{
"object": "list",
"data": [
{
"id": "~anthropic/claude-fable-latest",
"object": "model",
"created": 1781049608,
"owned_by": "~anthropic",
"context_length": 1000000,
"description": "This model always redirects to the latest model in the Claude Fable family."
},
{
"id": "~anthropic/claude-haiku-latest",
"object": "model",
"created": 1777334425,
"owned_by": "~anthropic",
"context_length": 1000000,
"description": "This model always redirects to the latest model in the Claude Haiku family."
},
{
"id": "~anthropic/claude-opus-latest",
"object": "model",
"created": 1776816009,
"owned_by": "~anthropic",
"context_length": 1000000,
"description": "This model always redirects to the latest model in the Claude Opus family."
},
{
"id": "~anthropic/claude-sonnet-latest",
"object": "model",
"created": 1777334425,
"owned_by": "~anthropic",
"context_length": 1000000,
"description": "This model always redirects to the latest model in the Claude Sonnet family."
},
{
"id": "~deepseek/deepseek-flash-latest",
"object": "model",
"created": 1791211614,
"owned_by": "~deepseek",
"context_length": 1048576,
"description": "This model always redirects to the latest model in the DeepSeek Flash family."
},
{
"id": "~deepseek/deepseek-pro-latest",
"object": "model",
"created": 1791211614,
"owned_by": "~deepseek",
"context_length": 1048576,
"description": "This model always redirects to the latest model in the DeepSeek Pro family."
},
{
"id": "~deepseek/deepseek-v4-flash-latest",
"object": "model",
"created": 1785628804,
"owned_by": "~deepseek",
"context_length": 1048576,
"description": "This model always redirects to the latest model in the DeepSeek V4 Flash family."
},
{
"id": "~google/gemini-flash-latest",
"object": "model",
"created": 1777334425,
"owned_by": "~google",
"context_length": 1048576,
"description": "This model always redirects to the latest model in the Gemini Flash family."
},
{
"id": "~google/gemini-pro-latest",
"object": "model",
"created": 1777334425,
"owned_by": "~google",
"context_length": 1048576,
"description": "This model always redirects to the latest model in the Gemini Pro family."
},
{
"id": "~moonshotai/kimi-latest",
"object": "model",
"created": 1777334425,
"owned_by": "~moonshotai",
"context_length": 1048576,
"description": "This model always redirects to the latest model in the Kimi family."
},
{
"id": "~openai/gpt-astra-latest",
"object": "model",
"created": 1789149628,
"owned_by": "~openai",
"context_length": 1050000,
"description": "This model always redirects to the latest model in the GPT Astra family."
},
{
"id": "~openai/gpt-luna-latest",
"object": "model",
"created": 1789149628,
"owned_by": "~openai",
"context_length": 1050000,
"description": "This model always redirects to the latest model in the GPT Luna family."
},
{
"id": "~openai/gpt-mini-latest",
"object": "model",
"created": 1777334425,
"owned_by": "~openai",
"context_length": 400000,
"description": "This model always redirects to the latest model in the GPT Mini family."
},
{
"id": "~openai/gpt-sol-latest",
"object": "model",
"created": 1789149628,
"owned_by": "~openai",
"context_length": 1050000,
"description": "This model always redirects to the latest model in the GPT Sol family."
},
{
"id": "~openai/gpt-terra-latest",
"object": "model",
"created": 1789149628,
"owned_by": "~openai",
"context_length": 1050000,
"description": "This model always redirects to the latest model in the GPT Terra family."
},
{
"id": "~unbiased/pareto-latest",
"object": "model",
"created": 1791936060,
"owned_by": "~unbiased",
"context_length": 1048576,
"description": "This model always redirects to the latest model in the Pareto family."
},
{
"id": "~x-ai/grok-latest",
"object": "model",
"created": 1783555259,
"owned_by": "~x-ai",
"context_length": 500000,
"description": "This model always redirects to the latest Grok model from xAI."
},
{
"id": "~z-ai/glm-flash-latest",
"object": "model",
"created": 1788328826,
"owned_by": "~z-ai",
"context_length": 1048576,
"description": "This model always redirects to the latest model in the GLM Flash family."
},
{
"id": "~z-ai/glm-latest",
"object": "model",
"created": 1787162454,
"owned_by": "~z-ai",
"context_length": 1048576,
"description": "This model always redirects to the latest GLM model from Z.ai."
},
{
"id": "aion-labs/aion-2.0",
"object": "model",
"created": 1774600871,
"owned_by": "aion-labs",
"context_length": 131072,
"description": "Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging...."
},
{
"id": "aion-labs/aion-3.0",
"object": "model",
"created": 1783468846,
"owned_by": "aion-labs",
"context_length": 131072,
"description": "Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute..."
},
{
"id": "aion-labs/aion-3.0-mini",
"object": "model",
"created": 1783468846,
"owned_by": "aion-labs",
"context_length": 131072,
"description": "Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each..."
},
{
"id": "aion-labs/aion-3.5",
"object": "model",
"created": 1791211614,
"owned_by": "aion-labs",
"context_length": 262144,
"description": "Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each..."
},
{
"id": "aion-labs/aion-3.5-mini",
"object": "model",
"created": 1791211614,
"owned_by": "aion-labs",
"context_length": 262144,
"description": "Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses..."
},
{
"id": "aion-labs/aion-rp-llama-3.1-8b",
"object": "model",
"created": 1774608817,
"owned_by": "aion-labs",
"context_length": 32768,
"description": "Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model..."
},
{
"id": "amazon/nova-2-lite-v1",
"object": "model",
"created": 1774608817,
"owned_by": "amazon",
"context_length": 1000000,
"description": "Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing..."
},
{
"id": "amazon/nova-lite-v1",
"object": "model",
"created": 1774608817,
"owned_by": "amazon",
"context_length": 300000,
"description": "Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite..."
},
{
"id": "amazon/nova-micro-v1",
"object": "model",
"created": 1774608817,
"owned_by": "amazon",
"context_length": 128000,
"description": "Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length..."
},
{
"id": "amazon/nova-premier-v1",
"object": "model",
"created": 1774608817,
"owned_by": "amazon",
"context_length": 1000000,
"description": "Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models."
