from Black Forest Labs that brings maximum performance across all aspects. Send a prompt to generate an image, or send an image along with an instruction to edit the image.  \n\nOptional parameters:\nSet the aspect ratio for text-to-image-generation. Available aspect ratio (21:9, 16:9, 4:3, 1:1, 3:4, 9:16, & 9:21)", "owned_by": "fal", "root": "flux-kontext-max", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Flux-Kontext-Max", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6070808-200-oszgrnhurnzlwgktgibuwqohvkgtymuv.jpeg", "alt": "Flux-Kontext-Max model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-kontext-max"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "9:21"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "flux-kontext-pro", "object": "model", "created": 1748527242279, "description": "The FLUX.1 Kontext [pro] model delivers state-of-the-art image generation results with unprecedented prompt following, photorealistic rendering, flawless typography, and image editing capabilities. Send a prompt to generate an image, or send an image along with an instruction to edit the image. \n\nOptional parameters:\nSet the aspect ratio for text-to-image-generation. Available aspect ratio (21:9, 16:9, 4:3, 1:1, 3:4, 9:16, & 9:21)", "owned_by": "fal", "root": "flux-kontext-pro", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Flux-Kontext-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6070828-200-dwbqeaiqasaxnpgxvcpxdumhunivnyos.jpeg", "alt": "Flux-Kontext-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-kontext-pro"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "9:21"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "flux-krea", "object": "model", "created": 1753991501514, "description": "FLUX-Krea is a version of FLUX Dev tuned for superior aesthetics. \n\nOptional parameters:\nSelect an aspect ratio. Valid aspect ratios are 16:9, 4:3, 1:1, 3:4, 9:16.  Send an image to have this model reimagine/regenerate it via FLUX Krea Redux.", "owned_by": "fal", "root": "flux-krea", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "FLUX-Krea", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6281988-200-kfdumrvpwzjlihwsdpaexvmqysxdblks.jpeg", "alt": "FLUX-Krea model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-krea"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "imagen-3", "object": "model", "created": 1729023417016, "description": "Google DeepMind's highest quality text-to-image model, capable of generating images with great detail, rich lighting, and few distracting artifacts. \n\nOptional parameters:\nAspect ratio of your image (1:1, 16:9, 9:16, 4:3, 3:4). \n\nNotes: \nFor simpler prompts, faster results, & lower cost, use @Imagen3-Fast. Non english input will be translated first. Image prompt cannot exceed 480 tokens.", "owned_by": "Google", "root": "imagen-3", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.028", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 480, "max_output_tokens": null}, "context_length": 480, "metadata": {"display_name": "Imagen-3", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5106005-200-wpmztuegafrvrufgngtiotbxqexopmzp.jpeg", "alt": "Imagen-3 model icon", "width": 200, "height": 200}, "url": "https://poe.com/imagen-3"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "1:1"}]}, {"id": "wan-animate", "object": "model", "created": 1758552514026, "description": "Wan Animate takes in an image and a video to generate another video where a character in the image replaces a character in the video(default), or the video character's motion is used to animate the character in the image. Pass --animate for the second functionality.\nThe bot supports only four file types: JPEG, PNG, WebP, and MP4", "owned_by": "fal", "root": "wan-animate", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Wan-Animate", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6441476-200-otgldkisvndyfwicdnofpgzmliembygs.jpeg", "alt": "Wan-Animate model icon", "width": 200, "height": 200}, "url": "https://poe.com/wan-animate"}, "reasoning": null, "parameters": []}, {"id": "imagen-3-fast", "object": "model", "created": 1729127959259, "description": "Google DeepMind's highest quality text-to-image model, capable of generating images with great detail, rich lighting, and few distracting artifacts \u2014 optimized for short, simple prompts. \n\nOptional parameters:\nAspect ratio of your image (1:1, 16:9, 9:16, 4:3, 3:4). \n\nNotes: For more complex prompts, use @Imagen3. Non english input will be translated first. Image prompt cannot exceed 480 tokens.", "owned_by": "Google", "root": "imagen-3-fast", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.014", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 480, "max_output_tokens": null}, "context_length": 480, "metadata": {"display_name": "Imagen-3-Fast", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5112905-200-skoookakopnfvrutwrsysgnyagqxlrdw.jpeg", "alt": "Imagen-3-Fast model icon", "width": 200, "height": 200}, "url": "https://poe.com/imagen-3-fast"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "1:1"}, {"name": "no", "schema": {"type": "string"}}]}, {"id": "seedream-3.0", "object": "model", "created": 1750007407012, "description": "Seedream 3.0 by ByteDance is a bilingual (Chinese and English) text-to-image model that excels at text-to-image generation.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Bytedance", "root": "seedream-3.0", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Seedream-3.0", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6128545-200-rochnmkrsybmgzrthbcnzzebcerxhpcb.jpeg", "alt": "Seedream-3.0 model icon", "width": 200, "height": 200}, "url": "https://poe.com/seedream-3.0"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "seedance-1.0-pro", "object": "model", "created": 1750447821693, "description": "Seedance is a video generation model with text-to-video and image-to-video capabilities. It achieves breakthroughs in semantic understanding and prompt following. \n\nOptional parameters:\nAspect ratio (available values: `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`). \nResolution (one of `480p`,`720p`,`1080p` to set the video resolution. \nDuration` (3 to 12) sets the video duration.\n\nNotes: Number of video tokens calculated for pricing is approximately: `height * width * fps * duration / 1024).", "owned_by": "Bytedance", "root": "seedance-1.0-pro", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Seedance-1.0-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6146876-200-cnxsrvblegwxiuvicaabacuchswmtexp.jpeg", "alt": "Seedance-1.0-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/seedance-1.0-pro"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["21:9", "16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "16:9"}, {"name": "resolution", "schema": {"enum": ["480p", "720p", "1080p"]}, "default_value": "1080p"}, {"name": "duration", "schema": {"enum": ["3", "4", "5", "6", "7", "8", "9", "10", "11", "12"]}, "default_value": "5", "description": "Video duration in seconds"}]}, {"id": "seedance-1.0-lite", "object": "model", "created": 1750007728801, "description": "Seedance is a video generation model with text-to-video and image-to-video capabilities. It achieves breakthroughs in semantic understanding and prompt following. \n\nOptional paremeters:\nAspect ratio (available values:`21:9`, `16:9`, `4:3`, `1:1`, `3:4` and `9:16`). \nResolution (one of `480p`, `720p` and `1080p` to set the video resolution. \nDuration (3 to 12) sets the video duration. \n\nNotes: Number of video tokens calculated for pricing is approximately: `height * width * fps * duration / 1024).", "owned_by": "Bytedance", "root": "seedance-1.0-lite", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Seedance-1.0-Lite", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6128556-200-bewqvpqnxoekszklggunkqbytlncaxpe.jpeg", "alt": "Seedance-1.0-Lite model icon", "width": 200, "height": 200}, "url": "https://poe.com/seedance-1.0-lite"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["21:9", "16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "16:9"}, {"name": "resolution", "schema": {"enum": ["480p", "720p", "1080p"]}, "default_value": "720p"}, {"name": "duration", "schema": {"enum": ["3", "4", "5", "6", "7", "8", "9", "10", "11", "12"]}, "default_value": "5", "description": "Video duration in seconds"}]}, {"id": "ideogram-v3", "object": "model", "created": 1746189583927, "description": "Generate high-quality images, posters, and logos with Ideogram V3. Features exceptional typography handling and realistic outputs optimized for commercial and creative use. \n\nNote:\nSend one image with a prompt for image remixing/restyling. \nSend two images (one an image and the other a black-and-white mask image denoting an area) for image editing.\n\nOptional parameters:\nSet aspect ratio. Select from (5:4, 4:3, 4:5, 1:1, 1:2, 1:3, 3:4, 3:1, 3:2, 2:1, 2:3, 16:9, 16:10, 10:16, 9:16). It is set to 4:3 aspect ratio as default.\nSet style. Select the desired style preset. No style set as default.", "owned_by": "fal", "root": "ideogram-v3", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Ideogram-v3", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5979108-200-ndsbcxtuzoxgqovckthnzhenhbhlqfos.jpeg", "alt": "Ideogram-v3 model icon", "width": 200, "height": 200}, "url": "https://poe.com/ideogram-v3"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["1:3", "3:1", "1:2", "2:1", "9:16", "16:9", "10:16", "16:10", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "1:1"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}, {"name": "style_preset", "schema": {"enum": ["NONE", "80S_ILLUSTRATION", "90S_NOSTALGIA", "ABSTRACT_ORGANIC", "ANALOG_NOSTALGIA", "ART_BRUT", "ART_DECO", "ART_POSTER", "AURA", "AVANT_GARDE", "BAUHAUS", "BLUEPRINT", "BLURRY_MOTION", "BRIGHT_ART", "C4D_CARTOON", "CHILDRENS_BOOK", "COLLAGE", "COLORING_BOOK_I", "COLORING_BOOK_II", "CUBISM", "DARK_AURA", "DOODLE", "DOUBLE_EXPOSURE", "DRAMATIC_CINEMA", "EDITORIAL", "EMOTIONAL_MINIMAL", "ETHEREAL_PARTY", "EXPIRED_FILM", "FLAT_ART", "FLAT_VECTOR", "FOREST_REVERIE", "GEO_MINIMALIST", "GLASS_PRISM", "GOLDEN_HOUR", "GRAFFITI_I", "GRAFFITI_II", "HALFTONE_PRINT", "HIGH_CONTRAST", "HIPPIE_ERA", "ICONIC", "JAPANDI_FUSION", "JAZZY", "LONG_EXPOSURE", "MAGAZINE_EDITORIAL", "MINIMAL_ILLUSTRATION", "MIXED_MEDIA", "MONOCHROME", "NIGHTLIFE", "OIL_PAINTING", "OLD_CARTOONS", "PAINT_GESTURE", "POP_ART", "RETRO_ETCHING", "RIVIERA_POP", "SPOTLIGHT_80S", "STYLIZED_RED", "SURREAL_COLLAGE", "TRAVEL_POSTER", "VINTAGE_GEO", "VINTAGE_POSTER", "WATERCOLOR", "WEIRD", "WOODBLOCK_PRINT"]}, "default_value": "NONE", "description": "Select the desired style preset. The default is `NONE`"}]}, {"id": "ideogram-v2", "object": "model", "created": 1724273571743, "description": "Latest image model from Ideogram, with industry leading capabilities in generating realistic images, graphic design, typography, and more.\n\nOptional parameters:\nSet aspect ratio. Select from (10:16, 16:10, 9:16, 16:9, 3:2, 2:3, 4:3, 3:4, 1:1). It is set to 1:1 aspect ratio as default.\nSet style. Select from General, Realistic, Design, Render 3D, Anime. This is set to General by default.\n\nNotes: Supported file type: JPEG, WebP and PNG. Powered by Ideogram.", "owned_by": "IdeogramAI", "root": "ideogram-v2", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.058", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 150, "max_output_tokens": null}, "context_length": 150, "metadata": {"display_name": "Ideogram-v2", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-4801915-200-bgsrbuzxoqiqlkqbwdenztdyjszjlkgi.jpeg", "alt": "Ideogram-v2 model icon", "width": 200, "height": 200}, "url": "https://poe.com/ideogram-v2"}, "reasoning": null, "parameters": [{"name": "style", "schema": {"enum": ["GENERAL", "REALISTIC", "DESIGN", "RENDER_3D", "ANIME"]}, "default_value": "GENERAL"}, {"name": "aspect", "schema": {"enum": ["16:9", "16:10", "3:2", "4:3", "1:1", "9:16", "10:16", "2:3", "3:4"]}, "default_value": "1:1"}]}, {"id": "flux-dev-di", "object": "model", "created": 1750507284607, "description": "High quality image generator using FLUX dev model. Top of the line prompt following, visual quality and output diversity. This model is a text to image generation only and does not accept attachments. To further customize the prompt, you can follow the parameters available:\n\nSet width. Valid pixel options from 128 up to 1920. Default value: 1024\nSet height. Valid pixel options from 128, up to 1920. Default value: 1024\nSet seed for reproducible result. Options from 1 up to 2**32. Default value: random\nSet inference.  Options from 1 up to 50. Default: 25", "owned_by": "DeepInfra", "root": "flux-dev-di", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0050", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "FLUX-dev-DI", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6148905-200-gabasfamivjbdobyozmzsyhlgkzkdpvo.jpeg", "alt": "FLUX-dev-DI model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-dev-di"}, "reasoning": null, "parameters": [{"name": "width", "schema": {"type": "number", "minimum": 128, "maximum": 1920}, "default_value": 1024, "description": "Image width in pixels"}, {"name": "height", "schema": {"type": "number", "minimum": 128, "maximum": 1920}, "default_value": 1024, "description": "Image height in pixels"}, {"name": "num_inference_steps", "schema": {"type": "number", "minimum": 1, "maximum": 50}, "default_value": 25, "description": "Number of denoising steps"}, {"name": "seed", "schema": {"type": "string"}, "default_value": "", "description": "Random seed for reproducible results (leave empty for random)"}]}, {"id": "flux-schnell-di", "object": "model", "created": 1750333477944, "description": "This is the fastest version of FLUX, featuring highly optimized abstract models that excel at creative and unconventional renders. To further customize the prompt, you can follow the parameters available:\n\nTo set width, use \"--width\". Valid pixel options from 128 up to 1920. Default value: 1024\nTo set height, use \"--height\". Valid pixel options from 128, up to 1920. Default value: 1024\nTo set seed, use \"--seed\" for reproducible result. Options from 1 up to 2**32. Default value: random\nTo set inference, use \"--num_inference_steps\". Options from 1 up to 50. Default: 1", "owned_by": "DeepInfra", "root": "flux-schnell-di", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0010", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 256, "max_output_tokens": null}, "context_length": 256, "metadata": {"display_name": "FLUX-schnell-DI", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6142465-200-lnhjwdslbtqrldffzwhdeekzpfrxjzac.jpeg", "alt": "FLUX-schnell-DI model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-schnell-di"}, "reasoning": null, "parameters": [{"name": "width", "schema": {"type": "number", "minimum": 128, "maximum": 1920}, "default_value": 1024, "description": "Image width in pixels"}, {"name": "height", "schema": {"type": "number", "minimum": 128, "maximum": 1920}, "default_value": 1024, "description": "Image height in pixels"}, {"name": "num_inference_steps", "schema": {"type": "number", "minimum": 1, "maximum": 50}, "default_value": 1, "description": "Number of denoising steps"}, {"name": "seed", "schema": {"type": "string"}, "default_value": "", "description": "Random seed for reproducible results (leave empty for random)"}]}, {"id": "flux-pro-1.1", "object": "model", "created": 1727968438767, "description": "State-of-the-art image generation with top-of-the-line prompt following, visual quality, image detail and output diversity. This is the most powerful version of FLUX 1.1. \n\nOptional parameters:\nSet aspect ratio. Select from (16:9, 4:3, 1:1, 3:4, 9:16). It is set to 1:1 aspect ratio as default.\n\nNotes:\nSend an image (jpeg/png/webp/heic/heif) to have this model reimagine/regenerate it via FLUX Redux.", "owned_by": "fal", "root": "flux-pro-1.1", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": {"context_length": 256, "max_output_tokens": null}, "context_length": 256, "metadata": {"display_name": "FLUX-pro-1.1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5038493-200-kaqjjvliljatttdmmgeqyflyvlevubcb.jpeg", "alt": "FLUX-pro-1.1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-pro-1.1"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "luma-photon-flash", "object": "model", "created": 1733181412355, "description": "Luma Photon delivers industry-specific visual excellence, crafting images that align perfectly with professional standards - not just generic AI art. From marketing to creative design, each generation is purposefully tailored to your industry's unique requirements. \n\nOptional parameters:\nAspect to the end of your prompts to change the aspect ratio of your generations (1:1, 16:9, 9:16, 4:3, 3:4, 21:9, 9:21 are supported). \n\nNote: Prompt input cannot exceed 5,000 characters.", "owned_by": "fal", "root": "luma-photon-flash", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Luma-Photon-Flash", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5360375-200-ivlhpgvrpoepbbnjxcyiihqkykzpygtf.jpeg", "alt": "Luma-Photon-Flash model icon", "width": 200, "height": 200}, "url": "https://poe.com/luma-photon-flash"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "9:21"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "hidream-i1-full", "object": "model", "created": 1747144375790, "description": "Hidream-I1 is a state-of-the-art text to image model by Hidream. \n\nOptional parameters:\nAspect ratio. Valid aspect ratios are 16:9, 4:3, 1:1, 3:4, 9:16. \nNegative prompt to set the negative prompt.", "owned_by": "fal", "root": "hidream-i1-full", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Hidream-I1-full", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6015164-200-zxzpejkuueefgnuumxpzalmlyvjduyei.jpeg", "alt": "Hidream-I1-full model icon", "width": 200, "height": 200}, "url": "https://poe.com/hidream-i1-full"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "blur, low resolution, poor quality"}]}, {"id": "retro-diffusion-core", "object": "model", "created": 1742484693553, "description": "Generate true game ready pixel art in seconds at any resolution between 16x16 and 512x512 across the various styles. Create 48x48 walking animations of sprites using the \"animation_four_angle_walking\" style! First 50 basic image requests worth of points free! Check out more settings below \ud83d\udc47\n\n\nExample message: \"A cute corgi wearing sunglasses and a party hat\"\n\nSettings:\n- Set AR: Image size in pixels, larger images cost more. Or aspect ratio like 16:9\n- Set style: The name of the style you want to use. Available styles: rd_fast__anime, rd_fast__retro, rd_fast__simple, rd_fast__detailed, rd_fast__game_asset, rd_fast__portrait, rd_fast__texture, rd_fast__ui, rd_fast__item_sheet, rd_fast__mc_texture, rd_fast__mc_item, rd_fast__character_turnaround, rd_fast__1_bit, animation__four_angle_walking, rd_plus__default, rd_plus__retro, rd_plus__watercolor, rd_plus__textured, rd_plus__cartoon, rd_plus__ui_element, rd_plus__item_sheet, rd_plus__character_turnaround, rd_plus__isometric, rd_plus__isometric_asset, rd_plus__topdown_map, rd_plus__top_down_asset\n- Seed. Random number, keep the same for consistent generations\n- Tile. Creates seamless edges on applicable images\n- Tile X. Seamless horizontally only\n- Tile Y. Seamless vertically only\n- Native. Returns pixel art at native resolution, without upscaling\n- Remove background. Automatically remove the background\n- Strength. Controls how strong the image generation is. 0.0 for small changes, 1.0 for big changes\n\nAdditional notes: All styles have a size range of 48x48 -> 512x512, except for the \"mc\" styles, which have a size range of 16x16 -> 128x128, and the \"animation_four_angle_walking\" style, which will only create 48x48 animations.", "owned_by": "Retro Diffusion", "root": "retro-diffusion-core", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Retro-Diffusion-Core", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5816908-200-xuhygnuelshvlcwvnypvblbbiibicfwz.jpeg", "alt": "Retro-Diffusion-Core model icon", "width": 200, "height": 200}, "url": "https://poe.com/retro-diffusion-core"}, "reasoning": null, "parameters": [{"name": "style", "schema": {"enum": ["animation__four_angle_walking", "animation__vfx", "default", "retro", "simple", "detailed", "anime", "game_asset", "portrait", "texture", "ui", "item_sheet", "mc_texture", "mc_item", "character_turnaround", "1_bit", "rd_fast__low_res", "no_style", "rd_plus__default", "rd_plus__retro", "rd_plus__watercolor", "rd_plus__textured", "rd_plus__cartoon", "rd_plus__ui_element", "rd_plus__item_sheet", "rd_plus__character_turnaround", "rd_plus__topdown_map", "rd_plus__topdown_asset", "rd_plus__isometric", "rd_plus__isometric_asset", "rd_plus__low_res", "rd_plus__mc_item", "rd_plus__mc_texture", "rd_plus__classic"]}, "default_value": "default"}, {"name": "seed", "schema": {"type": "string"}}, {"name": "width", "schema": {"type": "string"}, "default_value": "256"}, {"name": "height", "schema": {"type": "string"}, "default_value": "256"}, {"name": "tilex", "schema": {"type": "boolean"}}, {"name": "tiley", "schema": {"type": "boolean"}}, {"name": "iw", "schema": {"type": "number", "minimum": 0.1, "maximum": 1}, "default_value": 0.8}, {"name": "native", "schema": {"type": "boolean"}}, {"name": "removebg", "schema": {"type": "boolean"}}, {"name": "edit", "schema": {"type": "boolean"}, "description": "Edit images using instructions"}]}, {"id": "stablediffusion3.5-l", "object": "model", "created": 1729613306476, "description": "Stability.ai's StableDiffusion3.5 Large, hosted by @fal, is the Stable Diffusion family's most powerful image generation model both in terms of image quality and prompt adherence. \n\nOptional parameters:\nAspect to select an aspect ratio. Valid aspect ratios are 16:9, 4:3, 1:1, 3:4, 9:16.", "owned_by": "fal", "root": "stablediffusion3.5-l", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "StableDiffusion3.5-L", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5142246-200-vtsjthjjkbctjmqubwfbckzlywzttuat.jpeg", "alt": "StableDiffusion3.5-L model icon", "width": 200, "height": 200}, "url": "https://poe.com/stablediffusion3.5-l"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "glm-4.7-fw", "object": "model", "created": 1766458152288, "description": "GLM-4.7 is a next-generation general-purpose model optimized for coding, reasoning, and agentic workflows, delivering strong gains in multilingual software engineering, tool use, and complex problem solving. It introduces advanced thinking controls\u2014interleaved, preserved, and turn-level thinking\u2014to improve stability on long-horizon, multi-turn tasks. Supported context length: 198k tokens. More information: https://app.fireworks.ai/models/fireworks/glm-4p7\n\nSupported file format: jpg, jpeg, png, heic, pdf, python, xlsx\n", "owned_by": "Fireworks AI", "root": "glm-4.7-fw", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0061", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "GLM-4.7-FW", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6689310-200-ecptbivmxmilucwvimwtysnsnwbrmuxv.jpeg", "alt": "GLM-4.7-FW model icon", "width": 200, "height": 200}, "url": "https://poe.com/glm-4.7-fw"}, "reasoning": null, "parameters": []}, {"id": "flux-schnell", "object": "model", "created": 1722523149211, "description": "Turbo speed image generation with strengths in prompt following, visual quality, image detail and output diversity. This is the fastest version of FLUX.1. \n\nOptional parameters:\nSet aspect ratio. Valid aspect ratios are 16:9, 4:3, 1:1, 3:4, 9:16. \n\nNote: Send an image to have this model reimagine/regenerate it via FLUX Redux.", "owned_by": "fal", "root": "flux-schnell", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": {"context_length": 256, "max_output_tokens": null}, "context_length": 256, "metadata": {"display_name": "FLUX-schnell", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-4692053-200-dqazarvqsjcnksmiaxwnfzwsrwivvchr.jpeg", "alt": "FLUX-schnell model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-schnell"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "gpt-image-1", "object": "model", "created": 1743434309185, "description": "OpenAI's model that powers image generation in ChatGPT, offering exceptional prompt adherence, level of detail, and quality. It supports editing, restyling, and combining images attached to the latest user query. For a conversational editing experience, use https://poe.com/GPT-4o (all users) or https://poe.com/Assistant (subscribers) instead.