},
{
"id": "amazon/nova-pro-v1",
"object": "model",
"created": 1774608817,
"owned_by": "amazon",
"context_length": 300000,
"description": "Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December..."
},
{
"id": "anthracite-org/magnum-v4-72b",
"object": "model",
"created": 1774608817,
"owned_by": "anthracite-org",
"context_length": 32768,
"description": "This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).\n\nThe model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct)."
},
{
"id": "anthropic/claude-fable-5",
"object": "model",
"created": 1781028008,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and..."
},
{
"id": "anthropic/claude-fable-5:batch",
"object": "model",
"created": 1785261664,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and..."
},
{
"id": "anthropic/claude-fable-5.1",
"object": "model",
"created": 1788307221,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual..."
},
{
"id": "anthropic/claude-fable-5.1:batch",
"object": "model",
"created": 1788328826,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual..."
},
{
"id": "anthropic/claude-haiku-4.5",
"object": "model",
"created": 1774608817,
"owned_by": "anthropic",
"context_length": 200000,
"description": "Claude Haiku 4.5 is Anthropic’s 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’s performance..."
},
{
"id": "anthropic/claude-haiku-4.5:batch",
"object": "model",
"created": 1785261664,
"owned_by": "anthropic",
"context_length": 200000,
"description": "Claude Haiku 4.5 is Anthropic’s 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’s performance..."
},
{
"id": "anthropic/claude-haiku-5.5",
"object": "model",
"created": 1791417661,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and..."
},
{
"id": "anthropic/claude-haiku-5.5:batch",
"object": "model",
"created": 1791417661,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and..."
},
{
"id": "anthropic/claude-opus-4.1",
"object": "model",
"created": 1774608817,
"owned_by": "anthropic",
"context_length": 200000,
"description": "Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains..."
},
{
"id": "anthropic/claude-opus-4.1:batch",
"object": "model",
"created": 1785261664,
"owned_by": "anthropic",
"context_length": 200000,
"description": "Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains..."
},
{
"id": "anthropic/claude-opus-4.5",
"object": "model",
"created": 1774608817,
"owned_by": "anthropic",
"context_length": 200000,
"description": "Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and..."
},
{
"id": "anthropic/claude-opus-4.5:batch",
"object": "model",
"created": 1785261664,
"owned_by": "anthropic",
"context_length": 200000,
"description": "Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and..."
},
{
"id": "anthropic/claude-opus-4.6",
"object": "model",
"created": 1774600871,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective..."
},
{
"id": "anthropic/claude-opus-4.6:batch",
"object": "model",
"created": 1785261664,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective..."
},
{
"id": "anthropic/claude-opus-4.7",
"object": "model",
"created": 1776362407,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on..."
},
{
"id": "anthropic/claude-opus-4.7:batch",
"object": "model",
"created": 1785261664,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on..."
},
{
"id": "anthropic/claude-opus-4.8",
"object": "model",
"created": 1779991234,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token..."
},
{
"id": "anthropic/claude-opus-4.8:batch",
"object": "model",
"created": 1785261664,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token..."
},
{
"id": "anthropic/claude-opus-5",
"object": "model",
"created": 1784916031,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis..."
},
{
"id": "anthropic/claude-opus-5:batch",
"object": "model",
"created": 1785261664,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis..."
},
{
"id": "anthropic/claude-opus-5.5",
"object": "model",
"created": 1791211614,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code..."
},
{
"id": "anthropic/claude-opus-5.5:batch",
"object": "model",
"created": 1791211614,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code..."
},
{
"id": "anthropic/claude-sonnet-4.5",
"object": "model",
"created": 1774608817,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with..."
},
{
"id": "anthropic/claude-sonnet-4.5:batch",
"object": "model",
"created": 1785261664,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with..."
},
{
"id": "anthropic/claude-sonnet-4.6",
"object": "model",
"created": 1774600871,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with..."
},
{
"id": "anthropic/claude-sonnet-4.6:batch",
"object": "model",
"created": 1786039230,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with..."
},
{
"id": "anthropic/claude-sonnet-5",
"object": "model",
"created": 1782864023,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,..."
},
{
"id": "anthropic/claude-sonnet-5:batch",
"object": "model",
"created": 1785261664,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,..."
},
{
"id": "anthropic/claude-sonnet-5.5",
"object": "model",
"created": 1791211614,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing..."
},
{
"id": "anthropic/claude-sonnet-5.5:batch",
"object": "model",
"created": 1791211614,
"owned_by": "anthropic",
"context_length": 1000000,
"description": "Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing..."
},
{
"id": "bytedance-seed/seed-1.6",
"object": "model",
"created": 1774600871,
"owned_by": "bytedance-seed",
"context_length": 262144,
"description": "Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window."
},
{
"id": "bytedance-seed/seed-1.6-flash",
"object": "model",
"created": 1774600871,
"owned_by": "bytedance-seed",
"context_length": 262144,
"description": "Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of..."
},
{
"id": "bytedance-seed/seed-2-1-turbo",
"object": "model",
"created": 1786557637,
"owned_by": "bytedance-seed",
"context_length": 262144,
"description": "Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and..."
},
{
"id": "bytedance-seed/seed-2.0-code",
"object": "model",
"created": 1786471238,
"owned_by": "bytedance-seed",
"context_length": 262144,
"description": "Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude..."
},
{
"id": "bytedance-seed/seed-2.0-lite",
"object": "model",
"created": 1774600871,
"owned_by": "bytedance-seed",
"context_length": 262144,
"description": "Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across..."
},
{
"id": "bytedance-seed/seed-2.0-mini",
"object": "model",
"created": 1774600871,
"owned_by": "bytedance-seed",
"context_length": 262144,
"description": "Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,..."
},
{
"id": "bytedance/ui-tars-1.5-7b",
"object": "model",
"created": 1774608817,
"owned_by": "bytedance",
"context_length": 128000,
"description": "UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement..."
},
{
"id": "cognitivecomputations/dolphin-mistral-24b-venice-edition",
"object": "model",
"created": 1783663257,
"owned_by": "cognitivecomputations",
"context_length": 128000,
"description": "Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving..."
},
{
"id": "cohere/command-a",
"object": "model",
"created": 1774608817,
"owned_by": "cohere",
"context_length": 256000,
"description": "Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary..."
},
{
"id": "cohere/command-a-plus",
"object": "model",
"created": 1791211614,
"owned_by": "cohere",
"context_length": 192000,
"description": "Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured..."
},
{
"id": "cohere/command-r-08-2024",
"object": "model",
"created": 1774608817,
"owned_by": "cohere",
"context_length": 128000,
"description": "command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and..."
},
{
"id": "cohere/command-r-plus-08-2024",
"object": "model",
"created": 1774608817,
"owned_by": "cohere",
"context_length": 128000,
"description": "command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint..."
},
{
"id": "cohere/command-r7b-12-2024",
"object": "model",
"created": 1774608817,
"owned_by": "cohere",
"context_length": 128000,
"description": "Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning..."
},
{
"id": "cohere/north-mini-code:free",
"object": "model",
"created": 1781740857,
"owned_by": "cohere",
"context_length": 256000,
"description": "North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized..."
},
{
"id": "deepseek/deepseek-chat",
"object": "model",
"created": 1774608817,
"owned_by": "deepseek",
"context_length": 163840,
"description": "DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations..."
},
{
"id": "deepseek/deepseek-chat-v3-0324",
"object": "model",
"created": 1774608817,
"owned_by": "deepseek",
"context_length": 163840,
"description": "DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well..."
},
{
"id": "deepseek/deepseek-chat-v3.1",
"object": "model",
"created": 1774608817,
"owned_by": "deepseek",
"context_length": 163840,
"description": "DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context..."
},
{
"id": "deepseek/deepseek-r1-0528",
"object": "model",
"created": 1774608817,
"owned_by": "deepseek",
"context_length": 163840,
"description": "May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active..."
},
{
"id": "deepseek/deepseek-v3.1-terminus",
"object": "model",
"created": 1774608817,
"owned_by": "deepseek",
"context_length": 163840,
"description": "DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's..."
},
{
"id": "deepseek/deepseek-v3.2",
"object": "model",
"created": 1774608817,
"owned_by": "deepseek",
"context_length": 163840,
"description": "DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism..."
},
{
"id": "deepseek/deepseek-v3.2-exp",
"object": "model",
"created": 1774608817,
"owned_by": "deepseek",
"context_length": 163840,
"description": "DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism..."
},
{
"id": "deepseek/deepseek-v4-flash",
"object": "model",
"created": 1777010440,
"owned_by": "deepseek",
"context_length": 1048576,
"description": "DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and..."
},
{
"id": "deepseek/deepseek-v4-flash-0731",
"object": "model",
"created": 1785499247,
"owned_by": "deepseek",
"context_length": 1048576,
"description": "DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows...."
},
{
"id": "deepseek/deepseek-v4-flash-vision-exp",
"object": "model",
"created": 1787313608,
"owned_by": "deepseek",
"context_length": 1048576,
"description": "DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,..."
},
{
"id": "deepseek/deepseek-v4-pro",
"object": "model",
"created": 1777010440,
"owned_by": "deepseek",
"context_length": 1048576,
"description": "DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,..."
},
{
"id": "deepseek/deepseek-v4-pro-0813",
"object": "model",
"created": 1786557637,
"owned_by": "deepseek",
"context_length": 1048576,
"description": "DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro."
},
{
"id": "deepseek/deepseek-v4.1-flash",
"object": "model",
"created": 1789041613,
"owned_by": "deepseek",
"context_length": 1048576,
"description": "DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on..."
},
{
"id": "deepseek/deepseek-v4.1-flash-1017",
"object": "model",
"created": 1792238411,
"owned_by": "deepseek",
"context_length": 1048576,
"description": "DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model..."
},
{
"id": "deepseek/deepseek-v4.1-flash:batch",
"object": "model",
"created": 1791211614,
"owned_by": "deepseek",
"context_length": 1048576,
"description": "DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on..."
},
{
"id": "dots-studio/dots-3-note-preview:free",
"object": "model",
"created": 1786687237,
"owned_by": "dots-studio",
"context_length": 512000,
"description": "Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is..."
},
{
"id": "elorian/glimpse",
"object": "model",
"created": 1792216810,
"owned_by": "elorian",
"context_length": 262144,
"description": "Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than..."
},
{
"id": "fireworks/ember-1",
"object": "model",
"created": 1791211614,
"owned_by": "fireworks",
"context_length": 1048576,
"description": "Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%..."
},
{
"id": "google/gemini-2.5-flash",
"object": "model",
"created": 1774608817,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater..."
},
{
"id": "google/gemini-2.5-flash-image",
"object": "model",
"created": 1774608817,
"owned_by": "google",
"context_length": 32768,
"description": "Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,..."
},
{
"id": "google/gemini-2.5-flash-lite",
"object": "model",
"created": 1774608817,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance..."
},
{
"id": "google/gemini-2.5-pro",
"object": "model",
"created": 1774608817,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy..."
},
{
"id": "google/gemini-2.5-pro-preview",
"object": "model",
"created": 1774608817,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy..."
},
{
"id": "google/gemini-3-flash-preview",
"object": "model",
"created": 1774600871,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool..."
},
{
"id": "google/gemini-3-flash-preview:batch",
"object": "model",
"created": 1785261664,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool..."
},
{
"id": "google/gemini-3-pro-image",
"object": "model",
"created": 1781762457,
"owned_by": "google",
"context_length": 131072,
"description": "Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and..."
},
{
"id": "google/gemini-3-pro-image-preview",
"object": "model",
"created": 1774608817,
"owned_by": "google",
"context_length": 65536,
"description": "Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and..."
},
{
"id": "google/gemini-3.1-flash-image",
"object": "model",
"created": 1781762457,
"owned_by": "google",
"context_length": 131072,
"description": "Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced..."
},
{
"id": "google/gemini-3.1-flash-image-preview",
"object": "model",
"created": 1774600871,
"owned_by": "google",
"context_length": 65536,
"description": "Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines..."
},
{
"id": "google/gemini-3.1-flash-lite",
"object": "model",
"created": 1778176846,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic..."
},
{
"id": "google/gemini-3.1-flash-lite-image",
"object": "model",
"created": 1782842423,
"owned_by": "google",
"context_length": 65536,
"description": "Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation..."
},
{
"id": "google/gemini-3.1-flash-lite-preview",
"object": "model",
"created": 1774600871,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across..."