\n\nOptional parameters:\n- Aspect Ration. Aspect ratio of the output image (Options: 1:1, 3:2, 2:3)\n- Quality: Image resolution (options: high, medium, low)\n- Mask.  Indicates that the last attached image is a mask for in-painting (editing specific regions). The mask must match the dimensions of the base image, with transparent (zero-alpha) areas showing which parts to edit.\n- High fidelity to false to disable high input fidelity. This option is enabled by default.", "owned_by": "OpenAI", "root": "gpt-image-1", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": ["/v1/images"], "pricing": null, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "GPT-Image-1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5860961-200-lqgunndzxoajcyjfnmyuctxudtanfivt.jpeg", "alt": "GPT-Image-1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-image-1"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["1:1", "3:2", "2:3"]}}, {"name": "quality", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "high"}, {"name": "use_mask", "schema": {"type": "boolean"}, "default_value": false, "description": "Indicates that the last attached image is a mask for inpainting (editing specific regions). The mask must match the dimensions of the base image, with transparent (zero-alpha) areas showing which parts to edit."}, {"name": "use_high_fidelity", "schema": {"type": "boolean"}, "default_value": true, "description": "High input fidelity allows you to make subtle edits to an image without altering unrelated areas. This is ideal for controlled, localized changes."}]}, {"id": "gpt-image-1-mini", "object": "model", "created": 1756235580926, "description": "OpenAI's model that powers image generation in ChatGPT, offering exceptional prompt adherence, level of detail, and quality. It supports editing, restyling, and combining images attached to the latest user query. \n\nOptional parameters:\n- Aspect ratio of the output image (options: 1:1, 3:2, 2:3). \n- Quality. Image resolution (options: high, medium, low).\n- Mask. Indicates that the last attached image is a mask for in-painting (editing specific regions). The mask must match the dimensions of the base image, with transparent (zero-alpha) areas showing which parts to edit.", "owned_by": "OpenAI", "root": "gpt-image-1-mini", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "GPT-Image-1-Mini", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6362921-200-qeyxhoaryufggsvpjxbhseajfbhyryia.jpeg", "alt": "GPT-Image-1-Mini model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-image-1-mini"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["1:1", "3:2", "2:3"]}}, {"name": "quality", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "high"}, {"name": "use_mask", "schema": {"type": "boolean"}, "default_value": false, "description": "Indicates that the last attached image is a mask for inpainting (editing specific regions). The mask must match the dimensions of the base image, with transparent (zero-alpha) areas showing which parts to edit."}]}, {"id": "veo-3.1", "object": "model", "created": 1760537766690, "description": "Google\u2019s Veo 3.1 is an updated version of the Veo family of models that features richer native audio, from natural conversations to synchronized sound effects, and offers greater narrative control with an improved understanding of cinematic styles. Enhanced image-to-video capabilities ensure better prompt adherence while delivering superior audio and visual quality and maintaining character consistency across multiple scenes.\n\nOptional parameters:\n- Set the aspect ratio (either `16:9` or `9:16`), which defaults to `16:9`\n- Negative prompt can be set on elements to avoid\n- Set the duration (one of `4s`, `6s`, or `8s`), which defaults to `8s`\n- Seed to set the seed (set number value)\n- Resolution (set from 720p or 1080p)\n- Reference mode. Toggle to use input images (3 max) as reference for video generation\n\nFor first & last frame video generation and references support, please use www.poe.com/Veo-v3.1", "owned_by": "Google", "root": "veo-3.1", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": ["/v1/videos"], "pricing": null, "context_window": {"context_length": 480, "max_output_tokens": null}, "context_length": 480, "metadata": {"display_name": "Veo-3.1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6501423-200-ulpnllwaaaonkxsedbljuanxokvwknwz.jpeg", "alt": "Veo-3.1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/veo-3.1"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["16:9", "9:16"]}, "default_value": "16:9"}, {"name": "no", "schema": {"type": "string"}}, {"name": "duration", "schema": {"enum": ["4", "6", "8"]}, "default_value": "8"}, {"name": "seed", "schema": {"type": "string"}}, {"name": "silent", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to generate a video without audio. Decreases cost."}, {"name": "reference_mode", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to use input images(3 max) as reference for video generation."}, {"name": "resolution", "schema": {"enum": ["720p", "1080p"]}, "default_value": "720p"}]}, {"id": "veo-3.1-fast", "object": "model", "created": 1760540647924, "description": "Google\u2019s Veo 3.1 Fast is an updated version of the Veo family of models that's optimized for speed and cost, but still features richer native audio, from natural conversations to synchronized sound effects, and offer greater narrative control with an improved understanding of cinematic styles. Enhanced image-to-video capabilities ensure better prompt adherence while delivering superior audio and visual quality and maintaining character consistency across multiple scenes.\n\nOptional parameters:\n- Set the aspect ratio (either `16:9` or `9:16`), which defaults to `16:9`\n- Negative prompt can be set on elements to avoid\n- Set the duration (one of `4s`, `6s`, or `8s`), which defaults to `8s`\n- Seed to set the seed (set number value)\n- Resolution (set from 720p or 1080p)\n\nFor first & last frame video generation support, please use www.poe.com/Veo-v3.1-Fast", "owned_by": "Google", "root": "veo-3.1-fast", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["video"], "modality": "text,image->video"}, "supported_features": [], "supported_endpoints": ["/v1/videos"], "pricing": null, "context_window": {"context_length": 480, "max_output_tokens": null}, "context_length": 480, "metadata": {"display_name": "Veo-3.1-Fast", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6501541-200-ayjxcwkcfikkjicbsbhcywnxljitkxxv.jpeg", "alt": "Veo-3.1-Fast model icon", "width": 200, "height": 200}, "url": "https://poe.com/veo-3.1-fast"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["16:9", "9:16"]}, "default_value": "16:9"}, {"name": "no", "schema": {"type": "string"}}, {"name": "duration", "schema": {"enum": ["4", "6", "8"]}, "default_value": "8"}, {"name": "seed", "schema": {"type": "string"}}, {"name": "silent", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to generate a video without audio. Decreases cost."}, {"name": "resolution", "schema": {"enum": ["720p", "1080p"]}, "default_value": "720p"}]}, {"id": "sora-2-pro", "object": "model", "created": 1759779974530, "description": "Sora 2 Pro is OpenAI\u2019s state-of-the-art video and audio generation model, capable of creating richly detailed, dynamic clips with synchronized audio from natural language prompts or images. It builds on Sora 2\u2019s capabilities with enhanced physical accuracy, intricate world-state persistence, and higher fidelity in cinematic styles. The model excels at generating synchronized dialogue, sound effects, and realistic simulations, all while adhering to real-world physics. Sora 2 Pro also supports seamless editing, complex multi-shot prompt execution, and the integration of real-world elements like people, animals, and objects with unparalleled detail and accuracy.\nThis bot supports text-to-video and image-to-video generation.\n\nOptional parameters:\n- Duration. Video output duration in seconds (options: 4, 8, 12)\n- Size. Resolution of the output video. Options: [Landscape] - 1280x720, 1792x1024, [Portrait] - 720x1280, 1024x1792", "owned_by": "OpenAI", "root": "sora-2-pro", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["video"], "modality": "text,image->video"}, "supported_features": [], "supported_endpoints": ["/v1/videos"], "pricing": null, "context_window": {"context_length": 480, "max_output_tokens": null}, "context_length": 480, "metadata": {"display_name": "Sora-2-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6478771-200-abbjvkqfxufhqojouahnbkrfzdguunlk.jpeg", "alt": "Sora-2-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/sora-2-pro"}, "reasoning": null, "parameters": [{"name": "size", "schema": {"enum": ["1280x720", "720x1280", "1792x1024", "1024x1792", "1920x1080", "1080x1920"]}, "default_value": "720x1280"}, {"name": "duration", "schema": {"enum": ["4", "8", "12", "16", "20"]}, "default_value": "4"}]}, {"id": "sora-2", "object": "model", "created": 1759780020960, "description": "Sora 2 is OpenAI\u2019s latest video and audio generation model, delivering exceptional realism, physical accuracy, and controllability. It excels at creating cinematic scenes, synchronized dialogue, sound effects, and dynamic simulations while faithfully adhering to the laws of physics. The model supports editing, multi-shot prompt adherence, and the integration of real-world elements, such as people, animals, and objects.\nThis bot supports text-to-video and image-to-video generation.\n\nOptional parameters:\n- Set Duration. Select from (4 seconds, 8 seconds or 12 seconds) to specify video length in seconds. Set to 4 seconds as default.\n- Set Resolution. Select from (Landscape - 1280x720 or Portrait - 720x1280). It is set to Portrait (720x1280) resolution as default.", "owned_by": "OpenAI", "root": "sora-2", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["video"], "modality": "text,image->video"}, "supported_features": [], "supported_endpoints": ["/v1/videos"], "pricing": null, "context_window": {"context_length": 480, "max_output_tokens": null}, "context_length": 480, "metadata": {"display_name": "Sora-2", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6478775-200-pkaiapkzxadtwqatzmwzraneemwedqtz.jpeg", "alt": "Sora-2 model icon", "width": 200, "height": 200}, "url": "https://poe.com/sora-2"}, "reasoning": null, "parameters": [{"name": "size", "schema": {"enum": ["1280x720", "720x1280"]}, "default_value": "720x1280"}, {"name": "duration", "schema": {"enum": ["4", "8", "12", "16", "20"]}, "default_value": "4"}]}, {"id": "kling-2.5-turbo-std", "object": "model", "created": 1761145308745, "description": "Generate high-quality videos from images using Kling 2.5 Turbo Standard. \n\nOptional parameters:\n- Negative prompt. Type things to avoid in generated images\n- CFG Scale. To send a classifier-free guidance scale between 0.0 and 1.0. This is set to 0.5 as default\n- Set Duration. Select from (5 seconds or 10 seconds) to specify video length in seconds. Set to 5 seconds as default\n\nNote: Only Image to Video is supported, aspect ratio is inferred automatically from the image and cannot be set.\n\nSupported image file format: jpeg, png, webp", "owned_by": "fal", "root": "kling-2.5-turbo-std", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["video"], "modality": "text,image->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Kling-2.5-Turbo-Std", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6520915-200-uykdwawubrwzfpzuealtvqjesuydeqnr.jpeg", "alt": "Kling-2.5-Turbo-Std model icon", "width": 200, "height": 200}, "url": "https://poe.com/kling-2.5-turbo-std"}, "reasoning": null, "parameters": [{"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "blur, distort, and low quality"}, {"name": "cfg_scale", "schema": {"type": "number", "minimum": 0.0, "maximum": 1.0}, "default_value": 0.5, "description": "Classifer Guidance Scale for generation."}, {"name": "duration", "schema": {"enum": ["5", "10"]}, "default_value": "5", "description": "Video duration in seconds"}]}, {"id": "wan-2.6", "object": "model", "created": 1765907288740, "description": "Wan 2.6 is Alibaba\u2019s multimodal video generation model built for cinematic, multi-shot storytelling\u2014creating high-fidelity videos from text and/or images while keeping characters and style consistent across scenes. It also supports native audio-visual sync (including lip-sync) and can generate or align dialogue/music/SFX with the visuals, enabling \u201cprompt-to-video\u201d results that feel production-ready without heavy post work.\n\nNotes:\n- This model is served from the Singapore area. \n- Upload an image to enable image-to-video generations or video(s) for reference-to-video generations. The mode is auto-detected from your attachments, or you can choose manually to override.\n- Responses may take upwards of 10 minutes to finish generating. \n\nAttachments\n   - For i2v: Attach an image as the first frame\n   - For r2v: Attach up to 5 images + 1-3 reference videos (1-30 seconds each, 100MB max, MP4/MOV) (Use `character1`, `character2`, `character3` in prompt to reference subjects, ex. character1 references the subject in the first uploaded video) (combined max 5). Uploaded audio files are silently ignored in R2V. Instead, audio is extracted from reference videos.\n   - For t2v/i2v: Optionally attach an audio file (3-30 seconds, max 15mb, .mp3/.wav) for custom audio\n   - Images are automatically resized to fit limits (I2V: 240\u20138,000px, R2V: 240\u20138,000px). HEIC/HEIF images are auto-converted. Videos for R2V are validated (MP4/MOV, 1\u201330s, \u2264100 MB) and auto-trimmed if longer than 30 seconds. For R2V, if output duration is set above 10 seconds, it will be automatically capped to 10 seconds.\n\nMulti-Shot Prompting\n   - For multi-shot mode, use timeline syntax: `[Shot #] [Timestamp] [Action]`. Example: `[Shot 1] [0-5s] Wide shot of city skyline. [Shot 2] [5-10s] Close-up of character walking.` \n   - Ensure timestamps match your selected duration and use transition keywords like \"Hard cut\" or \"Fade in\" between shots.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "wan-2.6", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Wan-2.6", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6674409-200-uodardabopjiblfkwjbstiibrscmcotq.jpeg", "alt": "Wan-2.6 model icon", "width": 200, "height": 200}, "url": "https://poe.com/wan-2.6"}, "reasoning": null, "parameters": [{"name": "mode", "schema": {"enum": ["auto", "t2v", "i2v", "r2v"]}, "default_value": "auto", "description": "Auto-detected from your attachments, or choose manually to override."}, {"name": "resolution", "schema": {"enum": ["720p", "1080p"]}, "default_value": "1080p", "description": "Higher resolution costs more per second."}, {"name": "aspect_ratio", "schema": {"enum": ["16:9", "9:16", "1:1", "4:3", "3:4"]}, "default_value": "16:9", "description": "Ignored for Image-to-Video (uses the input image's ratio instead)."}, {"name": "duration", "schema": {"type": "number", "minimum": 5, "maximum": 15}, "default_value": 5, "description": "How long the generated video will be. Reference-to-Video is automatically capped to 10 seconds."}, {"name": "flash_mode", "schema": {"type": "boolean"}, "default_value": false, "description": "Faster generation at reduced cost. Applies to Image-to-Video and Reference-to-Video."}, {"name": "prompt_extend", "schema": {"type": "boolean"}, "default_value": true, "description": "Let AI rewrite your prompt for better results. Adds a little extra processing time."}, {"name": "audio", "schema": {"type": "boolean"}, "default_value": true, "description": "Generate video with audio. Disabling reduces Flash mode cost."}, {"name": "shot_type", "schema": {"enum": ["single", "multi"]}, "default_value": "multi", "description": "Single continuous shot or multi-shot narrative."}, {"name": "seed", "schema": {"type": "string"}, "default_value": "", "description": "Set a number for reproducible results. Leave blank for random."}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "", "description": "Describe anything you want to avoid in the video."}]}, {"id": "seedream-4.0", "object": "model", "created": 1757430793599, "description": "Seedream 4.0 is ByteDance's latest and best text-to-image model, capable of impressive high fidelity image generation, with great text-rendering ability. Seedream 4.0 can also take in  multiple images as references and combine them together or edit them to return an output. \n\nOptional parameters:\nSet aspect ratio. Select from (One of `16:9`, `4:3`, `1:1`, `3:4`, `9:16`).", "owned_by": "Bytedance", "root": "seedream-4.0", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Seedream-4.0", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6402778-200-rxptfikgaavvapruaenkqljttzpyzeaz.jpeg", "alt": "Seedream-4.0 model icon", "width": 200, "height": 200}, "url": "https://poe.com/seedream-4.0"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "kling-2.5-turbo-pro", "object": "model", "created": 1758612711916, "description": "Generate high-quality videos from text and images using Kling 2.5 Turbo Pro. \n\nOptional parameters:\n- Negative prompt. Type things to avoid in generated images\n- CFG Scale. To send a classifier-free guidance scale between 0.0 and 1.0. This is set to 0.5 as default\n- Set aspect ratio. Select from (16:9, 1:1, 9:16). It is set to 16:9 aspect ratio as default. Only works for text-to-video\n- Set Duration. Select from (5 seconds or 10 seconds) to specify video length in seconds. Set to 5 seconds as default.", "owned_by": "fal", "root": "kling-2.5-turbo-pro", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Kling-2.5-Turbo-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6443215-200-vfpmkcpwtedpvujuzokeshqgqwokglxf.jpeg", "alt": "Kling-2.5-Turbo-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/kling-2.5-turbo-pro"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "1:1", "9:16"]}, "default_value": "16:9"}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "blur, distort, and low quality"}, {"name": "cfg_scale", "schema": {"type": "number", "minimum": 0.0, "maximum": 1.0}, "default_value": 0.5, "description": "Classifer Guidance Scale for generation."}, {"name": "duration", "schema": {"enum": ["5", "10"]}, "default_value": "5", "description": "Video duration in seconds"}]}, {"id": "kling-2.1-master", "object": "model", "created": 1748544153317, "description": "Kling 2.1 Master: The premium endpoint for Kling 2.1, designed for top-tier image-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision. \n\nOptional parameters:\n- Negative prompt. Type things to avoid in generated images\n- CFG Scale. To send a classifier-free guidance scale between 0.0 and 1.0. This is set to 0.5 as default\n- Set aspect ratio. Select from (16:9, 1:1, 9:16). It is set to 16:9 aspect ratio as default.\n- Set Duration. Select from (5 seconds or 10 seconds) to specify video length in seconds. Set to 5 seconds as default.", "owned_by": "fal", "root": "kling-2.1-master", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Kling-2.1-Master", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6071460-200-xvbvdcdyzstayucglmczvtsqqapmsole.jpeg", "alt": "Kling-2.1-Master model icon", "width": 200, "height": 200}, "url": "https://poe.com/kling-2.1-master"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "1:1", "9:16"]}, "default_value": "16:9"}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "blur, distort, and low quality"}, {"name": "cfg_scale", "schema": {"type": "number", "minimum": 0.0, "maximum": 1.0}, "default_value": 0.5, "description": "Classifer Guidance Scale for generation."}, {"name": "duration", "schema": {"enum": ["5", "10"]}, "default_value": "5", "description": "Video duration in seconds"}]}, {"id": "hailuo-02", "object": "model", "created": 1750150747414, "description": "Hailuo-02, MiniMax's latest video generation model. Generates 6-second, 768p videos, just submit a text prompt or an image with a prompt describing the desired video behavior, and it will create it; typically takes ~5 minutes for generation time. Strong motion effects and ultra-clear quality.", "owned_by": "Minimax", "root": "hailuo-02", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Hailuo-02", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6134645-200-axrxqotrrughgqqdqaclzvlnijhjyesy.jpeg", "alt": "Hailuo-02 model icon", "width": 200, "height": 200}, "url": "https://poe.com/hailuo-02"}, "reasoning": null, "parameters": []}, {"id": "hailuo-02-standard", "object": "model", "created": 1750266147410, "description": "MiniMax Hailuo-02 Video Generation model: Advanced image-to-video generation model with 768p resolution. Send a prompt with an image for image-to-video, and just a prompt for text-to-video generation. \n\nOptional parameters:\nSet Duration. Select from (6 seconds or 10 seconds) to specify video length in seconds. Set to 6 seconds as default", "owned_by": "fal", "root": "hailuo-02-standard", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Hailuo-02-Standard", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6139813-200-lcbibgfzexghkmncnlxktidsnrmuniid.jpeg", "alt": "Hailuo-02-Standard model icon", "width": 200, "height": 200}, "url": "https://poe.com/hailuo-02-standard"}, "reasoning": null, "parameters": [{"name": "duration", "schema": {"enum": ["6", "10"]}, "default_value": "6", "description": "Video duration in seconds"}]}, {"id": "hailuo-02-pro", "object": "model", "created": 1753281868828, "description": "MiniMax Hailuo-02 Pro Video Generation model: Advanced image-to-video generation model with 1080p resolution. Send a prompt with an image for image-to-video, and just a prompt for text-to-video generation. Generates 5 second video.", "owned_by": "fal", "root": "hailuo-02-pro", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Hailuo-02-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6250706-200-fvdcrmnrdnjgjtnogwygvieblixbpshw.jpeg", "alt": "Hailuo-02-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/hailuo-02-pro"}, "reasoning": null, "parameters": []}, {"id": "deepseek-r1-turbo-di", "object": "model", "created": 1741250889407, "description": "Top open-source reasoning LLM rivaling OpenAI's o1 model; delivers top-tier performance across math, code, and reasoning tasks at a fraction of the cost. Turbo model is quantized to achieve higher speeds. All data you provide this bot will not be used in training, and is sent only to DeepInfra, a US-based company.\n\nSupports 32k tokens of input context and 8k tokens of output context. Quantization: FP4 (turbo).", "owned_by": "DeepInfra", "root": "deepseek-r1-turbo-di", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.015", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 32000, "max_output_tokens": null}, "context_length": 32000, "metadata": {"display_name": "DeepSeek-R1-Turbo-DI", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5755292-200-xtvccqsbbpdrciwbcpfpplogqvlfdeqw.jpeg", "alt": "DeepSeek-R1-Turbo-DI model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepseek-r1-turbo-di"}, "reasoning": null, "parameters": []}, {"id": "hailuo-director-01", "object": "model", "created": 1749502785341, "description": "Generate video clips more accurately with respect to natural language descriptions and using camera movement instructions for shot control. Both text-to-video and image-to-video are supported. \nCamera movement instructions can be added using square brackets (e.g. [Pan left] or [Zoom in]). \nYou can use up to 3 combined movements per prompt. Duration is fixed to 5 seconds. \nSupported movements: Truck left/right, Pan left/right, Push in/Pull out, Pedestal up/down, Tilt up/down, Zoom in/out, Shake, Tracking shot, Static shot. For example: [Truck left, Pan right, Zoom in]. \nFor a more detailed guide, refer https://sixth-switch-2ac.notion.site/T2V-01-Director-Model-Tutorial-with-camera-movement-1886c20a98eb80f395b8e05291ad8645", "owned_by": "fal", "root": "hailuo-director-01", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Hailuo-Director-01", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6107505-200-wyfxlankxkygcftfdbdudlhbgldrllgq.jpeg", "alt": "Hailuo-Director-01 model icon", "width": 200, "height": 200}, "url": "https://poe.com/hailuo-director-01"}, "reasoning": null, "parameters": []}, {"id": "pixverse-v5", "object": "model", "created": 1760645525570, "description": "Pixverse v5 offers advanced creative tools with three main features: \n1. Text-to-Video, which transforms written prompts into cinematic, high-detail video clips with fluid motion and accurate visual interpretation;\n2. Image-to-Video, which animates static images into dynamic short videos with lifelike motion and smooth transitions; and \n3. Transition, which generates seamless morphs between frames or scenes to create unified, professional-quality visual flow.\n\nParameter Controls and Usage:\n1. Video Generation (Main Control Section)\n  - Set Video Resolution. Select from 360p , 540p, 720p, 1080p. This is set to 720p by default.\n  - Set Duration. Select from (5 seconds or 8 seconds) to specify video length in seconds. Set to 5 seconds as default. Note: 8s not supported for 1080p.\n  - Set aspect ratio. Select from (16:9, 4:3, 1:1, 3:4, 9:16). It is set to 16:9 aspect ratio as default.\n  - Negative prompt. Type things to avoid in generated images\n  - Seed. Random seed number for reproducible generation with fixed seed (e.g. 12345)\n\n2. Generation Modes (Determined by attachments)\n- Text-to-Video: Provide a prompt with 0 image attachments.\n- Image-to-Video: Provide 1 image attachment.\n- Transition: Provide 2 image attachments (first is start frame, second is end frame).\n\n3. Limitations\n- The combination of resolution `1080p` and duration `8 seconds` is not supported.\n- Only 0, 1, or 2 image attachments are supported.\n- Attachments must be images (PNG/JPEG/WEBP/TIFF/BMP/HEIC/GIF).", "owned_by": "EmpirioLabs AI", "root": "pixverse-v5", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Pixverse-v5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6505434-200-uyvtsdugnudctlreivrhpdnftwngethw.jpeg", "alt": "Pixverse-v5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/pixverse-v5"}, "reasoning": null, "parameters": [{"name": "resolution", "schema": {"enum": ["360p", "540p", "720p", "1080p"]}, "default_value": "720p", "description": "Video resolution."}, {"name": "duration", "schema": {"enum": ["5", "8"]}, "default_value": "5", "description": "Video length in seconds. Note: 8s not supported for 1080p."}, {"name": "aspect_ratio", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "16:9", "description": "Video aspect ratio."}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "", "description": "Elements to avoid (optional)."}, {"name": "seed", "schema": {"type": "string"}, "default_value": "", "description": "Optional seed for reproducibility (integer)."}]}, {"id": "wan-2.5", "object": "model", "created": 1758919750787, "description": "Wan-2.5 Video Generation bot. Has text-to-video and image-to-video capabilities. Optionally, send an audio file (mp3) to guide the video generation. \n\nOptional Parameters:\nControl the output's resolution. Select from 480p, 720p or 1080p defaults to 720. Pricing varies on the basis of resolution.\nAspect ratio. Select from 16:9, 1:1, 9:16 defaults to 16:9 aspect ratio.\nDuration. Select video duration either 5 seconds or 10 seconds. Defaults to 5 seconds.", "owned_by": "fal", "root": "wan-2.5", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["video"], "modality": "text,image->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Wan-2.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6453745-200-kfoxvndgzylncscaqzzkpvelxtpqqcao.jpeg", "alt": "Wan-2.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/wan-2.5"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "1:1", "9:16"]}, "default_value": "16:9"}, {"name": "resolution", "schema": {"enum": ["480p", "720p", "1080p"]}, "default_value": "720p"}, {"name": "duration", "schema": {"enum": ["5", "10"]}, "default_value": "5", "description": "Video duration in seconds"}]}, {"id": "pixverse-v4.5", "object": "model", "created": 1747737997951, "description": "Pixverse v4.5 is a video generation model capable of generating high quality videos in under a minute. \n\nNote:\nSend 1 image to perform an image-to-video task or a video effect generation task, and 2 images to perform a video transition task, using the first image as the first frame and the second image as the last frame. \n\nOptional parameters:\nNegative prompt to set the negative prompt. \nDuration to set the video duration (5 or 8 seconds). \nSet the resolution (360p,540p,720p or 1080p). \nEffect to set the video generation effect, provided 1 image is given (Options: `Kiss_Me_AI`, `Kiss`, `Muscle_Surge`, `Warmth_of_Jesus`, `Anything,_Robot`, `The_Tiger_Touch`, `Hug`, `Holy_Wings`, `Hulk`, `Venom`, `Microwave`). Use `--style` to set the video generation style (for text-to-video,image-to-video, and transition only, options: `anime`, `3d_animation`, `clay`, `comic`, `cyberpunk`).  \nSeed to set the seed and Aspect ratio to set the aspect ratio (16:9, 4:3, 1:1, 3:4, 9:16).", "owned_by": "fal", "root": "pixverse-v4.5", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Pixverse-v4.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6038042-200-lwiivahvgvkwpdbvbkvvjabcxuuvyohu.jpeg", "alt": "Pixverse-v4.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/pixverse-v4.5"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "16:9"}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "blurry, low quality, low resolution, pixelated, noisy, grainy, out of focus, poorly lit, poorly exposed, poorly composed, poorly framed, poorly cropped, poorly color corrected, poorly color graded"}, {"name": "duration", "schema": {"enum": ["5", "8"]}, "default_value": "5", "description": "Video duration in seconds"}, {"name": "resolution", "schema": {"enum": ["360p", "540p", "720p", "1080p"]}, "default_value": "720p", "description": "Resolution of the video."}, {"name": "style", "schema": {"enum": ["None", "anime", "3d_animation", "clay", "comic", "cyberpunk"]}, "default_value": "None", "description": "Style of the video."}, {"name": "seed", "schema": {"type": "string"}, "description": "Seed to generate the video."}, {"name": "effect", "schema": {"enum": ["None", "Kiss_Me_AI", "Kiss", "Muscle_Surge", "Warmth_of_Jesus", "Anything,_Robot", "The_Tiger_Touch", "Hug", "Holy_Wings", "Microwave"]}, "default_value": "None", "description": "Effect to apply on the image."}]}, {"id": "flux-dev", "object": "model", "created": 1722521612508, "description": "High-performance image generation with top of the line prompt following, visual quality, image detail and output diversity. This is a more efficient version of FLUX-pro, balancing quality and speed. \n\nOptional parameters:\nAspect ratio. Valid aspect ratios are 16:9, 4:3, 1:1, 3:4, 9:16.  \n\nNote: Send an image to have this model reimagine/regenerate it via FLUX Redux.", "owned_by": "fal", "root": "flux-dev", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": {"context_length": 256, "max_output_tokens": null}, "context_length": 256, "metadata": {"display_name": "FLUX-dev", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-4691939-200-wjmsiwztndchfvsdmvowztddsrmszhtw.jpeg", "alt": "FLUX-dev model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-dev"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "lyria-3", "object": "model", "created": 1774462776129, "description": "Google DeepMind\u2019s Lyria 3 is an advanced AI music generation model that creates high-fidelity, up to three-minute tracks from text or image prompts, with detailed control over vocals, style, and composition.\n\nOptional parameters:\nFull song: Turn it on to generate a full-length track (up to 3 minutes).\n\nNotes:\nLyria blocks prompts that name specific artists or songs (artist-intent and recitation checks).", "owned_by": "Google", "root": "lyria-3", "architecture": {"input_modalities": ["text"], "output_modalities": ["audio"], "modality": "text->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Lyria-3", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6903480-200-kjryamkevckydypfxrqyurkzduypqqmh.jpeg", "alt": "Lyria-3 model icon", "width": 200, "height": 200}, "url": "https://poe.com/lyria-3"}, "reasoning": null, "parameters": [{"name": "full_song", "schema": {"type": "boolean"}, "default_value": false, "description": "Generate a full-length song with verses, choruses, and bridges. When off, generates a 30-second clip or loop instead."}]}, {"id": "lyria", "object": "model", "created": 1749063911995, "description": "Google DeepMind's Lyria 2 delivers high-quality audio generation, capable of creating diverse soundscapes and musical pieces from text prompts.\n\nOptional parameters:\nNegative prompt. Allows users to specify elements to exclude in the audio. \nSeed for deterministic generation. e.g. \"An energetic electronic dance track `no vocals`, slow tempo 1seed 123`\". \n\nNotes: \nLyria blocks prompts that name specific artists or songs (artist-intent and recitation checks)\nThis bot does not support attachments. \nThis bot accepts input prompts of up to 480 tokens.", "owned_by": "Google", "root": "lyria", "architecture": {"input_modalities": ["text"], "output_modalities": ["audio"], "modality": "text->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Lyria", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6090541-200-loimwrwctofaadexurdsipsxnzhkdmqo.jpeg", "alt": "Lyria model icon", "width": 200, "height": 200}, "url": "https://poe.com/lyria"}, "reasoning": null, "parameters": [{"name": "no", "schema": {"type": "string"}}, {"name": "seed", "schema": {"type": "string"}}]}, {"id": "kling-1.6-pro", "object": "model", "created": 1737537681579, "description": "Kling v1.6 video generation bot, hosted by fal.ai. For best results, upload an image attachment.\n\nOptional parameters:\nSet the aspect ratio. Allowed values are `16:9`, `9:16` and `1:1`. \nDuration` to set the duration of the generated video (5 or 10 seconds).", "owned_by": "fal", "root": "kling-1.6-pro", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Kling-1.6-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5574816-200-ridhbdhnrzbvrawdzckwhzfineuouyhh.jpeg", "alt": "Kling-1.6-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/kling-1.6-pro"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "1:1", "9:16"]}, "default_value": "16:9"}, {"name": "duration", "schema": {"enum": ["5", "10"]}, "default_value": "5", "description": "Video duration in seconds"}]}, {"id": "clarity-upscaler", "object": "model", "created": 1736160594594, "description": "Upscales images with high fidelity to the original image. \n\nOptional parameters:\nUpscale_factor (value is a number between 1 and 4) to set the upscaled images' size (2 means the output image is 2x in size, etc.).  \nCreativity and Clarity can be set between 0 and 1 to alter the faithfulness to the original image and the sharpness, respectively.\n\nNote: This bot supports .jpg, .png, bmp, gif and tiff images.", "owned_by": "fal", "root": "clarity-upscaler", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Clarity-Upscaler", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5511730-200-dwaajkcknqmucbevlnrktpmtyqbrigjv.jpeg", "alt": "Clarity-Upscaler model icon", "width": 200, "height": 200}, "url": "https://poe.com/clarity-upscaler"}, "reasoning": null, "parameters": [{"name": "upscale_factor", "schema": {"type": "number", "minimum": 1.1, "maximum": 4}, "default_value": 2}, {"name": "creativity", "schema": {"type": "number", "minimum": 0.0, "maximum": 1.0}, "default_value": 0.3}, {"name": "resemblance", "schema": {"type": "number", "minimum": 0.0, "maximum": 1.0}, "default_value": 0.65}]}, {"id": "topazlabs", "object": "model", "created": 1733266151324, "description": "Topaz Labs\u2019 image upscaler is a best-in-class generative AI model to increase overall clarity and the pixel amount of inputted photos \u2014 whether they be ones generated by AI image models and from the real world \u2014 while preserving the original photo\u2019s contents. It can produce images of as small as ~10MB and as large as 512MB, depending on the size of the input photo. \n\nOptional parameters:\nSpecify upscale and a number up to 16 to control the upscaling factor, output height and/or output_width to specify the number of pixels for each dimension, and toggle generated if the input photo is AI-generated. \n\nNotes: With no parameters specified, it will increase both input photo\u2019s height and width by 2; especially effective on images of human faces.", "owned_by": "TopazLabs-Co", "root": "topazlabs", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.000030", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 204, "max_output_tokens": null}, "context_length": 204, "metadata": {"display_name": "TopazLabs", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5365520-200-iycciuwxnpjfzrjnivbovoeosyaozdqp.jpeg", "alt": "TopazLabs model icon", "width": 200, "height": 200}, "url": "https://poe.com/topazlabs"}, "reasoning": null, "parameters": [{"name": "upscale", "schema": {"type": "number", "minimum": 1, "maximum": 16}, "default_value": 4}, {"name": "output_width", "schema": {"type": "string"}}, {"name": "output_height", "schema": {"type": "string"}}, {"name": "generated", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable if the input image was AI-generated."}]}, {"id": "veo-v3.1", "object": "model", "created": 1760568057558, "description": "Google's Veo-3.1 is an improved version of Veo 3.\n\nOptional parameters:\nSet the aspect ratio of the generated image (one of `16:9`, `9:16`).\nSet silent to generate a silent video at a lower cost.\nSet negative prompt option `blur`, `low resolution`, `poor quality`. (only for T2V).\nSet the duration `4s`, `6s`, `8s`, default `8s`. `4s` and `6s` are only supported for text-to-video generation.\n\nNotes:\nPass a single image for image to video tasks. \nPass two images for a first-frame-to-last-frame video generation task. \nPass up to 3 images with reference for a reference-to-video task. Reference images will be directly used in the video generation.", "owned_by": "fal", "root": "veo-v3.1", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Veo-v3.1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6502467-200-wjytahnyprthxsdpipukyyjdwcgnlrkf.jpeg", "alt": "Veo-v3.1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/veo-v3.1"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "9:16"]}, "default_value": "16:9"}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "blur, low resolution, poor quality"}, {"name": "silent", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to generate a video without audio. Decreases cost."}, {"name": "reference", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to use input images as reference for video generation."}, {"name": "duration", "schema": {"enum": ["4s", "6s", "8s"]}, "default_value": "8s", "description": "Video duration in seconds"}, {"name": "resolution", "schema": {"enum": ["720p", "1080p"]}, "default_value": "1080p"}]}, {"id": "veo-v3.1-fast", "object": "model", "created": 1760650990090, "description": "Google's Veo 3.1 Fast is a fast version of Veo 3.1.\n\nOptional parameters:\nSet the aspect ratio of the generated image (one of `16:9`, `9:16`).\nSilent to generate a silent video at a lower cost.\nSet negative prompt option `blur`, `low resolution`, `poor quality`. (only for T2V).\nSet the duration `4s`, `6s`, `8s`, default `8s`. `4s` and `6s` are only supported for text-to-video generation\n\nNote: Pass a single image for image to video tasks. Pass two images for a first-frame-to-last-frame video generation task.", "owned_by": "fal", "root": "veo-v3.1-fast", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["video"], "modality": "text,image->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Veo-v3.1-Fast", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6505629-200-ahtphhtsfwhadshmrqzunqfpjonfrhsg.jpeg", "alt": "Veo-v3.1-Fast model icon", "width": 200, "height": 200}, "url": "https://poe.com/veo-v3.1-fast"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "9:16"]}, "default_value": "16:9"}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "blur, low resolution, poor quality"}, {"name": "silent", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to generate a video without audio. Decreases cost."