},
{
"id": "google/gemini-3.1-flash-lite:batch",
"object": "model",
"created": 1785261664,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic..."
},
{
"id": "google/gemini-3.1-pro-preview",
"object": "model",
"created": 1774600871,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation..."
},
{
"id": "google/gemini-3.1-pro-preview-customtools",
"object": "model",
"created": 1774600871,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party..."
},
{
"id": "google/gemini-3.1-pro-preview:batch",
"object": "model",
"created": 1785261664,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation..."
},
{
"id": "google/gemini-3.5-flash",
"object": "model",
"created": 1779213605,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution..."
},
{
"id": "google/gemini-3.5-flash-lite",
"object": "model",
"created": 1784656832,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows."
},
{
"id": "google/gemini-3.5-flash-lite:batch",
"object": "model",
"created": 1785261664,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows."
},
{
"id": "google/gemini-3.5-flash:batch",
"object": "model",
"created": 1785261664,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution..."
},
{
"id": "google/gemini-3.6-flash",
"object": "model",
"created": 1784656832,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and..."
},
{
"id": "google/gemini-3.6-flash:batch",
"object": "model",
"created": 1785261664,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and..."
},
{
"id": "google/gemini-3.7-flash",
"object": "model",
"created": 1786644037,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step..."
},
{
"id": "google/gemini-3.7-flash:batch",
"object": "model",
"created": 1786644037,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step..."
},
{
"id": "google/gemini-3.8-flash",
"object": "model",
"created": 1788372033,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning."
},
{
"id": "google/gemini-3.8-flash:batch",
"object": "model",
"created": 1788372033,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning."
},
{
"id": "google/gemini-4-argon",
"object": "model",
"created": 1791914481,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across..."
},
{
"id": "google/gemini-4-argon:batch",
"object": "model",
"created": 1791936060,
"owned_by": "google",
"context_length": 1048576,
"description": "Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across..."
},
{
"id": "google/gemini-nano-banana-2.1",
"object": "model",
"created": 1791374077,
"owned_by": "google",
"context_length": 65536,
"description": "Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,..."
},
{
"id": "google/gemma-2-27b-it",
"object": "model",
"created": 1774608817,
"owned_by": "google",
"context_length": 8192,
"description": "Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of..."
},
{
"id": "google/gemma-3-12b-it",
"object": "model",
"created": 1774608817,
"owned_by": "google",
"context_length": 131072,
"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,..."
},
{
"id": "google/gemma-3-27b-it",
"object": "model",
"created": 1774608817,
"owned_by": "google",
"context_length": 131072,
"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,..."
},
{
"id": "google/gemma-3-4b-it",
"object": "model",
"created": 1774608817,
"owned_by": "google",
"context_length": 131072,
"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,..."
},
{
"id": "google/gemma-4-26b-a4b-it",
"object": "model",
"created": 1775239248,
"owned_by": "google",
"context_length": 262144,
"description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at..."
},
{
"id": "google/gemma-4-26b-a4b-it:free",
"object": "model",
"created": 1775606429,
"owned_by": "google",
"context_length": 262144,
"description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at..."
},
{
"id": "google/gemma-4-31b-it",
"object": "model",
"created": 1775174421,
"owned_by": "google",
"context_length": 262144,
"description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function..."
},
{
"id": "google/gemma-4-31b-it:free",
"object": "model",
"created": 1775606429,
"owned_by": "google",
"context_length": 262144,
"description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function..."
},
{
"id": "google/lyria-3-clip-preview",
"object": "model",
"created": 1774915224,
"owned_by": "google",
"context_length": 1048576,
"description": "30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate..."
},
{
"id": "google/lyria-3-pro-preview",
"object": "model",
"created": 1774915224,
"owned_by": "google",
"context_length": 1048576,
"description": "Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz..."
},
{
"id": "gryphe/mythomax-l2-13b",
"object": "model",
"created": 1774608817,
"owned_by": "gryphe",
"context_length": 8192,
"description": "One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge"
},
{
"id": "ibm-granite/granite-4.2-8b",
"object": "model",
"created": 1788220821,
"owned_by": "ibm-granite",
"context_length": 131072,
"description": "Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,..."
},
{
"id": "inception/mercury-2",
"object": "model",
"created": 1774600871,
"owned_by": "inception",
"context_length": 128000,
"description": "Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving..."
},
{
"id": "inception/mercury-2.5",
"object": "model",
"created": 1788912022,
"owned_by": "inception",
"context_length": 260000,
"description": "Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving..."
},
{
"id": "inception/mercury-3",
"object": "model",
"created": 1792432839,
"owned_by": "inception",
"context_length": 1000000,
"description": "Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such..."
},
{
"id": "inclusionai/ling-3.0-flash",
"object": "model",
"created": 1784829631,
"owned_by": "inclusionai",
"context_length": 262144,
"description": "*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers..."
},
{
"id": "inclusionai/ling-3.0-flash-vl",
"object": "model",
"created": 1789149628,
"owned_by": "inclusionai",
"context_length": 131072,
"description": "Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual..."
},
{
"id": "inclusionai/ling-3.1-flash",
"object": "model",
"created": 1791211614,
"owned_by": "inclusionai",
"context_length": 1000000,
"description": "Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total."
},
{
"id": "inference-net/schematron-v2-small",
"object": "model",
"created": 1789192834,
"owned_by": "inference-net",
"context_length": 128000,
"description": "Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema..."
},
{
"id": "inference-net/schematron-v2-turbo",
"object": "model",
"created": 1789192834,
"owned_by": "inference-net",
"context_length": 128000,
"description": "Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather..."
},
{
"id": "liquid/lfm-2.5-2.6b",
"object": "model",
"created": 1792886410,
"owned_by": "liquid",
"context_length": 128000,
"description": "LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or..."
},
{
"id": "liquid/lfm-2.5-2.6b:free",
"object": "model",
"created": 1786492838,
"owned_by": "liquid",
"context_length": 65536,
"description": "LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or..."
},
{
"id": "liquid/lfm-2.5-24b-a2b",
"object": "model",
"created": 1791914481,
"owned_by": "liquid",
"context_length": 128000,
"description": "LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid..."