}, {"name": "duration", "schema": {"enum": ["4s", "6s", "8s"]}, "default_value": "8s", "description": "Video duration in seconds"}, {"name": "resolution", "schema": {"enum": ["720p", "1080p"]}, "default_value": "1080p"}]}, {"id": "wan-2.2", "object": "model", "created": 1753731782474, "description": "Wan-2.2 is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts. Send one image for image to video tasks, and send two images for first-frame - last-frame generation. \n\nOptional parameters:\nSet the aspect ratio (One of `16:9`, `1:1`, `9:16`) for text-to-video requests. \nDuration is limited to 5 seconds only with up to 720p resolution.", "owned_by": "fal", "root": "wan-2.2", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Wan-2.2", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6271439-200-miqdbogqpycjwyyuqaainaxmspxmvvcz.jpeg", "alt": "Wan-2.2 model icon", "width": 200, "height": 200}, "url": "https://poe.com/wan-2.2"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "1:1", "9:16"]}, "default_value": "16:9"}]}, {"id": "ltx-2-fast", "object": "model", "created": 1761343254536, "description": "LTX-2 Fast is a video model by Lightricks that delivers exceptional quality and speed. It can generate videos at up to 50 FPS in high resolutions and supports both text-to-video and image-to-video generation.\n\nOptional Prompts:\nGenerate an audio with the video. This is disabled by default. \nSet. resolution with one of `1080p`, `1440p`, `2160p`. This is set to 1080p by default.\nSet the duration of the generated video (one of `6s, 8s, 10s`). This is set to 6s by default. \nSet the fps of the generated video to one of 25 or 50. This is set to 25 by default\n\nNotes: \nDuration and resolution values will change the price. \nFile attachment accepted: jpeg, png, webp", "owned_by": "fal", "root": "ltx-2-fast", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["video"], "modality": "text,image->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "LTX-2-Fast", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6527895-200-uiestjlshdkekhndkdftqajxyyfwyyec.jpeg", "alt": "LTX-2-Fast model icon", "width": 200, "height": 200}, "url": "https://poe.com/ltx-2-fast"}, "reasoning": null, "parameters": [{"name": "duration", "schema": {"enum": ["6", "8", "10"]}, "default_value": "6", "description": "Video duration in seconds"}, {"name": "resolution", "schema": {"enum": ["1080p", "1440p", "2160p"]}, "default_value": "1080p", "description": "Video resolution"}, {"name": "fps", "schema": {"enum": ["25", "50"]}, "default_value": "25", "description": "Frames per second"}, {"name": "generate_audio", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to generate audio with video."}]}, {"id": "ltx-2-pro", "object": "model", "created": 1761343366727, "description": "LTX-2 Pro is an advanced video generation model by Lightricks designed for professional\u2011grade results. It offers high\u2011quality, realistic video generation at exceptional speed and supports outputs up to 2K resolution. Perfect for both text\u2011to\u2011video and image\u2011to\u2011video creation, it delivers cinematic detail and smooth performance.\n\nOptional Prompts:\nGenerate an audio with the video. This is disabled by default. \nSet. resolution with one of `1080p`, `1440p`, `2160p`. This is set to 1080p by default.\nSet the duration of the generated video (one of `6s, 8s, 10s`). This is set to 6s by default. \nSet the fps of the generated video to one of 25 or 50. This is set to 25 by default\n\nNotes: \nDuration and resolution values will change the price. \nFile attachment accepted: jpeg, png, webp", "owned_by": "fal", "root": "ltx-2-pro", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["video"], "modality": "text,image->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "LTX-2-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6527896-200-ucmdvzxftfqhoiuipngepaqiypytxtcu.jpeg", "alt": "LTX-2-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/ltx-2-pro"}, "reasoning": null, "parameters": [{"name": "duration", "schema": {"enum": ["6", "8", "10"]}, "default_value": "6", "description": "Video duration in seconds"}, {"name": "resolution", "schema": {"enum": ["1080p", "1440p", "2160p"]}, "default_value": "1080p", "description": "Video resolution"}, {"name": "fps", "schema": {"enum": ["25", "50"]}, "default_value": "25", "description": "Frames per second"}, {"name": "generate_audio", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to generate audio with video."}]}, {"id": "veo-3", "object": "model", "created": 1747796700448, "description": "Veo 3 produces incredibly high-quality videos across a diverse range of subjects and styles. It incorporates an enhanced understanding of real-world physics and the subtleties of human movement and expression, resulting in greater detail and overall realism.\n\nVeo 3 is fluent in the unique language of cinematography: you can request a specific genre, specify a lens, or suggest cinematic effects, and Veo 3 will deliver stunning 8-second video clips. It supports both text-to-video and image-to-video generation and also features native audio generation based on text prompts.\n\nNote: Please note that Veo 3 does not accept audio attachments.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "Google", "root": "veo-3", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": ["/v1/videos"], "pricing": null, "context_window": {"context_length": 480, "max_output_tokens": null}, "context_length": 480, "metadata": {"display_name": "Veo-3", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6040520-200-ycffcgunfwthfylqqbbhffkfxotsufqj.jpeg", "alt": "Veo-3 model icon", "width": 200, "height": 200}, "url": "https://poe.com/veo-3"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["16:9", "9:16"]}, "default_value": "16:9"}, {"name": "no", "schema": {"type": "string"}}, {"name": "duration", "schema": {"enum": ["4", "6", "8"]}, "default_value": "8"}, {"name": "seed", "schema": {"type": "string"}}, {"name": "silent", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to generate a video without audio. Decreases cost."}, {"name": "resolution", "schema": {"enum": ["720p", "1080p"]}, "default_value": "720p"}]}, {"id": "veo-3-vfast", "object": "model", "created": 1752140109634, "description": "Veo-3 Fast is a faster and more cost effective version of Google's Veo 3. \n\nOptional parameters:\nSet the aspect ratio of the generated image (one of `16:9`, `1:1`, `9:16`). \nToggle `on` the generate audio with your video at a higher cost. \nNegative prompt on what to exclude e.g. `blur`, `low resolution`, `poor quality`. \nDuration is limited to 7 seconds. This is a text to video generation model only.", "owned_by": "fal", "root": "veo-3-vfast", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Veo-3-vFast", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6210038-200-ipukatrlluhzwodiyhlaspzpyxsdevop.jpeg", "alt": "Veo-3-vFast model icon", "width": 200, "height": 200}, "url": "https://poe.com/veo-3-vfast"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "1:1", "9:16"]}, "default_value": "16:9"}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "blur, low resolution, poor quality"}, {"name": "generate_audio", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to generate audio with video. Increases cost."}]}, {"id": "vidu", "object": "model", "created": 1756292711841, "description": "The Vidu Video Generation Bot creates videos using images and text prompts. You can generate videos in four modes: \n(1) Image-to-Video: send 1 image with a prompt, \n(2) Start-to-End Frame: send 2 images with a prompt for transition videos, \n(3) Reference-to-Video: send up to 3 images with the reference image parameter for guidance, and \n(4) Template-to-Video: use `--template` to apply pre-designed templates (1-3 images required, pricing varies by template). \n\nNumber of images required varies by template: `dynasty_dress` and `shop_frame` accept 1-2 images, `wish_sender` requires exactly 3 images, all other templates accept only 1 image.\n\nThe bot supports aspect ratios (16:9, 1:1, 9:16), set movement amplitude, and accepts PNG, JPEG, and WEBP formats. \nTasks are mutually exclusive (e.g., you cannot combine start-to-end frame and reference-to-video).\nDuration is limited to 5 seconds.", "owned_by": "fal", "root": "vidu", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["video"], "modality": "text,image->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Vidu", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6364969-200-epdnwvkvjlbawxbxsmoxxvfivcatzuuz.jpeg", "alt": "Vidu model icon", "width": 200, "height": 200}, "url": "https://poe.com/vidu"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "1:1", "9:16"]}, "default_value": "16:9"}, {"name": "movement_amplitude", "schema": {"enum": ["auto", "small", "medium", "large"]}, "default_value": "auto"}, {"name": "template", "schema": {"enum": ["dreamy_wedding", "romantic_lift", "sweet_proposal", "couple_arrival", "cupid_arrow", "pet_lovers", "lunar_newyear", "hug", "kiss", "dynasty_dress", "wish_sender", "love_pose", "hair_swap", "youth_rewind", "morphlab", "live_photo", "emotionlab", "live_memory", "interaction", "christmas", "pet_finger", "eat_mushrooms", "beast_chase_library", "beast_chase_supermarket", "petal_scattered", "emoji_figure", "hair_color_change", "multiple_people_kissing", "beast_chase_amazon", "beast_chase_mountain", "balloonman_explodes_pro", "get_thinner", "jump2pool", "bodyshake", "jiggle_up", "shake_it_dance", "subject_3", "pubg_winner_hit", "shake_it_down", "blueprint_supreme", "hip_twist", "motor_dance", "rat_dance", "kwok_dance", "leg_sweep_dance", "heeseung_march", "shake_to_max", "dame_un_grrr", "i_know", "lit_bounce", "wave_dance", "chill_dance", "hip_flicking", "sakura_season", "zongzi_wrap", "zongzi_drop", "dragonboat_shot", "rain_kiss", "child_memory", "couple_drop", "couple_walk", "flower_receive", "love_drop", "cheek_kiss", "carry_me", "blow_kiss", "love_fall", "french_kiss_8s", "workday_feels", "love_story", "bloom_magic", "ghibli", "minecraft", "box_me", "claw_me", "clayshot", "manga_meme", "quad_meme", "pixel_me", "clayshot_duo", "irasutoya", "american_comic", "simpsons_comic", "yayoi_kusama_style", "pop_art", "jojo_style", "slice_therapy", "balloon_flyaway", "flying", "paperman", "pinch", "bloom_doorobear", "gender_swap", "nap_me", "sexy_me", "spin360", "smooth_shift", "paper_fall", "jump_to_cloud", "pilot", "sweet_dreams", "soul_depart", "punch_hit", "watermelon_hit", "split_stance_pet", "make_face", "break_glass", "split_stance_human", "covered_liquid_metal", "fluffy_plunge", "pet_belly_dance", "water_float", "relax_cut", "head_to_balloon", "cloning", "across_the_universe_jungle", "clothes_spinning_remnant", "across_the_universe_jurassic", "across_the_universe_moon", "fisheye_pet", "hitchcock_zoom", "cute_bangs", "earth_zoom_out", "fisheye_human", "drive_yacht", "virtual_singer", "earth_zoom_in", "aliens_coming", "drive_ferrari", "bjd_style", "virtual_fitting", "orbit", "zoom_in", "ai_outfit", "spin180", "orbit_dolly", "orbit_dolly_fast", "auto_spin", "walk_forward", "outfit_show", "zoom_in_fast", "zoom_out_image", "zoom_out_startend", "muscling", "captain_america", "hulk", "cap_walk", "hulk_dive", "exotic_princess", "beast_companion", "cartoon_doll", "golden_epoch", "oscar_gala", "fashion_stride", "star_carpet", "flame_carpet", "frost_carpet", "mecha_x", "style_me", "tap_me", "saber_warrior", "pet2human", "graduation", "fishermen", "happy_birthday", "fairy_me", "ladudu_me", "ladudu_me_random", "squid_game", "superman", "grow_wings"]}, "description": "AI video template to use. Pricing varies by template: Standard templates (hug, kiss, love_pose, etc.) cost 6667 points, Premium templates (lunar_newyear, dynasty_dress, dreamy_wedding, etc.) cost 10000 points, and Advanced templates (live_photo) cost 16667 points."}, {"name": "reference", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to use reference images for video generation. A maximum of 3 images are allowed for reference."}]}, {"id": "vidu-q1", "object": "model", "created": 1755797522439, "description": "The Vidu Q1 Video Generation Bot creates videos using text prompts and images. You can generate videos in three modes: \n(1) Text-to-Video: send a text prompt, \n(2) Image-to-Video: send 1 image with a prompt, and \n(3) Reference-to-Video: send up to 7 images. \n\nNumber of images required varies by template: `dynasty_dress` and `shop_frame` accept 1-2 images, `wish_sender` requires exactly 3 images, all other templates accept only 1 image.\n\nThe bot support aspect ratios (16:9, 1:1, 9:16) and set movement amplitude  that can be customized for text-to-video and reference-to-video tasks. \nTasks are mutually exclusive (e.g., you cannot combine start-to-end frame and reference-to-video generation).\nThe bot accepts PNG, JPEG, and WEBP formats. Duration is limited to 5 seconds.", "owned_by": "fal", "root": "vidu-q1", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["video"], "modality": "text,image->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Vidu-Q1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6348215-200-cmwqdoqxpoirfgqlgvuuvpmnumvlidvz.jpeg", "alt": "Vidu-Q1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/vidu-q1"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "1:1", "9:16"]}, "default_value": "16:9"}, {"name": "style", "schema": {"enum": ["general", "anime"]}, "default_value": "general", "description": "Style of the video."}, {"name": "movement_amplitude", "schema": {"enum": ["auto", "small", "medium", "large"]}, "default_value": "auto"}, {"name": "reference", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to use reference images for video generation. A maximum of 7 images are allowed for reference."}]}, {"id": "veo-3-fast", "object": "model", "created": 1760335513509, "description": "Veo 3 Fast is a speed-optimized variant of Google\u2019s Veo 3 AI video generation engine. It\u2019s designed for rapid, cost-efficient production of short clips with synchronized audio (dialogue, ambient sound, effects). Prioritizes faster generation times while still delivering solid visual and audio quality, supports text-to-video and image-to-video workflows, allowing creators to animate still images into motion sequences, operates under defined constraints (e.g. video lengths of 4, 6, or 8 seconds). Set the aspect ratio (either `16:9` or `9:16`), which defaults to `16:9`.\nPlease only upload photos that you own or have the right to use, otherwise the bot will throw an error.", "owned_by": "Google", "root": "veo-3-fast", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": ["/v1/videos"], "pricing": null, "context_window": {"context_length": 480, "max_output_tokens": null}, "context_length": 480, "metadata": {"display_name": "Veo-3-Fast", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6494812-200-hhoigayewqibyxyfiibwqvpwtujjxlvv.jpeg", "alt": "Veo-3-Fast model icon", "width": 200, "height": 200}, "url": "https://poe.com/veo-3-fast"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["16:9", "9:16"]}, "default_value": "16:9"}, {"name": "no", "schema": {"type": "string"}}, {"name": "duration", "schema": {"enum": ["4", "6", "8"]}, "default_value": "8"}, {"name": "seed", "schema": {"type": "string"}}, {"name": "silent", "schema": {"type": "boolean"}, "default_value": false, "description": "Toggle to generate a video without audio. Decreases cost."}, {"name": "resolution", "schema": {"enum": ["720p", "1080p"]}, "default_value": "720p"}]}, {"id": "seedance-1.0-pro-fast", "object": "model", "created": 1761334162620, "description": "Seedance Pro Fast is a faster version of Seedance 1.0 Pro that balances speed, quality and cost. Seedance is a video generation model with text-to-video and image-to-video capabilities. It achieves breakthroughs in semantic understanding and prompt following.\n\nOptional prompts:\nSet the aspect ratio (available values: `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`). Set to `16:9` as default.\nSet resolution (one of `480p`,`720p`,`1080p` to set the video resolution. Set to `1080p` as default.\nSet video duration (3s to 12s). Set to `5s` as default.\n\nNotes:\nNumber of video tokens calculated for pricing is approximately: `height * width * fps * duration / 1024).\nFile attachment accepted: jpeg, png, webp", "owned_by": "Bytedance", "root": "seedance-1.0-pro-fast", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["video"], "modality": "text,image->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Seedance-1.0-Pro-Fast", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6527652-200-khbstcxheeudjqxzuzwfdquxbbivgwzw.jpeg", "alt": "Seedance-1.0-Pro-Fast model icon", "width": 200, "height": 200}, "url": "https://poe.com/seedance-1.0-pro-fast"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["21:9", "16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "16:9"}, {"name": "resolution", "schema": {"enum": ["480p", "720p", "1080p"]}, "default_value": "1080p"}, {"name": "duration", "schema": {"enum": ["3", "4", "5", "6", "7", "8", "9", "10", "11", "12"]}, "default_value": "5", "description": "Video duration in seconds"}]}, {"id": "omnihuman", "object": "model", "created": 1753875678785, "description": "OmniHuman, by Bytedance, generates video using an image of a human figure paired with an audio file. It produces vivid, high-quality videos where the character\u2019s emotions and movements maintain a strong correlation with the audio. Send an image including a human figure with a visible face, and an audio, and the bot will return a video. The maximum audio length accepted is 30 seconds.", "owned_by": "Bytedance", "root": "omnihuman", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "OmniHuman", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6277273-200-frkjphqclxxhvtzjzegrnsuxjlubrumm.jpeg", "alt": "OmniHuman model icon", "width": 200, "height": 200}, "url": "https://poe.com/omnihuman"}, "reasoning": null, "parameters": []}, {"id": "grok-code-fast-1", "object": "model", "created": 1755884835039, "description": "Grok-Code-Fast-1 from xAI is a high-performance, cost-efficient model designed for agentic coding. It offers visible reasoning traces, strong steerability, and supports a 256k context window.", "owned_by": "XAI", "root": "grok-code-fast-1", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.000000202", "completion": "0.0000015152", "image": null, "request": null, "input_cache_read": "0.0000000202", "input_cache_write": null}, "context_window": {"context_length": 256000, "max_output_tokens": null}, "context_length": 256000, "metadata": {"display_name": "Grok-Code-Fast-1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6351729-200-ayhigssyjillkqpbnugirdlispkubknu.jpeg", "alt": "Grok-Code-Fast-1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/grok-code-fast-1"}, "reasoning": null, "parameters": []}, {"id": "deep-ai-search", "object": "model", "created": 1753262625533, "description": "Deep search engine that integrates Brave AI with real-time web search. This research assistant executes commands, validates facts and scrapes websites at scale while preserving its hallmark speed and intelligence advantage. The bot doesn't accept file attachments.\n\nExamples:\nhttps://poe.com/s/HZSVi8Ma2qoN9Qx4QBKR\nhttps://poe.com/s/P0BQmsvbE7zusdY0n49l\nhttps://poe.com/s/QgQSPsLD9efQrIwbmwuO", "owned_by": "Open-Source-Lab", "root": "deep-ai-search", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Deep-AI-Search", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6249935-200-ywgdrjnhpcmzrecgmaxljbjfcfxyfxmb.jpeg", "alt": "Deep-AI-Search model icon", "width": 200, "height": 200}, "url": "https://poe.com/deep-ai-search"}, "reasoning": null, "parameters": []}, {"id": "kling-avatar-pro", "object": "model", "created": 1758919888726, "description": "Create lifelike avatar videos featuring realistic humans, animals, cartoons, or stylized characters. Simply upload an image and an audio file to generate a video of your character speaking.\n\nSupported file formats:\nImages: JPEG, PNG, WEBP\nAudio: MP3, WAV", "owned_by": "fal", "root": "kling-avatar-pro", "architecture": {"input_modalities": ["text", "image", "audio"], "output_modalities": ["video"], "modality": "text,image,audio->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Kling-Avatar-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6453747-200-awtrmzzgttzbitwqmingrunzbedkiahu.jpeg", "alt": "Kling-Avatar-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/kling-avatar-pro"}, "reasoning": null, "parameters": []}, {"id": "luma-photon", "object": "model", "created": 1733181326256, "description": "Luma Photon delivers industry-specific visual excellence, crafting images that align perfectly with professional standards - not just generic AI art. From marketing to creative design, each generation is purposefully tailored to your industry's unique requirements. \n\nOptional parameters:\nAspect ratio to change the aspect ratio of your generations (1:1, 16:9, 9:16, 4:3, 3:4, 21:9, 9:21 are supported). \n\nNote: Prompt input cannot exceed 5,000 characters.", "owned_by": "fal", "root": "luma-photon", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Luma-Photon", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5360374-200-uwystravnvoonxzssimpworyoetjlvwy.jpeg", "alt": "Luma-Photon model icon", "width": 200, "height": 200}, "url": "https://poe.com/luma-photon"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "9:21"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "ideogram", "object": "model", "created": 1712178346331, "description": "Excels at creating high-quality images from text prompts. For most prompts, https://poe.com/Ideogram-v2 will produce better results. Allows users to specify the aspect ratio of the image using the \"--aspect\" parameter at the end of the prompt (e.g. \"Tall trees, daylight --aspect 9:16\"). Valid aspect ratios are 10:16, 16:10, 9:16, 16:9, 3:2, 2:3, 4:3, 3:4, & 1:1.