},
{
"id": "mancer/weaver",
"object": "model",
"created": 1774608817,
"owned_by": "mancer",
"context_length": 8000,
"description": "An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations."
},
{
"id": "meituan/longcat-2.0",
"object": "model",
"created": 1784570430,
"owned_by": "meituan",
"context_length": 1048756,
"description": "LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic..."
},
{
"id": "meta-llama/llama-3.1-70b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "meta-llama",
"context_length": 131072,
"description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong..."
},
{
"id": "meta-llama/llama-3.1-8b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "meta-llama",
"context_length": 131072,
"description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to..."
},
{
"id": "meta-llama/llama-3.2-1b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "meta-llama",
"context_length": 60000,
"description": "Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate..."
},
{
"id": "meta-llama/llama-3.2-3b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "meta-llama",
"context_length": 131072,
"description": "Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it..."
},
{
"id": "meta-llama/llama-3.3-70b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "meta-llama",
"context_length": 131072,
"description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model..."
},
{
"id": "meta-llama/llama-4-maverick",
"object": "model",
"created": 1774608817,
"owned_by": "meta-llama",
"context_length": 524288,
"description": "Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward..."
},
{
"id": "meta-llama/llama-4-scout",
"object": "model",
"created": 1774608817,
"owned_by": "meta-llama",
"context_length": 1310720,
"description": "Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input..."
},
{
"id": "meta-llama/llama-guard-4-12b",
"object": "model",
"created": 1774608817,
"owned_by": "meta-llama",
"context_length": 163840,
"description": "Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM..."
},
{
"id": "meta/muse-glimmer-30b",
"object": "model",
"created": 1786406438,
"owned_by": "meta",
"context_length": 131072,
"description": "Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon..."
},
{
"id": "meta/muse-spark-1.1",
"object": "model",
"created": 1784246408,
"owned_by": "meta",
"context_length": 1048576,
"description": "Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window...."
},
{
"id": "meta/muse-spark-1.2",
"object": "model",
"created": 1785974430,
"owned_by": "meta",
"context_length": 1048576,
"description": "Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window...."
},
{
"id": "meta/muse-spark-1.2-contributor",
"object": "model",
"created": 1787356808,
"owned_by": "meta",
"context_length": 1048576,
"description": "Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark..."
},
{
"id": "meta/muse-spark-1.3",
"object": "model",
"created": 1788393633,
"owned_by": "meta",
"context_length": 1048576,
"description": "Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through..."
},
{
"id": "meta/muse-spark-1.3-contributor",
"object": "model",
"created": 1788393633,
"owned_by": "meta",
"context_length": 1048576,
"description": "Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information..."
},
{
"id": "meta/muse-spark-open",
"object": "model",
"created": 1792087210,
"owned_by": "meta",
"context_length": 1048576,
"description": "Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers..."
},
{
"id": "meta/muse-wonder",
"object": "model",
"created": 1791828091,
"owned_by": "meta",
"context_length": 1048576,
"description": "Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with..."
},
{
"id": "microsoft/phi-4",
"object": "model",
"created": 1774608817,
"owned_by": "microsoft",
"context_length": 16384,
"description": "[Microsoft Research](/microsoft) 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. At 14 billion..."
},
{
"id": "minimax/minimax-01",
"object": "model",
"created": 1774608817,
"owned_by": "minimax",
"context_length": 1000192,
"description": "MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context..."
},
{
"id": "minimax/minimax-m1",
"object": "model",
"created": 1774608817,
"owned_by": "minimax",
"context_length": 1000000,
"description": "MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it..."
},
{
"id": "minimax/minimax-m2",
"object": "model",
"created": 1774608817,
"owned_by": "minimax",
"context_length": 204800,
"description": "MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,..."
},
{
"id": "minimax/minimax-m2-her",
"object": "model",
"created": 1774600871,
"owned_by": "minimax",
"context_length": 65536,
"description": "MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message..."
},
{
"id": "minimax/minimax-m2.1",
"object": "model",
"created": 1774600871,
"owned_by": "minimax",
"context_length": 204800,
"description": "MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world..."
},
{
"id": "minimax/minimax-m2.5",
"object": "model",
"created": 1774600871,
"owned_by": "minimax",
"context_length": 204800,
"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..."
},
{
"id": "minimax/minimax-m2.7",
"object": "model",
"created": 1774600871,
"owned_by": "minimax",
"context_length": 204800,
"description": "MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent..."
},
{
"id": "minimax/minimax-m3",
"object": "model",
"created": 1780293644,
"owned_by": "minimax",
"context_length": 1048576,
"description": "MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,..."
},
{
"id": "minimax/minimax-m3.1-flash",
"object": "model",
"created": 1792692028,
"owned_by": "minimax",
"context_length": 1048576,
"description": "MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,..."
},
{
"id": "mistralai/codestral-2508",
"object": "model",
"created": 1774608817,
"owned_by": "mistralai",
"context_length": 256000,
"description": "Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)"
},
{
"id": "mistralai/devstral-2512",
"object": "model",
"created": 1774600871,
"owned_by": "mistralai",
"context_length": 262144,
"description": "Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring..."
},
{
"id": "mistralai/ministral-14b-2512",
"object": "model",
"created": 1774608817,
"owned_by": "mistralai",
"context_length": 262144,
"description": "The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language..."
},
{
"id": "mistralai/ministral-3b-2512",
"object": "model",
"created": 1774608817,
"owned_by": "mistralai",
"context_length": 131072,
"description": "The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities."
},
{
"id": "mistralai/ministral-8b-2512",
"object": "model",
"created": 1774608817,
"owned_by": "mistralai",
"context_length": 262144,
"description": "A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities."
},
{
"id": "mistralai/mistral-large",
"object": "model",
"created": 1774608817,
"owned_by": "mistralai",
"context_length": 128000,
"description": "This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)...."
},
{
"id": "mistralai/mistral-large-2407",
"object": "model",
"created": 1774608817,
"owned_by": "mistralai",
"context_length": 131072,
"description": "This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)...."
},
{
"id": "mistralai/mistral-large-2512",
"object": "model",
"created": 1774608817,
"owned_by": "mistralai",
"context_length": 262144,
"description": "Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license."
},
{
"id": "mistralai/mistral-large-4-0",
"object": "model",
"created": 1791374077,
"owned_by": "mistralai",
"context_length": 1048576,
"description": "Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up..."
},
{
"id": "mistralai/mistral-medium-3",
"object": "model",
"created": 1774608817,
"owned_by": "mistralai",
"context_length": 131072,
"description": "Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost..."
},
{
"id": "mistralai/mistral-medium-3-5",
"object": "model",
"created": 1777939200,
"owned_by": "mistralai",
"context_length": 262144,
"description": "Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex..."
},
{
"id": "mistralai/mistral-medium-3-5:batch",
"object": "model",
"created": 1787918443,
"owned_by": "mistralai",
"context_length": 262144,
"description": "Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex..."
},
{
"id": "mistralai/mistral-medium-3.1",
"object": "model",
"created": 1774608817,
"owned_by": "mistralai",
"context_length": 131072,
"description": "Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances..."
},
{
"id": "mistralai/mistral-nemo",
"object": "model",
"created": 1774608817,
"owned_by": "mistralai",
"context_length": 131072,
"description": "A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,..."
},
{
"id": "mistralai/mistral-saba",
"object": "model",
"created": 1774608817,
"owned_by": "mistralai",
"context_length": 32768,
"description": "Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional..."
},
{
"id": "mistralai/mistral-small-24b-instruct-2501",
"object": "model",
"created": 1774608817,
"owned_by": "mistralai",
"context_length": 32768,
"description": "Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed..."
},
{
"id": "mistralai/mistral-small-2603",
"object": "model",
"created": 1774600871,
"owned_by": "mistralai",
"context_length": 262144,
"description": "Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from..."
},
{
"id": "mistralai/mistral-small-3.1-24b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "mistralai",
"context_length": 128000,
"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..."
},
{
"id": "mistralai/mistral-small-3.2-24b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "mistralai",
"context_length": 256000,
"description": "Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on..."
},
{
"id": "mistralai/mixtral-8x22b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "mistralai",
"context_length": 65536,
"description": "Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,..."
},
{
"id": "mistralai/voxtral-small-24b-2507",
"object": "model",
"created": 1774608817,
"owned_by": "mistralai",
"context_length": 32768,
"description": "Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio..."
},
{
"id": "moondream/moondream3-preview",
"object": "model",
"created": 1792108780,
"owned_by": "moondream",
"context_length": 32000,
"description": "Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with..."
},
{
"id": "moondream/moondream3.1-9b-a2b",
"object": "model",
"created": 1792108780,
"owned_by": "moondream",
"context_length": 32000,
"description": "Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and..."
},
{
"id": "moonshotai/kimi-k2",
"object": "model",
"created": 1774608817,
"owned_by": "moonshotai",
"context_length": 131072,
"description": "Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for..."
},
{
"id": "moonshotai/kimi-k2-0905",
"object": "model",
"created": 1774608817,
"owned_by": "moonshotai",
"context_length": 262144,
"description": "Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32..."
},
{
"id": "moonshotai/kimi-k2-thinking",
"object": "model",
"created": 1774608817,
"owned_by": "moonshotai",
"context_length": 262144,
"description": "Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in..."
},
{
"id": "moonshotai/kimi-k2.5",
"object": "model",
"created": 1774600871,
"owned_by": "moonshotai",
"context_length": 262144,
"description": "Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed..."
},
{
"id": "moonshotai/kimi-k2.6",
"object": "model",
"created": 1776708045,
"owned_by": "moonshotai",
"context_length": 262144,
"description": "Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and..."
},
{
"id": "moonshotai/kimi-k2.7-code",
"object": "model",
"created": 1781287232,
"owned_by": "moonshotai",
"context_length": 262144,
"description": "MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts..."
},
{
"id": "moonshotai/kimi-k3",
"object": "model",
"created": 1784246408,
"owned_by": "moonshotai",
"context_length": 1048576,
"description": "Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at..."
},
{
"id": "moonshotai/kimi-k3:batch",
"object": "model",
"created": 1787961643,
"owned_by": "moonshotai",
"context_length": 1048576,
"description": "Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at..."
},
{
"id": "moonshotai/kimi-k3.1-pro",
"object": "model",
"created": 1792800026,
"owned_by": "moonshotai",
"context_length": 1048576,
"description": "Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D..."
},
{
"id": "morph/morph-v3-fast",
"object": "model",
"created": 1774608817,
"owned_by": "morph",
"context_length": 262144,
"description": "Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: {instruction} {initial_code} {edit_snippet}..."
},
{
"id": "morph/morph-v3-large",
"object": "model",
"created": 1774608817,
"owned_by": "morph",
"context_length": 262144,
"description": "Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: {instruction} {initial_code}..."
},
{
"id": "nex-agi/nex-n2.5-mini",
"object": "model",
"created": 1791211614,
"owned_by": "nex-agi",
"context_length": 262144,
"description": "Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file..."
},
{
"id": "nex-agi/nex-n2.5-pro",
"object": "model",
"created": 1791211614,
"owned_by": "nex-agi",
"context_length": 262144,
"description": "Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file..."
},
{
"id": "nousresearch/hermes-4-405b",
"object": "model",
"created": 1774608817,
"owned_by": "nousresearch",
"context_length": 131072,
"description": "Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with..."
},
{
"id": "nvidia/nemotron-3-nano-30b-a3b",
"object": "model",
"created": 1774600871,
"owned_by": "nvidia",
"context_length": 262144,
"description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully..."
},
{
"id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
"object": "model",
"created": 1777399243,
"owned_by": "nvidia",
"context_length": 256000,
"description": "NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and..."
},
{
"id": "nvidia/nemotron-3-super-120b-a12b",
"object": "model",
"created": 1774600871,
"owned_by": "nvidia",
"context_length": 1048576,
"description": "NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer..."
},
{
"id": "nvidia/nemotron-3-ultra-550b-a55b",
"object": "model",
"created": 1780596013,
"owned_by": "nvidia",
"context_length": 262144,
"description": "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it..."
},
{
"id": "nvidia/nemotron-3-ultra-550b-a55b:free",
"object": "model",
"created": 1780596013,
"owned_by": "nvidia",
"context_length": 1000000,
"description": "NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it..."
},
{
"id": "nvidia/nemotron-3.5-content-safety",
"object": "model",
"created": 1788480033,
"owned_by": "nvidia",
"context_length": 131072,
"description": "NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting..."