\nBot does not accept attachments.", "owned_by": "IdeogramAI", "root": "ideogram", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.045", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 150, "max_output_tokens": null}, "context_length": 150, "metadata": {"display_name": "Ideogram", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3933897-200-xnrwscymyhjafossfrkwzbcddolnnebi.jpeg", "alt": "Ideogram model icon", "width": 200, "height": 200}, "url": "https://poe.com/ideogram"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "16:10", "3:2", "4:3", "1:1", "9:16", "10:16", "2:3", "3:4"]}, "default_value": "1:1"}]}, {"id": "seededit-3.0", "object": "model", "created": 1754502655602, "description": "SeedEdit 3.0 is an image editing model independently developed by ByteDance. It excels in accurately following editing instructions and effectively preserving image content, especially excelling in handling real images. Please send an image with a prompt to edit the image.", "owned_by": "Bytedance", "root": "seededit-3.0", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "SeedEdit-3.0", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6299901-200-uryltyotomrywzvbcsichxzpppaxdljt.jpeg", "alt": "SeedEdit-3.0 model icon", "width": 200, "height": 200}, "url": "https://poe.com/seededit-3.0"}, "reasoning": null, "parameters": []}, {"id": "kling-2.1-pro", "object": "model", "created": 1748544740987, "description": "Kling 2.1 Pro is an advanced endpoint for the Kling 2.1 model, offering professional-grade videos with enhanced visual fidelity, precise camera movements, and dynamic motion control, perfect for cinematic storytelling. \n\nOptional parameters:\n- Negative prompt. Type things to avoid in generated images\n- CFG Scale. To send a classifier-free guidance scale between 0.0 and 1.0. This is set to 0.5 as default\n- Set Duration. Select from (5 seconds or 10 seconds) to specify video length in seconds. Set to 5 seconds as default", "owned_by": "fal", "root": "kling-2.1-pro", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Kling-2.1-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6071482-200-miavykwdwtiowaqyxhqaflbcukdeujou.jpeg", "alt": "Kling-2.1-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/kling-2.1-pro"}, "reasoning": null, "parameters": [{"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "blur, distort, and low quality"}, {"name": "cfg_scale", "schema": {"type": "number", "minimum": 0.0, "maximum": 1.0}, "default_value": 0.5, "description": "Classifer Guidance Scale for generation."}, {"name": "duration", "schema": {"enum": ["5", "10"]}, "default_value": "5", "description": "Video duration in seconds"}]}, {"id": "kling-2.1-std", "object": "model", "created": 1748545509401, "description": "Kling 2.1 Standard is a cost-efficient endpoint for the Kling 2.1 model, delivering high-quality image-to-video generation. \n\nOptional parameters:\n- Negative prompt. Type things to avoid in generated images\n- CFG Scale. To send a classifier-free guidance scale between 0.0 and 1.0. This is set to 0.5 as default\n- Set Duration. Select from (5 seconds or 10 seconds) to specify video length in seconds. Set to 5 seconds as default\n\nNote: This bot can only process 1 image at a time.", "owned_by": "fal", "root": "kling-2.1-std", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Kling-2.1-Std", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6071504-200-zqrdusgqwboferuzxwalzhrpexoajwke.jpeg", "alt": "Kling-2.1-Std model icon", "width": 200, "height": 200}, "url": "https://poe.com/kling-2.1-std"}, "reasoning": null, "parameters": [{"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "blur, distort, and low quality"}, {"name": "cfg_scale", "schema": {"type": "number", "minimum": 0.0, "maximum": 1.0}, "default_value": 0.5, "description": "Classifer Guidance Scale for generation."}, {"name": "duration", "schema": {"enum": ["5", "10"]}, "default_value": "5", "description": "Video duration in seconds"}]}, {"id": "runway-gen-4-turbo", "object": "model", "created": 1746825004531, "description": "Runway's Gen-4 Turbo model creates best-in-class, controllable, and high-fidelity video generations based on your prompts. Both text inputs (max 1000 characters) and image inputs are supported, but we recommend using image inputs for best results. \n\nOptional parameters:\n\nAspect ratio (16:9, 1:1, 9:16) for landscape/portrait videos. \nDuration (5, 10) to specify video length in seconds. \n\nFull prompting guide here: https://help.runwayml.com/hc/en-us/articles/39789879462419-Gen-4-Video-Prompting-Guide", "owned_by": "RunwayML", "root": "runway-gen-4-turbo", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["video"], "modality": "text,image->video"}, "supported_features": [], "supported_endpoints": ["/v1/videos"], "pricing": null, "context_window": {"context_length": 256, "max_output_tokens": null}, "context_length": 256, "metadata": {"display_name": "Runway-Gen-4-Turbo", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6003903-200-asmxgypvwyudvtqwhrkduzwxsarmxfmt.jpeg", "alt": "Runway-Gen-4-Turbo model icon", "width": 200, "height": 200}, "url": "https://poe.com/runway-gen-4-turbo"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["16:9", "9:16", "1:1"]}, "default_value": "16:9"}, {"name": "duration", "schema": {"enum": ["5", "10"]}, "default_value": "5"}]}, {"id": "runway", "object": "model", "created": 1728610474100, "description": "Runway's Gen-3 Alpha Turbo model creates best-in-class, controllable, and high-fidelity video generations based on your prompts. Both text inputs (max 1000 characters) and image inputs are supported, but we recommend using image inputs for best results. \n\nParameter controls:\nAspect_ratio (16:9, 9:16) for landscape/portrait videos. \nDuration (5, 10) to specify video length in seconds. ", "owned_by": "RunwayML", "root": "runway", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["video"], "modality": "text,image->video"}, "supported_features": [], "supported_endpoints": ["/v1/videos"], "pricing": null, "context_window": {"context_length": 256, "max_output_tokens": null}, "context_length": 256, "metadata": {"display_name": "Runway", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5078946-200-jsndnxbvsncuxazsaoakhffbbgwtkhup.jpeg", "alt": "Runway model icon", "width": 200, "height": 200}, "url": "https://poe.com/runway"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["16:9", "9:16"]}, "default_value": "16:9"}, {"name": "duration", "schema": {"enum": ["5", "10"]}, "default_value": "5"}]}, {"id": "veo-2", "object": "model", "created": 1733117805122, "description": "Veo 2 creates incredibly high-quality videos in a wide range of subjects and styles. It brings an improved understanding of real-world physics and the nuances of human movement and expression, which helps improve its detail and realism overall. Veo 2 understands the unique language of cinematography: ask it for a genre, specify a lens, suggest cinematic effects and Veo 2 will deliver in 8-second clips. Use `--aspect_ratio` (16:9 or 9:16) to customize video aspect ratio. Supports text-to-video as well as image-to-video. Non english input will be translated first. Note: currently has low rate limit so you may need to retry your request at times of peak usage.", "owned_by": "Google", "root": "veo-2", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": ["/v1/videos"], "pricing": null, "context_window": {"context_length": 480, "max_output_tokens": null}, "context_length": 480, "metadata": {"display_name": "Veo-2", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5356474-200-ibzsqagpmxpivhmtlxiefknlknxoibxi.jpeg", "alt": "Veo-2 model icon", "width": 200, "height": 200}, "url": "https://poe.com/veo-2"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["16:9", "9:16"]}, "default_value": "16:9"}, {"name": "no", "schema": {"type": "string"}}, {"name": "duration", "schema": {"enum": ["5", "6", "7", "8"]}, "default_value": "8"}, {"name": "seed", "schema": {"type": "string"}}]}, {"id": "kling-2.0-master", "object": "model", "created": 1744698597290, "description": "Generate high-quality videos from text or images using Kling 2.0 Master. Use `--negative_prompt` to send a negative prompt, and `--cfg_scale` to send a classifier-free guidance scale between 0.0 and 1.0 (inclusive). Use `--aspect` to set the aspect ratio (One of `16:9`, `9:16` and `1:1`). Use `--duration` to set either 5 or 10 second video.", "owned_by": "fal", "root": "kling-2.0-master", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Kling-2.0-Master", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5918230-200-zeuncibludpfobwdjkbcfdypdfkuipem.jpeg", "alt": "Kling-2.0-Master model icon", "width": 200, "height": 200}, "url": "https://poe.com/kling-2.0-master"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "1:1", "9:16"]}, "default_value": "16:9"}, {"name": "negative_prompt", "schema": {"type": "string"}, "default_value": "blur, distort, and low quality"}, {"name": "cfg_scale", "schema": {"type": "number", "minimum": 0.0, "maximum": 1.0}, "default_value": 0.5, "description": "Classifer Guidance Scale for generation."}, {"name": "duration", "schema": {"enum": ["5", "10"]}, "default_value": "5", "description": "Video duration in seconds"}]}, {"id": "qwen-edit", "object": "model", "created": 1755628345426, "description": "Image editing model based on Qwen-Image, with superior text editing capabilities.", "owned_by": "fal", "root": "qwen-edit", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen-Edit", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6341471-200-xkawjgzzpandmhdibxpigatstmfwvqrp.jpeg", "alt": "Qwen-Edit model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen-edit"}, "reasoning": null, "parameters": []}, {"id": "gptzero", "object": "model", "created": 1761948657951, "description": "GPTZero is a deep-learning-driven platform designed to analyze and flag portions of text that are likely generated by AI vs. human authors. It distinguishes between \"entirely human,\" \"entirely AI,\" or \"mixed\" content and highlights the specific sentences involved. It can also perform bibliography scans to verify citations and references, and source analysis to find supporting sources for claims in your text.\n\n*Max number of files that can be submitted simultaneously is 50, and the max file size for all files combined is 15 MB. Each file's document will be truncated to 50,000 characters.\n\nSupported file types: PDF, DOC/DOCX, TXT, ODT\n\nParameter controls available:\n1. Scan Type (drop-down):\n   - AI Detection (default): Detect AI-generated text\n   - Bibliography Scan: Analyze citations & references\n   - Source Analysis: Find sources for claims in your text\n\n2. AI Detection Options (shown when Scan Type = AI Detection):\n   - Model Version: Select a specific GPTZero model version or use Latest (auto) for the newest\n   - Multilingual: Enable GPTZero's multilingual model for text scans (supports French, Spanish, etc.)\n   - AI Highlight Threshold: Probability cutoff for flagging sentences as AI-generated (default 0.70, range 0.10\u20130.99). Lower = more sensitive\n   - Max Highlighted Sentences: Limit how many flagged sentences appear in the report (default 15, range 1\u201350)\n\n3. Source Analysis Options (shown when Scan Type = Source Analysis):\n   - Sentence or Claim (optional text area): Specify one exact sentence or claim to check. If left blank, the full message is used\n   - Max Sources per Claim: How many sources to retrieve per claim (default 3, range 1\u201310)\n   - Claim Extractor: Method used to identify claims, ClaimBuster (fast) or LLM Extractor (more thorough)", "owned_by": "EmpirioLabs AI", "root": "gptzero", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "GPTZero", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6546470-200-rbucbmusmzupptmhmlutgwocqbilltrt.jpeg", "alt": "GPTZero model icon", "width": 200, "height": 200}, "url": "https://poe.com/gptzero"}, "reasoning": null, "parameters": [{"name": "scan_type", "schema": {"enum": ["ai_detection", "bibliography", "sources"]}, "default_value": "ai_detection", "description": "AI Detection: Detect AI-generated text. Bibliography Scan: Analyze citations & references. Source Analysis: Find sources for claims in your text."}, {"name": "model_version", "schema": {"enum": ["__latest__", "2026-03-11-base", "2026-02-14-base", "2026-01-20-base", "2025-12-04-multilingual", "2025-11-09-multilingual", "2025-09-04-base", "2025-08-22-base", "2025-05-02-base"]}, "default_value": "__latest__", "description": "Select a specific GPTZero model version, or Latest for the newest. Choosing an explicit multilingual release overrides the separate multilingual switch."}, {"name": "multilingual", "schema": {"type": "boolean"}, "default_value": false, "description": "This maps to GPTZero's separate multilingual request field for text scans when Model Version is Latest (auto). File scans only use the selected model version."}, {"name": "ai_threshold", "schema": {"type": "number", "minimum": 0.1, "maximum": 0.99}, "default_value": 0.7, "description": "Probability cutoff for flagging sentences as AI-generated. Lower = more sensitive."}, {"name": "max_sentences", "schema": {"type": "number", "minimum": 1, "maximum": 50}, "default_value": 15, "description": "Maximum number of sentences shown in the sentence highlights section."}, {"name": "source_sentence", "schema": {"type": "string"}, "default_value": "", "description": "Paste the full passage or context in the main Poe message box. Optionally put one exact sentence or claim here. If left blank, the bot uses the full Poe message as the claim."}, {"name": "max_sources", "schema": {"type": "number", "minimum": 1, "maximum": 10}, "default_value": 3, "description": "Maximum number of sources to retrieve for each identified claim."}, {"name": "claim_extractor", "schema": {"enum": ["claimbuster", "llm_claim_extractor"]}, "default_value": "claimbuster", "description": "Method used to identify claims in your text. ClaimBuster is faster; the LLM extractor is more thorough."}]}, {"id": "kling-pro-effects", "object": "model", "created": 1743698583798, "description": "Generate videos with effects like squishing an object, two people hugging, making heart gestures, etc. using Kling-Pro-Effects. Requires an image input. Send a single image for `squish` and `expansion` effects and two images (of people) for `hug`, `kiss`, and `heart_gesture` effects. Set effect with --effect. Default effect: `squish`. Set duration with `--duration` with either 5s or 10s, set to 5s by default.", "owned_by": "fal", "root": "kling-pro-effects", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Kling-Pro-Effects", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5874244-200-qimayfqswajzfbbeoocwxtmfmtpmpwpd.jpeg", "alt": "Kling-Pro-Effects model icon", "width": 200, "height": 200}, "url": "https://poe.com/kling-pro-effects"}, "reasoning": null, "parameters": [{"name": "duration", "schema": {"enum": ["5", "10"]}, "default_value": "5", "description": "Video duration in seconds"}, {"name": "effect", "schema": {"enum": ["hug", "kiss", "heart_gesture", "squish", "expansion"]}, "default_value": "squish", "description": "Video effects"}]}, {"id": "hailuo-live", "object": "model", "created": 1734370063740, "description": "Hailuo Live, the latest model from Minimax, sets a new standard for bringing still images to life. From breathtakingly vivid motion to finely tuned expressions, this state-of-the-art model enables your characters to captivate, move, and shine like never before. It excels in bring art and drawings to life, exceptional realism without morphing, emotional range, and unparalleled character consistency. Generates 5 second video.", "owned_by": "fal", "root": "hailuo-live", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["video"], "modality": "text,image->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Hailuo-Live", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5427382-200-rtllkixwtqfzctiovwnnozxnybczdqfz.jpeg", "alt": "Hailuo-Live model icon", "width": 200, "height": 200}, "url": "https://poe.com/hailuo-live"}, "reasoning": null, "parameters": []}, {"id": "hailuo-ai", "object": "model", "created": 1729194728486, "description": "Best-in-class text and image to video model by MiniMax.", "owned_by": "fal", "root": "hailuo-ai", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Hailuo-AI", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5117435-200-poindnzhlfwddmannizkdudeofubxulg.jpeg", "alt": "Hailuo-AI model icon", "width": 200, "height": 200}, "url": "https://poe.com/hailuo-ai"}, "reasoning": null, "parameters": []}, {"id": "veo-2-video", "object": "model", "created": 1740172728462, "description": "Veo2 is Google's cutting-edge video generation model. Veo creates videos with realistic motion and high quality output.", "owned_by": "fal", "root": "veo-2-video", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Veo-2-Video", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5696451-200-ckijnzgbsgbyfoeynrhdshmcwuoetlwf.jpeg", "alt": "Veo-2-Video model icon", "width": 200, "height": 200}, "url": "https://poe.com/veo-2-video"}, "reasoning": null, "parameters": []}, {"id": "wan-2.1", "object": "model", "created": 1741001573656, "description": "Wan-2.1 is a text-to-video and image-to-video model that generates high-quality videos with high visual quality and motion diversity from text prompts. Generates 5 second video.", "owned_by": "fal", "root": "wan-2.1", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Wan-2.1", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5740414-200-liifzckijnzgbsgbyfoeynrhdshmcwuo.jpeg", "alt": "Wan-2.1 model icon", "width": 200, "height": 200}, "url": "https://poe.com/wan-2.1"}, "reasoning": null, "parameters": []}, {"id": "ideogram-v2a-turbo", "object": "model", "created": 1740678577836, "description": "Fast, affordable text-to-image model, optimized for graphic design and photography. For higher quality, use https://poe.com/Ideogram-v2A\n\nNote: Supported file type: JPEG, WebP and PNG. \n\nOptional parameters:\nAspect to set the aspect ratio. Select from 16:9, 16:10, 3:2, 4:3, 1:1, 3:4, 2:3, 10:16, 9:16. Default to 1:1.\nStyle to specify a style (one of `GENERAL`, `REALISTIC`, `DESIGN`, `3D RENDER` and `ANIME` default: `GENERAL`.)", "owned_by": "IdeogramAI", "root": "ideogram-v2a-turbo", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.024", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 150, "max_output_tokens": null}, "context_length": 150, "metadata": {"display_name": "Ideogram-v2a-Turbo", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5722948-200-jbanwijxokqokidbqlfcxujiqgffqvii.jpeg", "alt": "Ideogram-v2a-Turbo model icon", "width": 200, "height": 200}, "url": "https://poe.com/ideogram-v2a-turbo"}, "reasoning": null, "parameters": [{"name": "style", "schema": {"enum": ["GENERAL", "REALISTIC", "DESIGN", "RENDER_3D", "ANIME"]}, "default_value": "GENERAL"}, {"name": "aspect", "schema": {"enum": ["16:9", "16:10", "3:2", "4:3", "1:1", "9:16", "10:16", "2:3", "3:4"]}, "default_value": "1:1"}]}, {"id": "ideogram-v2a", "object": "model", "created": 1740678539688, "description": "Fast, affordable text-to-image model, optimized for graphic design and photography. For faster and more cost-effective generations, use https://poe.com/Ideogram-v2A-Turbo.\nNote: Supported file type: JPEG, WebP and PNG.\n\nOptional parameters:\nAspect to set the aspect ratio. Valid aspect ratios are 10:16, 16:10, 9:16, 16:9, 3:2, 2:3, 4:3, 3:4, & 1:1.\nStyle to specify a style (one of `GENERAL`, `REALISTIC`, `DESIGN`, `3D RENDER` and `ANIME` default: `GENERAL`.)", "owned_by": "IdeogramAI", "root": "ideogram-v2a", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.039", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 150, "max_output_tokens": null}, "context_length": 150, "metadata": {"display_name": "Ideogram-v2a", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5722945-200-xjgieohseevtvhlmusozitdnpguwljyk.jpeg", "alt": "Ideogram-v2a model icon", "width": 200, "height": 200}, "url": "https://poe.com/ideogram-v2a"}, "reasoning": null, "parameters": [{"name": "style", "schema": {"enum": ["GENERAL", "REALISTIC", "DESIGN", "RENDER_3D", "ANIME"]}, "default_value": "GENERAL"}, {"name": "aspect", "schema": {"enum": ["16:9", "16:10", "3:2", "4:3", "1:1", "9:16", "10:16", "2:3", "3:4"]}, "default_value": "1:1"}]}, {"id": "trellis-3d", "object": "model", "created": 1743054517902, "description": "Generate 3D models from your images using Trellis, a native 3D generative model enabling versatile and high-quality 3D asset creation. Send an image to convert it into a 3D model.", "owned_by": "fal", "root": "trellis-3d", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Trellis-3D", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5843742-200-eaalfyrkgdmvkkqslqhhkpgfbqfigxlp.jpeg", "alt": "Trellis-3D model icon", "width": 200, "height": 200}, "url": "https://poe.com/trellis-3d"}, "reasoning": null, "parameters": []}, {"id": "flux-dev-finetuner", "object": "model", "created": 1727479142160, "description": "Fine-tune the FLUX dev model with your own pictures! Upload 8-12 of them (same subject, only one subject in the picture, ideally from different poses and backgrounds) and wait ~2-5 minutes to create your own finetuned bot that will generate pictures of this subject in whatever setting you want.", "owned_by": "fal", "root": "flux-dev-finetuner", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "FLUX-dev-finetuner", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5008462-200-vymehwmsdpkfssousiwayxprakkqyqgj.jpeg", "alt": "FLUX-dev-finetuner model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-dev-finetuner"}, "reasoning": null, "parameters": []}, {"id": "flux-inpaint", "object": "model", "created": 1736797755390, "description": "Given an image and a mask (separate images), fills in the region of the image given by the mask as per the prompt. The base image should be the first image attached and the black-and-white mask should be the second image; a text prompt is required and should specify what you want the model to inpaint in the white area of the mask.", "owned_by": "fal", "root": "flux-inpaint", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "FLUX-Inpaint", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5541160-200-rmivbkoymqoyizstzgybzeeznznnvgtg.jpeg", "alt": "FLUX-Inpaint model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-inpaint"}, "reasoning": null, "parameters": []}, {"id": "flux-fill", "object": "model", "created": 1736787123399, "description": "Given an image and a mask (separate images), fills in the region of the image given by the mask as per the prompt. The base image should be the first image attached and the black-and-white mask should be the second image; a text prompt is required and should specify what you want the model to inpaint in the white area of the mask.", "owned_by": "fal", "root": "flux-fill", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "FLUX-Fill", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5540651-200-sgqqktqksbtecthfedszizvwtjkrelop.jpeg", "alt": "FLUX-Fill model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-fill"}, "reasoning": null, "parameters": []}, {"id": "bria-eraser", "object": "model", "created": 1739957916196, "description": "Bria Eraser enables precise removal of unwanted objects from images while maintaining high-quality outputs. Trained exclusively on licensed data for safe and risk-free commercial use. Send an image and a black-and-white mask image denoting the objects to be cleared out from the image. The input prompt is only used to create the filename of the output image.", "owned_by": "fal", "root": "bria-eraser", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Bria-Eraser", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5685722-200-wyzpqxkeopjarifvxgavinsrornwatol.jpeg", "alt": "Bria-Eraser model icon", "width": 200, "height": 200}, "url": "https://poe.com/bria-eraser"}, "reasoning": null, "parameters": []}, {"id": "kling-1.5-pro", "object": "model", "created": 1733347438699, "description": "Kling-1.5-Pro video generation bot, hosted by fal.ai. For best results, upload an image attachment. \n\nThis bot supports optional parameters for additional customization.", "owned_by": "fal", "root": "kling-1.5-pro", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["video"], "modality": "text,image->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Kling-1.5-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5370453-200-dwfnlmyrxleyrknybkpspazdfuwxkqih.jpeg", "alt": "Kling-1.5-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/kling-1.5-pro"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "1:1", "9:16"]}, "default_value": "16:9"}, {"name": "duration", "schema": {"enum": ["5", "10"]}, "default_value": "5", "description": "Video duration in seconds"}]}, {"id": "deepreasoning", "object": "model", "created": 1740454833334, "description": "DeepReasoning (previously DeepClaude) is a high-performance LLM inference that combines DeepSeek R1's Chain of Thought (CoT) reasoning capabilities with Anthropic Claude's creative and code generation prowess. It provides a unified interface for leveraging the strengths of both models while maintaining complete control over your data. Learn more: https://deepclaude.com/\n\nSupported file type upload: PDF, TXT, PNG, JPG, JPEG\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "deepreasoning", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "DeepReasoning", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5708020-200-wlgmhyltpxxutdsuvvkqssgxbiuwythl.jpeg", "alt": "DeepReasoning model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepreasoning"}, "reasoning": null, "parameters": [{"name": "anthropic_model", "schema": {"enum": ["claude-sonnet-4-5-20250929", "claude-haiku-4-5-20251001", "claude-opus-4-5-20251101", "claude-sonnet-4-20250514", "claude-opus-4-1-20250805", "claude-opus-4-20250514"]}, "default_value": "claude-sonnet-4-5-20250929", "description": "Choose the Claude model to pair with DeepSeek R1 0528 reasoning."}]}, {"id": "gemma-3-27b", "object": "model", "created": 1742186137210, "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to Gemma 2", "owned_by": "EmpirioLabs AI", "root": "gemma-3-27b", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Gemma-3-27B", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5801299-200-sskptvhsvjtbrmtkladcyctahhmxfsob.jpeg", "alt": "Gemma-3-27B model icon", "width": 200, "height": 200}, "url": "https://poe.com/gemma-3-27b"}, "reasoning": null, "parameters": []}, {"id": "mistral-small-3", "object": "model", "created": 1738360161146, "description": "Mistral Small 3 is a pre-trained and instructed model catered to the \u201880%\u2019 of generative AI tasks--those that require robust language and instruction following performance, with very low latency. Released under an Apache 2.0 license and comparable to Llama-3.3-70B and Qwen2.5-32B-Instruct.", "owned_by": "Mistral", "root": "mistral-small-3", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": ["/v1/chat/completions"], "pricing": {"prompt": "0.000000101", "completion": "0.000000303", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": 4096}, "context_length": 128000, "metadata": {"display_name": "Mistral-Small-3", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-7012-200-oelvcswpytpieygsqdymsppwvpwoqdob.jpeg", "alt": "Mistral-Small-3 model icon", "width": 200, "height": 200}, "url": "https://poe.com/mistral-small-3"}, "reasoning": null, "parameters": []}, {"id": "deepseek-v3-di", "object": "model", "created": 1739797458982, "description": "Deepseek-v3 \u2013 the new top open-source LLM. Achieves state-of-the-art performance in tasks such as coding, mathematics, and reasoning. All data you submit to this bot is governed by the Poe privacy policy and is only sent to DeepInfra, a US-based company.\n\nSupports 64k tokens of input context and 8k tokens of output context. Quantization: FP8 (official).", "owned_by": "DeepInfra", "root": "deepseek-v3-di", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0044", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 64000, "max_output_tokens": null}, "context_length": 64000, "metadata": {"display_name": "DeepSeek-V3-DI", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5677175-200-eavnooylinrrqviqscfzywmijwagjarg.jpeg", "alt": "DeepSeek-V3-DI model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepseek-v3-di"}, "reasoning": null, "parameters": []}, {"id": "deepseek-v3-turbo-di", "object": "model", "created": 1741250579199, "description": "Deepseek-v3 \u2013 the new top open-source LLM. Achieves state-of-the-art performance in tasks such as coding, mathematics, and reasoning. Turbo variant is quantized to achieve higher speeds. All data you submit to this bot is governed by the Poe privacy policy and is only sent to DeepInfra, a US-based company.\n\nSupports 32k tokens of input context and 8k tokens of output context. Quantization: FP4 (turbo).", "owned_by": "DeepInfra", "root": "deepseek-v3-turbo-di", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0059", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 32000, "max_output_tokens": null}, "context_length": 32000, "metadata": {"display_name": "DeepSeek-V3-Turbo-DI", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5755273-200-ymnmqmdqngemljjwxndlpzlenfcpfapl.jpeg", "alt": "DeepSeek-V3-Turbo-DI model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepseek-v3-turbo-di"}, "reasoning": null, "parameters": []}, {"id": "phi-4-di", "object": "model", "created": 1740490334949, "description": "Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed.\n\nAt 14 billion parameters, it was trained on a mix of high-quality synthetic datasets, data from curated websites, and academic materials. It has undergone careful improvement to follow instructions accurately and maintain strong safety standards. It works best with English language inputs.\n\nAll data you provide this bot will not be used in training, and is sent only to DeepInfra, a US-based company.\n\nSupports 16k tokens of input context and 8k tokens of output context. Quantization: FP16 (official).", "owned_by": "DeepInfra", "root": "phi-4-di", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.00030", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 16000, "max_output_tokens": null}, "context_length": 16000, "metadata": {"display_name": "Phi-4-DI", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5710104-200-pkfvavvnpndbgbhyboaycbfvfvsqtcaj.jpeg", "alt": "Phi-4-DI model icon", "width": 200, "height": 200}, "url": "https://poe.com/phi-4-di"}, "reasoning": null, "parameters": []}, {"id": "mistral-7b-v0.3-di", "object": "model", "created": 1740490886743, "description": "Mistral Instruct 7B v0.3 from Mistral AI.\n\nAll data you provide this bot will not be used in training, and is sent only to DeepInfra, a US-based company.\n\nSupports 32k tokens of input context and 8k tokens of output context. Quantization: FP16 (official).", "owned_by": "DeepInfra", "root": "mistral-7b-v0.3-di", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.00015", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 32000, "max_output_tokens": null}, "context_length": 32000, "metadata": {"display_name": "Mistral-7B-v0.3-DI", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5710141-200-hpycxbxdjpyusoybfcqtiizgrecfejmh.jpeg", "alt": "Mistral-7B-v0.3-DI model icon", "width": 200, "height": 200}, "url": "https://poe.com/mistral-7b-v0.3-di"}, "reasoning": null, "parameters": []}, {"id": "liveportrait", "object": "model", "created": 1720556185003, "description": "Animates given portraits with the motion's in the video. Powered by fal.ai", "owned_by": "fal", "root": "liveportrait", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "LivePortrait", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-4562355-200-keofzhrnpnyiglsjgftwqklymqhmhnyk.jpeg", "alt": "LivePortrait model icon", "width": 200, "height": 200}, "url": "https://poe.com/liveportrait"}, "reasoning": null, "parameters": []}, {"id": "stablediffusion3-2b", "object": "model", "created": 1718216691252, "description": "Stable Diffusion v3 Medium - by fal.ai", "owned_by": "fal", "root": "stablediffusion3-2b", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "StableDiffusion3-2B", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-4402118-200-woqnbpfnmnrkixcgbmmxxbdvomiyhywe.jpeg", "alt": "StableDiffusion3-2B model icon", "width": 200, "height": 200}, "url": "https://poe.com/stablediffusion3-2b"}, "reasoning": null, "parameters": []}, {"id": "mixtral8x22b-inst-fw", "object": "model", "created": 1712949013942, "description": "Mixtral 8x22B Mixture-of-Experts instruct model from Mistral hosted by Fireworks. ", "owned_by": "Fireworks AI", "root": "mixtral8x22b-inst-fw", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0036", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 65536, "max_output_tokens": null}, "context_length": 65536, "metadata": {"display_name": "Mixtral8x22b-Inst-FW", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3993736-200-bfevqevrnmmcehczovuycpxismwvsfgp.jpeg", "alt": "Mixtral8x22b-Inst-FW model icon", "width": 200, "height": 200}, "url": "https://poe.com/mixtral8x22b-inst-fw"}, "reasoning": null, "parameters": []}, {"id": "mistral-large-2", "object": "model", "created": 1708971504266, "description": "Mistral's latest text generation model (Mistral-Large-2407) with top-tier reasoning capabilities. It can be used for complex multilingual reasoning tasks, including text understanding, transformation, and code generation. This bot has the full 128k context window supported by the model.", "owned_by": "Mistral", "root": "mistral-large-2", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": ["/v1/chat/completions"], "pricing": {"prompt": "0.0000030303", "completion": "0.0000090909", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": 4096}, "context_length": 128000, "metadata": {"display_name": "Mistral-Large-2", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-7010-200-jaspeixxffhayqwvhydkkjjmjwtjzgrv.jpeg", "alt": "Mistral-Large-2 model icon", "width": 200, "height": 200}, "url": "https://poe.com/mistral-large-2"}, "reasoning": null, "parameters": []}, {"id": "dall-e-3", "object": "model", "created": 1699306131647, "description": "OpenAI's most powerful image generation model. Generates high quality images with intricate details based on the user's most recent prompt. For most prompts, https://poe.com/FLUX-pro-1.1-ultra or https://poe.com/FLUX-dev or https://poe.com/Imagen3 will produce better results. \n\nOptional parameters:\nAspect Ratio to select an aspect ratio. Valid aspect ratios are 1:1, 7:4, & 4:7.", "owned_by": "OpenAI", "root": "dall-e-3", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": ["/v1/images"], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.045", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 800, "max_output_tokens": null}, "context_length": 800, "metadata": {"display_name": "DALL-E-3", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-2828029-200-mlvmbysbpfpcjfyxswvxbzufpvszchqb.jpeg", "alt": "DALL-E-3 model icon", "width": 200, "height": 200}, "url": "https://poe.com/dall-e-3"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["1:1", "7:4", "4:7"]}, "default_value": "1:1"}]}, {"id": "reka-core", "object": "model", "created": 1713038207102, "description": "Reka's largest and most capable multimodal language model. Works with text, images, and video inputs. 8k context length.", "owned_by": "Reka AI", "root": "reka-core", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "Reka-Core", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3999947-200-diobkezragtoakpszjrzxbovttmxiktj.jpeg", "alt": "Reka-Core model icon", "width": 200, "height": 200}, "url": "https://poe.com/reka-core"}, "reasoning": null, "parameters": []}, {"id": "reka-flash", "object": "model", "created": 1707892216404, "description": "Reka's efficient and capable 21B multimodal model optimized for fast workloads and amazing quality. Works with text, images and video inputs.", "owned_by": "Reka AI", "root": "reka-flash", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": {"context_length": 128000, "max_output_tokens": null}, "context_length": 128000, "metadata": {"display_name": "Reka-Flash", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3607788-200-cfiokftcrqzusmywgzeibtkvpqtmmjpy.jpeg", "alt": "Reka-Flash model icon", "width": 200, "height": 200}, "url": "https://poe.com/reka-flash"}, "reasoning": null, "parameters": []}, {"id": "gpt-3.5-turbo", "object": "model", "created": 1694610718926, "description": "OpenAI\u2019s GPT 3.5 Turbo model is a powerful language generation system designed to provide highly coherent, contextually relevant, and detailed responses. Supports 16,384 tokens of context. ", "owned_by": "OpenAI", "root": "gpt-3.5-turbo", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000004545", "completion": "0.0000013636", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 16384, "max_output_tokens": 2048}, "context_length": 16384, "metadata": {"display_name": "GPT-3.5-Turbo", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3004-200-usevzvvmpoyhfgfmfwagczjrcpfwpufw.jpeg", "alt": "GPT-3.5-Turbo model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-3.5-turbo"}, "reasoning": null, "parameters": []}, {"id": "sketch-to-image", "object": "model", "created": 1736176125104, "description": "Takes in sketches and converts them to colored images.", "owned_by": "fal", "root": "sketch-to-image", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Sketch-to-Image", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5512529-200-vcsulapoifatrxmpnubzpmxwkcwkatvw.jpeg", "alt": "Sketch-to-Image model icon", "width": 200, "height": 200}, "url": "https://poe.com/sketch-to-image"}, "reasoning": null, "parameters": []}, {"id": "stablediffusion3.5-t", "object": "model", "created": 1729817429663, "description": "Faster version of Stable Diffusion 3 Large, hosted by @fal. Excels for fast image generation. Use \"--aspect\" to select an aspect ratio (e.g --aspect 1:1).", "owned_by": "fal", "root": "stablediffusion3.5-t", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "StableDiffusion3.5-T", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5155879-200-upgrgnkfduxbatcaszulacjjfyvyahgq.jpeg", "alt": "StableDiffusion3.5-T model icon", "width": 200, "height": 200}, "url": "https://poe.com/stablediffusion3.5-t"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "flux-pro-1.1-t", "object": "model", "created": 1730863432942, "description": "The best state of the art image model from BFL. FLUX 1.1 Pro generates images six times faster than its predecessor, FLUX 1 Pro, while also improving image quality, prompt adherence, and output diversity. The bot does not support any attachments.", "owned_by": "Together AI", "root": "flux-pro-1.1-t", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.030", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 256, "max_output_tokens": null}, "context_length": 256, "metadata": {"display_name": "FLUX-pro-1.1-T", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5220409-200-wwylxwxlilbgdxwtqxmsdmxtitislywa.jpeg", "alt": "FLUX-pro-1.1-T model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-pro-1.1-t"}, "reasoning": null, "parameters": []}, {"id": "flux-schnell-t", "object": "model", "created": 1730862046687, "description": "Lightning-fast AI image generation model that excels in producing high-quality visuals in just seconds. Great for quick prototyping or real-time use cases. This is the fastest version of FLUX.1. \nThe bot does not support any attachments.", "owned_by": "Together AI", "root": "flux-schnell-t", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["image"], "modality": "text,image->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0021", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 256, "max_output_tokens": null}, "context_length": 256, "metadata": {"display_name": "Flux-Schnell-T", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5220273-200-pcunrweoawdpmzhvneukrjjcfnflgrxd.jpeg", "alt": "Flux-Schnell-T model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-schnell-t"}, "reasoning": null, "parameters": []}, {"id": "recraft-v3", "object": "model", "created": 1730322043217, "description": "Recraft V3, state of the art image generation. Prompt input cannot exceed 1,000 characters.\n\nThis bot supports optional parameters for additional customization.\n\nThis bot does not support attachments. ", "owned_by": "fal", "root": "recraft-v3", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": {"context_length": 256, "max_output_tokens": null}, "context_length": 256, "metadata": {"display_name": "Recraft-V3", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5187591-200-demafhwakljinxvuifvrjmiuftauevvs.jpeg", "alt": "Recraft-V3 model icon", "width": 200, "height": 200}, "url": "https://poe.com/recraft-v3"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "1:1", "description": "Select the desired aspect ratio for your image"}, {"name": "style", "schema": {"enum": ["any", "realistic_image", "digital_illustration", "vector_illustration", "realistic_image/b_and_w", "realistic_image/hard_flash", "realistic_image/hdr", "realistic_image/natural_light", "realistic_image/studio_portrait", "realistic_image/enterprise", "realistic_image/motion_blur", "realistic_image/evening_light", "realistic_image/faded_nostalgia", "realistic_image/forest_life", "realistic_image/mystic_naturalism", "realistic_image/natural_tones", "realistic_image/organic_calm", "realistic_image/real_life_glow", "realistic_image/retro_realism", "realistic_image/retro_snapshot", "realistic_image/urban_drama", "realistic_image/village_realism", "realistic_image/warm_folk", "digital_illustration/pixel_art", "digital_illustration/hand_drawn", "digital_illustration/grain", "digital_illustration/infantile_sketch", "digital_illustration/2d_art_poster", "digital_illustration/handmade_3d", "digital_illustration/hand_drawn_outline", "digital_illustration/engraving_color", "digital_illustration/2d_art_poster_2", "digital_illustration/antiquarian", "digital_illustration/bold_fantasy", "digital_illustration/child_book", "digital_illustration/child_books", "digital_illustration/cover", "digital_illustration/crosshatch", "digital_illustration/digital_engraving", "digital_illustration/expressionism", "digital_illustration/freehand_details", "digital_illustration/grain_20", "digital_illustration/graphic_intensity", "digital_illustration/hard_comics", "digital_illustration/long_shadow", "digital_illustration/modern_folk", "digital_illustration/multicolor", "digital_illustration/neon_calm", "digital_illustration/noir", "digital_illustration/nostalgic_pastel", "digital_illustration/outline_details", "digital_illustration/pastel_gradient", "digital_illustration/pastel_sketch", "digital_illustration/pop_art", "digital_illustration/pop_renaissance", "digital_illustration/street_art", "digital_illustration/tablet_sketch", "digital_illustration/urban_glow", "digital_illustration/urban_sketching", "digital_illustration/vanilla_dreams", "digital_illustration/young_adult_book", "digital_illustration/young_adult_book_2"]}, "default_value": "realistic_image", "description": "Select one of the given styles to "}]}, {"id": "gpt-4o-aug", "object": "model", "created": 1732149774348, "description": "OpenAI's most powerful model, GPT-4o, using the August 2024 model snapshot. Stronger than GPT-3.5 in quantitative questions (math and physics), creative writing, and many other challenging tasks. ", "owned_by": "OpenAI", "root": "gpt-4o-aug", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/responses", "/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000022727", "completion": "0.0000090909", "image": null, "request": null, "input_cache_read": "0.0000011364", "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": 8192}, "context_length": 128000, "metadata": {"display_name": "GPT-4o-Aug", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3026-200-kpqjzzdhjvmobqnpkwewrgrpqcxxbhiw.jpeg", "alt": "GPT-4o-Aug model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-4o-aug"}, "reasoning": null, "parameters": []}, {"id": "solar-pro-2", "object": "model", "created": 1694610718864, "description": "Solar Pro 2 is Upstage's latest frontier-scale LLM. With just 31B parameters, it delivers top-tier performance through world-class multilingual support, advanced reasoning, and real-world tool use. Especially in Korean, it outperforms much larger models across critical benchmarks. Built for the next generation of practical LLMs, Solar Pro 2 proves that smaller models can still lead. Supports a context length of 64k tokens.", "owned_by": "Upstage", "root": "solar-pro-2", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": [], "supported_endpoints": ["/v1/chat/completions"], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0021", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 4096, "max_output_tokens": 1024}, "context_length": 4096, "metadata": {"display_name": "Solar-Pro-2", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-7006-200-vawvkuecismyzqxchgrbiayuvjzowwuy.jpeg", "alt": "Solar-Pro-2 model icon", "width": 200, "height": 200}, "url": "https://poe.com/solar-pro-2"}, "reasoning": null, "parameters": []}, {"id": "remove-background", "object": "model", "created": 1714848450172, "description": "Remove background from your images", "owned_by": "fal", "root": "remove-background", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "remove-background", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-4142044-200-nhzozhqojyjdovdvbfqvqrmclhfvpuqt.jpeg", "alt": "remove-background model icon", "width": 200, "height": 200}, "url": "https://poe.com/remove-background"}, "reasoning": null, "parameters": []}, {"id": "sana-t2i", "object": "model", "created": 1736139178094, "description": "SANA can synthesize high-resolution, high-quality images at a remarkably fast rate, with the ability to generate 4K images in less than a second.