},
{
"id": "nvidia/nemotron-3.5-content-safety:free",
"object": "model",
"created": 1780596013,
"owned_by": "nvidia",
"context_length": 128000,
"description": "NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting..."
},
{
"id": "nvidia/nemotron-3.5-lightning",
"object": "model",
"created": 1786471238,
"owned_by": "nvidia",
"context_length": 262144,
"description": "NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that..."
},
{
"id": "nvidia/nemotron-3.5-lightning:free",
"object": "model",
"created": 1786471238,
"owned_by": "nvidia",
"context_length": 1000000,
"description": "NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that..."
},
{
"id": "nvidia/nemotron-3.5-super-vl",
"object": "model",
"created": 1792087210,
"owned_by": "nvidia",
"context_length": 1048576,
"description": "NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video..."
},
{
"id": "nvidia/nemotron-3.5-super-vl:free",
"object": "model",
"created": 1792081171,
"owned_by": "nvidia",
"context_length": 1000000,
"description": "NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video..."
},
{
"id": "nvidia/switchyard",
"object": "model",
"created": 1791211614,
"owned_by": "nvidia",
"context_length": 1000000,
"description": "Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most..."
},
{
"id": "openai/gpt-3.5-turbo-0613",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 4095,
"description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021."
},
{
"id": "openai/gpt-3.5-turbo-16k",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 16385,
"description": "This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up..."
},
{
"id": "openai/gpt-4",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 8191,
"description": "OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning..."
},
{
"id": "openai/gpt-4-turbo:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 128000,
"description": "The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023."
},
{
"id": "openai/gpt-4.1",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 1047576,
"description": "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and..."
},
{
"id": "openai/gpt-4.1-mini",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 1047576,
"description": "GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard..."
},
{
"id": "openai/gpt-4.1-mini:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 1047576,
"description": "GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard..."
},
{
"id": "openai/gpt-4.1-nano",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 1047576,
"description": "For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million..."
},
{
"id": "openai/gpt-4.1-nano:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 1047576,
"description": "For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million..."
},
{
"id": "openai/gpt-4.1:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 1047576,
"description": "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and..."
},
{
"id": "openai/gpt-4o",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 128000,
"description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as..."
},
{
"id": "openai/gpt-4o-2024-05-13",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 128000,
"description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as..."
},
{
"id": "openai/gpt-4o-2024-08-06",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 128000,
"description": "The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o (\"o\" for \"omni\") is..."
},
{
"id": "openai/gpt-4o-2024-11-20",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 128000,
"description": "The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded..."
},
{
"id": "openai/gpt-4o-mini",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 128000,
"description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable..."
},
{
"id": "openai/gpt-4o-mini-2024-07-18",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 128000,
"description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable..."
},
{
"id": "openai/gpt-4o-mini:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 128000,
"description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable..."
},
{
"id": "openai/gpt-4o:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 128000,
"description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as..."
},
{
"id": "openai/gpt-5",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy..."
},
{
"id": "openai/gpt-5-image",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 400000,
"description": "[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,..."
},
{
"id": "openai/gpt-5-image-mini",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text..."
},
{
"id": "openai/gpt-5-mini",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost...."
},
{
"id": "openai/gpt-5-mini:batch",
"object": "model",
"created": 1785261664,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost...."
},
{
"id": "openai/gpt-5-nano",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger..."
},
{
"id": "openai/gpt-5-nano:batch",
"object": "model",
"created": 1785261664,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger..."
},
{
"id": "openai/gpt-5-pro",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and..."
},
{
"id": "openai/gpt-5-pro:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and..."
},
{
"id": "openai/gpt-5:batch",
"object": "model",
"created": 1785261664,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy..."
},
{
"id": "openai/gpt-5.1",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning..."
},
{
"id": "openai/gpt-5.1-codex",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks...."
},
{
"id": "openai/gpt-5.1-codex-max",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic..."
},
{
"id": "openai/gpt-5.1-codex-mini",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex"
},
{
"id": "openai/gpt-5.1:batch",
"object": "model",
"created": 1785261664,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning..."
},
{
"id": "openai/gpt-5.2",
"object": "model",
"created": 1774600871,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly..."
},
{
"id": "openai/gpt-5.2-chat",
"object": "model",
"created": 1774600871,
"owned_by": "openai",
"context_length": 128000,
"description": "GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on..."
},
{
"id": "openai/gpt-5.2-codex",
"object": "model",
"created": 1774600871,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks...."
},
{
"id": "openai/gpt-5.2-pro",
"object": "model",
"created": 1774600871,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,..."
},
{
"id": "openai/gpt-5.2-pro:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,..."
},
{
"id": "openai/gpt-5.2:batch",
"object": "model",
"created": 1785261664,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly..."
},
{
"id": "openai/gpt-5.3-codex",
"object": "model",
"created": 1774600871,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results..."
},
{
"id": "openai/gpt-5.4",
"object": "model",
"created": 1774600871,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for..."
},
{
"id": "openai/gpt-5.4-image-2",
"object": "model",
"created": 1776816009,
"owned_by": "openai",
"context_length": 272000,
"description": "[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and..."
},
{
"id": "openai/gpt-5.4-mini",
"object": "model",
"created": 1774600871,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,..."
},
{
"id": "openai/gpt-5.4-mini:batch",
"object": "model",
"created": 1785261664,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,..."
},
{
"id": "openai/gpt-5.4-nano",
"object": "model",
"created": 1774600871,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency..."
},
{
"id": "openai/gpt-5.4-nano:batch",
"object": "model",
"created": 1785261664,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency..."
},
{
"id": "openai/gpt-5.4-pro",
"object": "model",
"created": 1774600871,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K..."
},
{
"id": "openai/gpt-5.4-pro:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K..."
},
{
"id": "openai/gpt-5.4:batch",
"object": "model",
"created": 1785261664,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for..."
},
{
"id": "openai/gpt-5.5",
"object": "model",
"created": 1777075259,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token..."
},
{
"id": "openai/gpt-5.5-pro",
"object": "model",
"created": 1777075259,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for..."
},
{
"id": "openai/gpt-5.5-pro:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for..."
},
{
"id": "openai/gpt-5.5:batch",
"object": "model",
"created": 1785261664,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token..."