\n\nOptional parameters:\nSet aspect ratio, with options 16:9, 4:3, 1:1, 3:4 and 9:16. This is set to 4:3 by default.", "owned_by": "fal", "root": "sana-t2i", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Sana-T2I", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5510515-200-rfppxqhvgiezuqfcuttrxrdplwfnsqjt.jpeg", "alt": "Sana-T2I model icon", "width": 200, "height": 200}, "url": "https://poe.com/sana-t2i"}, "reasoning": null, "parameters": [{"name": "aspect", "schema": {"enum": ["16:9", "4:3", "1:1", "3:4", "9:16"]}, "default_value": "4:3", "description": "Select the desired aspect ratio for your image"}]}, {"id": "tako", "object": "model", "created": 1723756137465, "description": "Tako is a bot that transforms your questions about stocks, sports, economics or politics into interactive, shareable knowledge cards from trusted sources. Tako's knowledge graph is built exclusively from authoritative, real-time data providers, and is embeddable in your apps, research and storytelling. You can adjust the specificity threshold by typing `--specificity 30` (or a value between 0 - 100) at the end of your query/question; the default is 60.", "owned_by": "TryTako", "root": "tako", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.030", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 2048, "max_output_tokens": null}, "context_length": 2048, "metadata": {"display_name": "Tako", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-4770366-200-bdcugycfrjdmfoxgwkmjsxvnfgjuzloq.jpeg", "alt": "Tako model icon", "width": 200, "height": 200}, "url": "https://poe.com/tako"}, "reasoning": null, "parameters": []}, {"id": "llama-3.1-8b-fp16", "object": "model", "created": 1724034517400, "description": "The smallest and fastest member of the Llama 3.1 family, offering exceptional efficiency and rapid response times with 128K context length.", "owned_by": "Hyperbolic", "root": "llama-3.1-8b-fp16", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0015", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 131000, "max_output_tokens": null}, "context_length": 131000, "metadata": {"display_name": "Llama-3.1-8B-FP16", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-4786666-200-dfrqqdurhupfddvanduirnadayoredrz.jpeg", "alt": "Llama-3.1-8B-FP16 model icon", "width": 200, "height": 200}, "url": "https://poe.com/llama-3.1-8b-fp16"}, "reasoning": null, "parameters": []}, {"id": "restyler", "object": "model", "created": 1739302186273, "description": "This bot enables rapid transformation of existing images, delivering high-quality style transfers and image modifications. Takes in a text input and an image attachment. Use --strength to control the guidance given by the initial image, with higher values adhering to the image more strongly.", "owned_by": "fal", "root": "restyler", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Restyler", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5654539-200-jeuammzieshjeqvmnsptrvfzdyhgsbia.jpeg", "alt": "Restyler model icon", "width": 200, "height": 200}, "url": "https://poe.com/restyler"}, "reasoning": null, "parameters": []}, {"id": "qwen-2.5-7b-t", "object": "model", "created": 1730863674687, "description": "Qwen 2.5 7B from Alibaba. Excels in coding, math, instruction following, natural language understanding, and has great multilangual support with more than 29 languages.", "owned_by": "Together AI", "root": "qwen-2.5-7b-t", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0023", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 32768, "max_output_tokens": null}, "context_length": 32768, "metadata": {"display_name": "Qwen-2.5-7B-T", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5220435-200-tvobdmkmusqgqcsiykwlnaiefbstsgbs.jpeg", "alt": "Qwen-2.5-7B-T model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen-2.5-7b-t"}, "reasoning": null, "parameters": []}, {"id": "python", "object": "model", "created": 1724756919380, "description": "Executes Python code (version 3.11) from the user message and outputs the results. If there are code blocks in the user message (surrounded by triple backticks), then only the code blocks will be executed. These libraries are imported into this bot's run-time automatically -- numpy, pandas, requests, matplotlib, scikit-learn, torch, PyYAML, tensorflow, scipy, pytest -- along with ~150 of the most widely used Python libraries.", "owned_by": "Poe", "root": "python", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.000030", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 131000, "max_output_tokens": null}, "context_length": 131000, "metadata": {"display_name": "Python", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-4831099-200-bapingzxfdggwnsscpykqjzjhnsbvskn.jpeg", "alt": "Python model icon", "width": 200, "height": 200}, "url": "https://poe.com/python"}, "reasoning": null, "parameters": []}, {"id": "markitdown", "object": "model", "created": 1746488364378, "description": "Convert anything to Markdown: URLs, PDFs, Word, Excel, images (EXIF metadata), audio (EXIF metadata and transcription), and more. This bot wraps Microsoft\u2019s MarkItDown MCP server (https://github.com/microsoft/markitdown).", "owned_by": "OpenTools", "root": "markitdown", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "MarkItDown", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5989413-200-kvdktcbnuuwcgrwxhthvmytzvwtczenh.jpeg", "alt": "MarkItDown model icon", "width": 200, "height": 200}, "url": "https://poe.com/markitdown"}, "reasoning": null, "parameters": []}, {"id": "gpt-4-turbo", "object": "model", "created": 1694610718932, "description": "Powered by OpenAI's GPT-4 Turbo. For most tasks, https://poe.com/GPT-4o will perform better. Supports 128k tokens of context. Requests with images will be routed to @GPT-4o.", "owned_by": "OpenAI", "root": "gpt-4-turbo", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000090909", "completion": "0.0000272727", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 128000, "max_output_tokens": 4096}, "context_length": 128000, "metadata": {"display_name": "GPT-4-Turbo", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3007-200-jxpvytakxobrimwauunmvbimxqfpqadi.jpeg", "alt": "GPT-4-Turbo model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-4-turbo"}, "reasoning": null, "parameters": []}, {"id": "flux-1-schnell-fw", "object": "model", "created": 1729619977045, "description": "FLUX.1 [schnell] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions.\n\nKey Features\n1. Cutting-edge output quality and competitive prompt following, matching the performance of closed source alternatives.\n2. Trained using latent adversarial diffusion distillation, FLUX.1 [schnell] can generate high-quality images in only 1 to 4 steps.\n3. Released under the apache-2.0 licence, the model can be used for personal, scientific, and commercial purposes.\nBot does not support attachments. ", "owned_by": "Fireworks AI", "root": "flux-1-schnell-fw", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0011", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 256, "max_output_tokens": null}, "context_length": 256, "metadata": {"display_name": "Flux-1-Schnell-FW", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5142729-200-bndpfjeryggvpoflasfqshmzqmstgkll.jpeg", "alt": "Flux-1-Schnell-FW model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-1-schnell-fw"}, "reasoning": null, "parameters": []}, {"id": "flux-1-dev-fw", "object": "model", "created": 1729618505818, "description": "FLUX.1 [dev] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions.\n\nKey Features\n1. Cutting-edge output quality, second only to our state-of-the-art model FLUX.1 [pro].\n2. Competitive prompt following, matching the performance of closed source alternatives.\n3. Trained using guidance distillation, making FLUX.1 [dev] more efficient.\n4. Open weights to drive new scientific research, and empower artists to develop innovative workflows.\n5. Generated outputs can be used for personal, scientific, and commercial purposes as described in the FLUX.1 [dev] Non-Commercial License.\nBot does not accept attachments.", "owned_by": "Fireworks AI", "root": "flux-1-dev-fw", "architecture": {"input_modalities": ["text"], "output_modalities": ["image"], "modality": "text->image"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.011", "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 256, "max_output_tokens": null}, "context_length": 256, "metadata": {"display_name": "Flux-1-Dev-FW", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5142643-200-jfekzqyvgogbdzucrbalbejhblwyyiep.jpeg", "alt": "Flux-1-Dev-FW model icon", "width": 200, "height": 200}, "url": "https://poe.com/flux-1-dev-fw"}, "reasoning": null, "parameters": []}, {"id": "mochi-preview", "object": "model", "created": 1729817676311, "description": "Open state-of-the-art video generation model with high-fidelity motion and strong prompt adherence. Supports both text-to-video and image-to-video. Generates 5 second video.", "owned_by": "fal", "root": "mochi-preview", "architecture": {"input_modalities": ["text"], "output_modalities": ["video"], "modality": "text->video"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Mochi-preview", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-5155894-200-xumtjguwrcasfwljiuwinlgadtrekvbg.jpeg", "alt": "Mochi-preview model icon", "width": 200, "height": 200}, "url": "https://poe.com/mochi-preview"}, "reasoning": null, "parameters": []}, {"id": "gpt-3.5-turbo-instruct", "object": "model", "created": 1695250309273, "description": "This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations.", "owned_by": "OpenAI", "root": "gpt-3.5-turbo-instruct", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000013636", "completion": "0.0000018182", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 3500, "max_output_tokens": 1024}, "context_length": 3500, "metadata": {"display_name": "GPT-3.5-Turbo-Instruct", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3011-200-srvppdhamtuiuaqrlgbeeldubkabxjrj.jpeg", "alt": "GPT-3.5-Turbo-Instruct model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-3.5-turbo-instruct"}, "reasoning": null, "parameters": []}, {"id": "gpt-3.5-turbo-raw", "object": "model", "created": 1695849978857, "description": "Powered by gpt-3.5-turbo without a system prompt.", "owned_by": "OpenAI", "root": "gpt-3.5-turbo-raw", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/chat/completions", "/v1/messages"], "pricing": {"prompt": "0.0000004545", "completion": "0.0000013636", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": {"context_length": 4524, "max_output_tokens": 2048}, "context_length": 4524, "metadata": {"display_name": "GPT-3.5-Turbo-Raw", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-3012-200-ucljxtkyryjbormooazpkjblkzydxihb.jpeg", "alt": "GPT-3.5-Turbo-Raw model icon", "width": 200, "height": 200}, "url": "https://poe.com/gpt-3.5-turbo-raw"}, "reasoning": null, "parameters": []}, {"id": "interpreter", "object": "model", "created": 1715753807980, "description": "Interpreter for Poe Python", "owned_by": "Poe Tools", "root": "interpreter", "architecture": {"input_modalities": ["text", "image", "video", "audio"], "output_modalities": ["text"], "modality": "text,image,video,audio->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Interpreter", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-4209681-200-ctejioamndxnxaiexyumnchuenumiehz.jpeg", "alt": "Interpreter model icon", "width": 200, "height": 200}, "url": "https://poe.com/interpreter"}, "reasoning": null, "parameters": []}, {"id": "claude-haiku-3", "object": "model", "created": 1709942726436, "description": "Anthropic's Claude Haiku 3 outperforms models in its intelligence category on performance, speed and cost without the need for specialized fine-tuning. The compute points value is subject to change. For most use cases, https://poe.com/Claude-Haiku-3.5 will be better.", "owned_by": "Anthropic", "root": "claude-haiku-3", "architecture": {"input_modalities": ["text", "image"], "output_modalities": ["text"], "modality": "text,image->text"}, "supported_features": ["tools"], "supported_endpoints": ["/v1/messages", "/v1/responses", "/v1/chat/completions"], "pricing": {"prompt": "0.0000002121", "completion": "0.0000010707", "image": null, "request": null, "input_cache_read": "0.0000000212", "input_cache_write": "0.0000002652"}, "context_window": {"context_length": 189096, "max_output_tokens": 8192}, "context_length": 189096, "metadata": {"display_name": "Claude-Haiku-3", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-1017-200-rlxulasuqgygechgjmvzhhcuykxwflxa.jpeg", "alt": "Claude-Haiku-3 model icon", "width": 200, "height": 200}, "url": "https://poe.com/claude-haiku-3"}, "reasoning": null, "parameters": []}, {"id": "code-saver", "object": "model", "created": 1754063583549, "description": "A system bot that handles Poe scripts in chat.", "owned_by": "Poe Tools", "root": "code-saver", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Code-Saver", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6285092-200-qptmswkqmzhxcumbenmwpxfnudkxdcwh.jpeg", "alt": "Code-Saver model icon", "width": 200, "height": 200}, "url": "https://poe.com/code-saver"}, "reasoning": null, "parameters": []}, {"id": "code-editor", "object": "model", "created": 1748902288662, "description": "Official code editor for Poe Scripting using Python, used to connect multiple Poe bots and create AI workflows. Guide and tips: https://creator.poe.com/docs/script-bots/poe-python-reference", "owned_by": "Poe Tools", "root": "code-editor", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Code-Editor", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6083783-200-urfvhmpceyqynijkxavvrodqjlukammo.jpeg", "alt": "Code-Editor model icon", "width": 200, "height": 200}, "url": "https://poe.com/code-editor"}, "reasoning": null, "parameters": []}, {"id": "gemini-3.1-flash-tts", "object": "model", "created": 1776295398177, "description": "Gemini 3.1 Flash TTS is Google\u2019s most controllable text-to-speech model yet, designed to turn text into natural-sounding audio with precise control over style, tone, pace, and delivery. It uses new Audio Tags to make voices feel more expressive and customizable for narration, assistants, and other voice experiences.\n\nNotes:\n- Text and style prompt limited to 4,000 bytes each (8,000 bytes combined)\n- Max output duration: approximately 10 minutes\n- Multi-speaker requires SpeakerName: text format (example: Alice: Hi! Bob: Hello, must be on new lines)\n- The model auto-detects the input language. The Language setting is a hint to help choose the right voice/accent, the model may override it if the text is in a different language.\n\nExpressive Audio Tags:\n- Use inline in your text to control delivery\n- Emotion/tone: [whispers], [shouts], [laughs], [cries], [sighs], [gasps], [groans], [scoffs], [sarcasm], [deadpan], [cheerful], [sad], [angry], [fearful], [surprised], [disgusted], [confused], [nervous], [bored], [excited], [relieved], [hopeful], [proud], [shy], [sincere], [playful], [serious], [tender], [dramatic], [monotone], [warm], [cold]\n- Pace/speed: [slow], [fast], [extremely fast], [extremely slow], [normal pace]\n- Pauses: [short pause], [long pause], [pause], [breath]\n- Emphasis/delivery: [emphasis], [softly], [loudly], [high pitch], [low pitch], [rising tone], [falling tone]\n- Example: \"[whispers] I have a secret. [normal pace] But first, let me explain.\"\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "gemini-3.1-flash-tts", "architecture": {"input_modalities": ["text"], "output_modalities": ["audio"], "modality": "text->audio"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Gemini-3.1-Flash-TTS", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6941527-200-fdancqdohsmwpgotnivjdlevxxikamzh.jpeg", "alt": "Gemini-3.1-Flash-TTS model icon", "width": 200, "height": 200}, "url": "https://poe.com/gemini-3.1-flash-tts"}, "reasoning": null, "parameters": [{"name": "mode", "schema": {"enum": ["single", "multi"]}, "default_value": "single", "description": "Choose between single speaker or conversation mode"}, {"name": "language", "schema": {"enum": ["ar-EG", "bn-BD", "nl-NL", "en-IN", "en-US", "fr-FR", "de-DE", "hi-IN", "id-ID", "it-IT", "ja-JP", "ko-KR", "mr-IN", "pl-PL", "pt-BR", "ro-RO", "ru-RU", "es-ES", "ta-IN", "te-IN", "th-TH", "tr-TR", "uk-UA", "vi-VN", "af-ZA", "sq-AL", "am-ET", "ar-001", "hy-AM", "az-AZ", "eu-ES", "be-BY", "bg-BG", "my-MM", "ca-ES", "ceb-PH", "cmn-CN", "cmn-TW", "hr-HR", "cs-CZ", "da-DK", "en-AU", "en-GB", "et-EE", "fil-PH", "fi-FI", "fr-CA", "gl-ES", "ka-GE", "el-GR", "gu-IN", "ht-HT", "he-IL", "hu-HU", "is-IS", "jv-JV", "kn-IN", "kok-IN", "lo-LA", "la-VA", "lv-LV", "lt-LT", "lb-LU", "mk-MK", "mai-IN", "mg-MG", "ms-MY", "ml-IN", "mn-MN", "ne-NP", "nb-NO", "nn-NO", "or-IN", "ps-AF", "fa-IR", "pt-PT", "pa-IN", "sr-RS", "sd-IN", "si-LK", "sk-SK", "sl-SI", "es-419", "es-MX", "sw-KE", "sv-SE", "ur-PK"]}, "default_value": "en-US", "description": "Language and region for speech synthesis"}, {"name": "output_format", "schema": {"enum": ["MP3", "WAV", "OGG", "ALAW", "MULAW"]}, "default_value": "WAV", "description": "Choose the audio file format"}, {"name": "voice", "schema": {"enum": ["Zephyr", "Puck", "Charon", "Kore", "Fenrir", "Leda", "Orus", "Aoede", "Callirrhoe", "Autonoe", "Enceladus", "Iapetus", "Umbriel", "Algieba", "Despina", "Erinome", "Algenib", "Rasalgethi", "Laomedeia", "Achernar", "Alnilam", "Schedar", "Gacrux", "Pulcherrima", "Achird", "Zubenelgenubi", "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat"]}, "default_value": "Charon", "description": "Voice for the first speaker"}, {"name": "voice2", "schema": {"enum": ["Zephyr", "Puck", "Charon", "Kore", "Fenrir", "Leda", "Orus", "Aoede", "Callirrhoe", "Autonoe", "Enceladus", "Iapetus", "Umbriel", "Algieba", "Despina", "Erinome", "Algenib", "Rasalgethi", "Laomedeia", "Achernar", "Alnilam", "Schedar", "Gacrux", "Pulcherrima", "Achird", "Zubenelgenubi", "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat"]}, "default_value": "Kore", "description": "Voice for the second speaker"}, {"name": "speaker1_name", "schema": {"type": "string"}, "default_value": "Speaker1", "description": "Name for first speaker (alphanumeric, no spaces)"}, {"name": "speaker2_name", "schema": {"type": "string"}, "default_value": "Speaker2", "description": "Name for second speaker (alphanumeric, no spaces)"}, {"name": "speed", "schema": {"type": "number", "minimum": 0.25, "maximum": 2.0}, "default_value": 1.0, "description": "Speaking rate (0.25x slowest to 2.0x fastest)"}, {"name": "volume_gain", "schema": {"type": "number", "minimum": -96, "maximum": 16}, "default_value": 0, "description": "Adjust output volume in decibels (-96 to +16 dB)"}, {"name": "sample_rate", "schema": {"enum": ["8000", "16000", "22050", "24000", "44100", "48000"]}, "default_value": "24000", "description": "Audio sample rate in Hz (applies to all formats)"}, {"name": "style_prompt", "schema": {"type": "string"}, "default_value": "", "description": "Instructions for how to speak (tone, emotion, pace, accent). Supports audio tags like [whispers], [laughs], [excited], [sigh], [shouting], etc."}]}, {"id": "minimax-m2.7-fw", "object": "model", "created": 1776304104364, "description": "Mixture-of-Experts language model. M2.7 is capable of building complex agent harnesses and completing highly elaborate productivity tasks, leveraging Agent Teams, complex Skills, and dynamic tool search.", "owned_by": "Fireworks AI", "root": "minimax-m2.7-fw", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.0061", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Minimax-M2.7-FW", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6941697-200-tzziybkhipwvzjstmrndofblgkehqhwn.jpeg", "alt": "Minimax-M2.7-FW model icon", "width": 200, "height": 200}, "url": "https://poe.com/minimax-m2.7-fw"}, "reasoning": null, "parameters": []}, {"id": "kimi-k2.6", "object": "model", "created": 1776700251806, "description": "Kimi K2.6 is an open-source, native multimodal agentic model that significantly advances practical capabilities in long-horizon coding, coding-driven design, and swarm-based task orchestration. It robustly executes complex, end-to-end development tasks across multiple programming languages and domains, seamlessly transforming simple prompts and visual inputs into production-ready, aesthetically precise interfaces and full-stack workflows. Uniquely engineered for high scalability, K2.6 can horizontally orchestrate up to 300 domain-specialized sub-agents through 4,000 coordinated steps, dynamically decomposing intricate tasks to deliver diverse end-to-end outputs\u2014from documents and spreadsheets to fully functional websites\u2014in a single autonomous run. Furthermore, its proactive execution capabilities empower persistent, 24/7 background agents to manage schedules, deploy code, and orchestrate cross-platform operations entirely without human oversight, establishing it as a premier foundational model for next-gener\n\nFile Support: Text, Markdown, Image, Video and PDF files\nContext window: 262k tokens", "owned_by": "Novita AI", "root": "kimi-k2.6", "architecture": {"input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "modality": "text,image,video->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000009596", "completion": "0.0000040404", "image": null, "request": null, "input_cache_read": "0.0000001616", "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Kimi-K2.6", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6950030-200-mzmbnpescigrcswguriqcgdupnjlqxaz.jpeg", "alt": "Kimi-K2.6 model icon", "width": 200, "height": 200}, "url": "https://poe.com/kimi-k2.6"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": false, "description": "This will cause the model to think..."}, {"name": "temperature", "schema": {"type": "number", "minimum": 0, "maximum": 2}, "default_value": 0.7, "description": "Controls randomness in the response. Lower values make the output more focused and deterministic."}, {"name": "max_output_tokens", "schema": {"type": "number", "minimum": 1, "maximum": 262144}, "default_value": 262144, "description": "Maximum number of tokens to generate in the response."}]}, {"id": "qwen3.6-max-preview", "object": "model", "created": 1776702599455, "description": "The Max model, the largest and most capable variant in the Qwen3.6 series, is now available in a preview version. At present, only its plain-text capabilities are open for experimentation. Compared with the previously released Qwen3-Max and Qwen3.6-Plus, this model features enhanced vibe coding abilities, more efficient coding agent execution, and significantly improved front-end development skills. Additionally, its long-tail knowledge retention has been further upgraded.\nThis model is served by Alibaba Cloud Int. from Singapore.\n\nNotes:\n- Pricing is ~1.5x when input tokens >128k\n- Context Window: 256k\n- Supported input modalities: Text, Image (non-native), Documents\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "qwen3.6-max-preview", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000013131", "completion": "0.0000078788", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Qwen3.6-Max-Preview", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6950083-200-ypqicbrbtrqbyobmnqcczwctfnqlmple.jpeg", "alt": "Qwen3.6-Max-Preview model icon", "width": 200, "height": 200}, "url": "https://poe.com/qwen3.6-max-preview"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Let the model reason step-by-step before answering"}, {"name": "thinking_budget", "schema": {"type": "number", "minimum": 1, "maximum": 32768}, "default_value": 32768, "description": "Maximum tokens for the thinking process (higher = deeper reasoning, more output tokens)"}, {"name": "tool_web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Search the web for real-time information before answering (adds latency)"}]}, {"id": "seedream-5.0-lite-el", "object": "model", "created": 1776720463370, "description": "Seedream 5.0 Lite is ByteDance\u2019s unified multimodal image-generation model, designed to think through prompts before rendering and offering stronger understanding, reasoning, and image quality. It supports both text-to-image and image-to-image creation, with features like high-resolution output, and consistent results for detailed scenes, editing, and branded visuals.\nThis model is served from Malaysia.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "seedream-5.0-lite-el", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "Seedream-5.0-Lite-EL", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6950409-200-wdtvaidgvgdiwnmmnslxbzyymbyvxmjb.jpeg", "alt": "Seedream-5.0-Lite-EL model icon", "width": 200, "height": 200}, "url": "https://poe.com/seedream-5.0-lite-el"}, "reasoning": null, "parameters": [{"name": "aspect_ratio", "schema": {"enum": ["1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3", "21:9"]}, "default_value": "", "description": "Leave unselected for Auto. With a reference image attached, Auto matches the closest preset to your reference's ratio. Without one, text-to-image defaults to 16:9."}, {"name": "quality", "schema": {"enum": ["2K", "3K"]}, "default_value": "2K"}, {"name": "use_custom_size", "schema": {"type": "boolean"}, "default_value": false, "description": "Override Auto with exact pixel dimensions instead of picking an aspect ratio above."}, {"name": "custom_width", "schema": {"type": "string"}, "default_value": "2848", "description": "Total pixels (W\u00d7H) in [3,686,400, 10,404,496]. Aspect ratio (W/H) in [1/16, 16]."}, {"name": "custom_height", "schema": {"type": "string"}, "default_value": "1600"}, {"name": "batch_enabled", "schema": {"type": "boolean"}, "default_value": false, "description": "Generate a set of related images (e.g. storyboards, design variants). Reference images + generated images \u2264 15. Each image is billed."}, {"name": "max_images", "schema": {"type": "number", "minimum": 1, "maximum": 15}, "default_value": 4}, {"name": "output_format", "schema": {"enum": ["png", "jpeg"]}, "default_value": "png"}, {"name": "watermark", "schema": {"type": "boolean"}, "default_value": false, "description": "Add an 'AI generated' watermark to the bottom-right corner."}]}, {"id": "seed-2.0-code", "object": "model", "created": 1776829691974, "description": "Seed 2.0 Code is optimized for enterprise-grade coding scenarios. Building on the strong agentic and VLM capabilities of Seed 2.0, it further strengthens code generation and software engineering performance. It delivers particularly strong front-end results and is also optimized for multilingual coding needs commonly found in enterprise environments, making it well suited for integration with a wide range of AI coding tools.\n\nNotes:\n- Pricing is 2x when input tokens >128k\n- Context Window: 256k\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "seed-2.0-code", "architecture": {"input_modalities": ["text", "image", "video"], "output_modalities": ["text"], "modality": "text,image,video->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000006313", "completion": "0.0000037879", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "Seed-2.0-Code", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6952763-200-whehtmjatuthltkbczubjwzgjtjotgeo.jpeg", "alt": "Seed-2.0-Code model icon", "width": 200, "height": 200}, "url": "https://poe.com/seed-2.0-code"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Let the model reason step-by-step before answering."}, {"name": "reasoning_effort", "schema": {"enum": ["low", "medium", "high"]}, "default_value": "medium", "description": "How deeply the model thinks. Low=fast, Medium=balanced, High=thorough."}, {"name": "enable_web_search", "schema": {"type": "boolean"}, "default_value": false, "description": "Enable real-time web search for up-to-date information."}, {"name": "image_detail", "schema": {"enum": ["low", "high", "xhigh"]}, "default_value": "high", "description": "Quality for image understanding. Higher = more accurate but more tokens."}, {"name": "video_fps", "schema": {"type": "number", "minimum": 0.2, "maximum": 5}, "default_value": 1, "description": "Frame sampling rate for video input (0.2-5). Higher = more frames, more accurate, more tokens."}]}, {"id": "mimo-v2.5", "object": "model", "created": 1777002390726, "description": "MiMo-V2.5 is a multimodal model with native visual and audio understanding, built to reason and act across modalities while supporting a large context window. It is positioned as a major step forward in agentic capability and multimodal understanding, with strong performance in visual reasoning, chart analysis, and real-world multimodal tasks.\n\nNotes: \n- Modalities: Text, Image, Video, Audio\n- Context window: 1M\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "mimo-v2.5", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "MiMo-V2.5", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6956957-200-uihsxhmoqbymymatnriqrsutxnoqaspt.jpeg", "alt": "MiMo-V2.5 model icon", "width": 200, "height": 200}, "url": "https://poe.com/mimo-v2.5"}, "reasoning": null, "parameters": [{"name": "deep_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Step-by-step reasoning before answering."}, {"name": "web_search_enabled", "schema": {"type": "boolean"}, "default_value": false, "description": "Allow the model to search the web for real-time information."}, {"name": "web_search_force", "schema": {"type": "boolean"}, "default_value": false, "description": "Always search, even if the model thinks it can answer directly."}, {"name": "web_search_max_keyword", "schema": {"type": "number", "minimum": 1, "maximum": 5}, "default_value": 3, "description": "Maximum search keywords per round. Each keyword triggers a separate API call. More = broader but costlier."}, {"name": "web_search_limit", "schema": {"type": "number", "minimum": 1, "maximum": 10}, "default_value": 5, "description": "Maximum web pages returned per search round."}, {"name": "video_fps", "schema": {"type": "number", "minimum": 0.1, "maximum": 10}, "default_value": 2, "description": "Frames extracted per second from video. Higher = finer temporal detail but more tokens."}, {"name": "video_resolution", "schema": {"enum": ["default", "max"]}, "default_value": "default", "description": "Resolution tier for video frame analysis. 'Max' enhances recognition of small objects and fine details but uses more tokens."}]}, {"id": "mimo-v2.5-pro", "object": "model", "created": 1777001772068, "description": "MiMo-V2.5-Pro is Xiaomi\u2019s most capable model, designed for advanced agentic workflows, complex software engineering, and long-horizon tasks with strong instruction following and coherence across very long contexts. It can sustain complex autonomous work over more than a thousand tool calls while delivering frontier-level capability with strong token efficiency.\n\nNotes: \n- Pricing is 2x when input tokens >256k\n- Context window: 1M\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "mimo-v2.5-pro", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000010101", "completion": "0.0000030303", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "MiMo-V2.5-Pro", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6956944-200-gvtnukflliewvwbjupculjihtrbpsbmj.jpeg", "alt": "MiMo-V2.5-Pro model icon", "width": 200, "height": 200}, "url": "https://poe.com/mimo-v2.5-pro"}, "reasoning": null, "parameters": [{"name": "deep_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Step-by-step reasoning before answering."}, {"name": "web_search_enabled", "schema": {"type": "boolean"}, "default_value": false, "description": "Allow the model to search the web for real-time information."}, {"name": "web_search_force", "schema": {"type": "boolean"}, "default_value": false, "description": "Always search, even if the model thinks it can answer directly."}, {"name": "web_search_max_keyword", "schema": {"type": "number", "minimum": 1, "maximum": 5}, "default_value": 3, "description": "Maximum search keywords per round. Each keyword triggers a separate API call. More = broader but costlier."}, {"name": "web_search_limit", "schema": {"type": "number", "minimum": 1, "maximum": 10}, "default_value": 5, "description": "Maximum web pages returned per search round."}]}, {"id": "happyhorse-1.0-el", "object": "model", "created": 1777302726008, "description": "HappyHorse 1.0 is Alibaba's latest video generation model, capable of creating high-fidelity, motion-smooth videos from text, images, or by editing existing videos. It supports four generation modes: Text-to-Video (T2V), Image-to-Video (I2V), Reference-to-Video (R2V), and Video Edit.\n\nNotes:\n- This model is served from the Singapore region.\n- Upload one image to enable image-to-video, multiple images for reference-to-video, or a video for video editing. The mode is auto-detected from your attachments, or you can choose manually to override.\n- Generation typically takes 1\u20135 minutes per video, but may take longer.\n- Shot type and camera moves are described directly in your prompt (e.g., \"side medium shot opens, then cuts to a low-angle shot, then pushes into a facial close-up\").\n\nAttachments:\n- For T2V: No attachments required. Just describe the video you want.\n- For I2V: Attach exactly 1 image as the first frame. The output's aspect ratio automatically follows your input image (the Aspect Ratio control is ignored). The prompt is optional but recommended.\n- For R2V: Attach 1\u20139 reference images. Use `character1`, `character2`, \u2026 in your prompt to reference each image in the order they were attached (e.g., \"A woman in a red qipao character1 holding a folding fan character2\u2026\").\n- For Video Edit: Attach 1 video (3\u201315s, \u2264100 MB, MP4/MOV) plus 0\u20135 reference images. Output duration follows the input video's length (capped at 15s); audio can be kept from the source via the Audio Setting control.\n- Audio files: Not supported. HappyHorse 1.0 does not accept audio attachments, please remove any audio file before submitting.\n- Images are automatically validated and resized to fit limits (300\u20138,000px per side; R2V references should be at least 400px on the short side, 720P+ recommended). HEIC/HEIF images are auto-converted to JPEG.\n- Videos are validated (MP4/MOV, \u2264100 MB, 3\u201315s) and auto-transcoded/trimmed if needed.\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "happyhorse-1.0-el", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": null, "context_window": null, "context_length": null, "metadata": {"display_name": "HappyHorse-1.0-EL", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6962577-200-ffhtbkotjuaqfkfkmedxwcnzyuryidlc.jpeg", "alt": "HappyHorse-1.0-EL model icon", "width": 200, "height": 200}, "url": "https://poe.com/happyhorse-1.0-el"}, "reasoning": null, "parameters": [{"name": "mode", "schema": {"enum": ["auto", "t2v", "i2v", "r2v", "videoedit"]}, "default_value": "auto", "description": "Auto-detected from your attachments, or choose manually to override."}, {"name": "resolution", "schema": {"enum": ["720p", "1080p"]}, "default_value": "1080p", "description": "Higher resolution costs more per second."}, {"name": "aspect_ratio", "schema": {"enum": ["16:9", "9:16", "1:1", "4:3", "3:4"]}, "default_value": "16:9", "description": "Used by Text-to-Video and Reference-to-Video. Image-to-Video automatically follows the input image. Video Edit follows the input video."}, {"name": "duration", "schema": {"type": "number", "minimum": 3, "maximum": 15}, "default_value": 5, "description": "How long the generated video will be. Applies to T2V, I2V, and R2V. Video Edit duration follows the input video."}, {"name": "audio_setting", "schema": {"enum": ["auto", "origin"]}, "default_value": "auto", "description": "Video Edit only. Controls what happens to the original video's audio."}, {"name": "watermark", "schema": {"type": "boolean"}, "default_value": false, "description": "Adds a 'HappyHorse' watermark in the bottom-right corner."}, {"name": "seed", "schema": {"type": "string"}, "default_value": "", "description": "Set a number for reproducible results. Leave blank for random. Range: 0\u20132147483647."}]}, {"id": "deepseek-v4-pro-t", "object": "model", "created": 1777056434492, "description": "DeepSeek V4 Pro is DeepSeek's 1.6T parameter (49B activated) MoE model supporting 1M token context. It introduces a hybrid attention architecture combining Compressed Sparse Attention and Heavily Compressed Attention, requiring only 27% of inference FLOPs and 10% of KV cache compared to V3.2 at million-token context. Pre-trained on 32T+ tokens with Muon optimizer and a two-stage post-training pipeline, V4 Pro delivers three configurable reasoning modes and strong performance across coding (93.5% LiveCodeBench), reasoning (90.1% GPQA Diamond), and agentic tasks (80.6% SWE-Bench Verified). MIT licensed.", "owned_by": "Together AI", "root": "deepseek-v4-pro-t", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": [], "supported_endpoints": [], "pricing": {"prompt": null, "completion": null, "image": null, "request": "0.015", "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "DeepSeek-V4-Pro-T", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6958301-200-hylegphkotnugjinojcjzuasuxztsrwd.jpeg", "alt": "DeepSeek-V4-Pro-T model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepseek-v4-pro-t"}, "reasoning": null, "parameters": []}, {"id": "deepseek-v4-flash-el", "object": "model", "created": 1777471073686, "description": "DeepSeek V4 Flash is a highly efficient lightweight Mixture-of-Experts model with 284 billion total parameters and 13 billion active parameters, natively supporting context windows of up to 1M tokens. Offers fast inference speed, low latency, and cost-effective invocation, delivering well-balanced overall performance. Designed for high-concurrency, lightweight workloads such as everyday dialogue, content creation, basic RAG applications, and batch text processing.\nThis model is served by Alibaba Cloud Int. from Germany (Frankfurt).\n\nNotes:\n- Context Window: 1M\n- Supported input modalities: Text, Image (non-native), Documents\n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "deepseek-v4-flash-el", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000001394", "completion": "0.0000002778", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "DeepSeek-V4-Flash-EL", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6966368-200-gtagjdlyymtuflkqgkiplwqviduyeiea.jpeg", "alt": "DeepSeek-V4-Flash-EL model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepseek-v4-flash-el"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Let the model reason step-by-step before answering"}, {"name": "thinking_budget", "schema": {"type": "number", "minimum": 1, "maximum": 393216}, "default_value": 32768, "description": "Maximum tokens for the thinking process (higher = deeper reasoning, more output tokens)"}]}, {"id": "deepseek-v4-pro-el", "object": "model", "created": 1777471120983, "description": "DeepSeek V4 Pro is a flagship Mixture-of-Experts large language model with 1.6 trillion total parameters and 49 billion active parameters, natively supporting context lengths of up to 1M tokens. Excels at advanced mathematical reasoning, complex logical inference, specialized coding, and deep analysis of long-form text, well suited for cutting-edge research, sophisticated office workflows, and advanced AI agents.\nThis model is served by Alibaba Cloud Int. from Germany (Frankfurt).\n\nNotes:\n- Context Window: 1M\n- Supported input modalities: Text, Image (non-native), Documents\n- Model may experience errors due to high usage upstream. \n\nThis bot supports optional parameters for additional customization.", "owned_by": "EmpirioLabs AI", "root": "deepseek-v4-pro-el", "architecture": {"input_modalities": ["text"], "output_modalities": ["text"], "modality": "text->text"}, "supported_features": ["tools"], "supported_endpoints": [], "pricing": {"prompt": "0.0000016667", "completion": "0.0000033343", "image": null, "request": null, "input_cache_read": null, "input_cache_write": null}, "context_window": null, "context_length": null, "metadata": {"display_name": "DeepSeek-V4-Pro-EL", "image": {"url": "https://qph.cf2.poecdn.net/main-thumb-pb-6966370-200-gsiotdzscvdfximqevdfsrydvpqxpnqi.jpeg", "alt": "DeepSeek-V4-Pro-EL model icon", "width": 200, "height": 200}, "url": "https://poe.com/deepseek-v4-pro-el"}, "reasoning": null, "parameters": [{"name": "enable_thinking", "schema": {"type": "boolean"}, "default_value": true, "description": "Let the model reason step-by-step before answering"}, {"name": "thinking_budget", "schema": {"type": "number", "minimum": 1, "maximum": 393216}, "default_value": 32768, "description": "Maximum tokens for the thinking process (higher = deeper reasoning, more output tokens)"}]}]}