},
{
"id": "openai/gpt-5.6-luna",
"object": "model",
"created": 1783620059,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for..."
},
{
"id": "openai/gpt-5.6-luna-pro",
"object": "model",
"created": 1783620059,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more..."
},
{
"id": "openai/gpt-5.6-luna-pro:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more..."
},
{
"id": "openai/gpt-5.6-luna:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for..."
},
{
"id": "openai/gpt-5.6-sol",
"object": "model",
"created": 1783620059,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks..."
},
{
"id": "openai/gpt-5.6-sol-pro",
"object": "model",
"created": 1783620059,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more..."
},
{
"id": "openai/gpt-5.6-sol-pro:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more..."
},
{
"id": "openai/gpt-5.6-sol:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks..."
},
{
"id": "openai/gpt-5.6-terra",
"object": "model",
"created": 1783620059,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic..."
},
{
"id": "openai/gpt-5.6-terra-pro",
"object": "model",
"created": 1783620059,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more..."
},
{
"id": "openai/gpt-5.6-terra-pro:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more..."
},
{
"id": "openai/gpt-5.6-terra:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic..."
},
{
"id": "openai/gpt-6-astra",
"object": "model",
"created": 1788566433,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon..."
},
{
"id": "openai/gpt-6-astra-pro",
"object": "model",
"created": 1788566433,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more..."
},
{
"id": "openai/gpt-6-astra-pro:batch",
"object": "model",
"created": 1788566433,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more..."
},
{
"id": "openai/gpt-6-astra:batch",
"object": "model",
"created": 1788566433,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon..."
},
{
"id": "openai/gpt-6-luna",
"object": "model",
"created": 1791211614,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic..."
},
{
"id": "openai/gpt-6-luna-pro",
"object": "model",
"created": 1791211614,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more..."
},
{
"id": "openai/gpt-6-luna-pro:batch",
"object": "model",
"created": 1791211614,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more..."
},
{
"id": "openai/gpt-6-luna:batch",
"object": "model",
"created": 1791211614,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic..."
},
{
"id": "openai/gpt-6-sol",
"object": "model",
"created": 1791211614,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional..."
},
{
"id": "openai/gpt-6-sol-pro",
"object": "model",
"created": 1791211614,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more..."
},
{
"id": "openai/gpt-6-sol-pro:batch",
"object": "model",
"created": 1791211614,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more..."
},
{
"id": "openai/gpt-6-sol:batch",
"object": "model",
"created": 1791211614,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional..."
},
{
"id": "openai/gpt-6.1-sol",
"object": "model",
"created": 1791211614,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional..."
},
{
"id": "openai/gpt-6.1-sol-pro",
"object": "model",
"created": 1791211614,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more..."
},
{
"id": "openai/gpt-6.1-sol-pro:batch",
"object": "model",
"created": 1791504061,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more..."
},
{
"id": "openai/gpt-6.1-sol:batch",
"object": "model",
"created": 1791504061,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional..."
},
{
"id": "openai/gpt-6.1-terra",
"object": "model",
"created": 1793059205,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots..."
},
{
"id": "openai/gpt-6.1-terra-pro",
"object": "model",
"created": 1793080804,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more..."
},
{
"id": "openai/gpt-6.1-terra-pro:batch",
"object": "model",
"created": 1793080804,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more..."
},
{
"id": "openai/gpt-6.1-terra:batch",
"object": "model",
"created": 1793059205,
"owned_by": "openai",
"context_length": 1050000,
"description": "GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots..."
},
{
"id": "openai/gpt-audio",
"object": "model",
"created": 1774600871,
"owned_by": "openai",
"context_length": 128000,
"description": "The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced..."
},
{
"id": "openai/gpt-audio-mini",
"object": "model",
"created": 1774600871,
"owned_by": "openai",
"context_length": 128000,
"description": "A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million..."
},
{
"id": "openai/gpt-chat-latest",
"object": "model",
"created": 1778004002,
"owned_by": "openai",
"context_length": 400000,
"description": "GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates..."
},
{
"id": "openai/gpt-oss-120b",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 131072,
"description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized..."
},
{
"id": "openai/gpt-oss-120b:batch",
"object": "model",
"created": 1787961643,
"owned_by": "openai",
"context_length": 131072,
"description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized..."
},
{
"id": "openai/gpt-oss-20b",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 131072,
"description": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for..."
},
{
"id": "openai/gpt-oss-20b:batch",
"object": "model",
"created": 1787961643,
"owned_by": "openai",
"context_length": 131072,
"description": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for..."
},
{
"id": "openai/gpt-oss-safeguard-20b",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 131072,
"description": "gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust..."
},
{
"id": "openai/o3",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 200000,
"description": "o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following...."
},
{
"id": "openai/o3-mini:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 200000,
"description": "OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to..."
},
{
"id": "openai/o3-pro",
"object": "model",
"created": 1774608817,
"owned_by": "openai",
"context_length": 200000,
"description": "The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently..."
},
{
"id": "openai/o3:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 200000,
"description": "o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following...."
},
{
"id": "openai/o4-mini:batch",
"object": "model",
"created": 1786039230,
"owned_by": "openai",
"context_length": 200000,
"description": "OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning..."
},
{
"id": "openrouter/auto",
"object": "model",
"created": 1774608817,
"owned_by": "openrouter",
"context_length": 2000000,
"description": "The Auto Router automatically selects the best model for your prompt, powered by the wisdom of the market. It routes you based on what the OpenRouter community collectively spends on..."
},
{
"id": "openrouter/auto-beta",
"object": "model",
"created": 1784332856,
"owned_by": "openrouter",
"context_length": 2000000,
"description": "The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta..."
},
{
"id": "openrouter/bodybuilder",
"object": "model",
"created": 1774608817,
"owned_by": "openrouter",
"context_length": 128000,
"description": "Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:..."
},
{
"id": "openrouter/free",
"object": "model",
"created": 1774600871,
"owned_by": "openrouter",
"context_length": 200000,
"description": "The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that..."
},
{
"id": "openrouter/fusion",
"object": "model",
"created": 1780444841,
"owned_by": "openrouter",
"context_length": 1000000,
"description": "Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a..."
},
{
"id": "openrouter/pareto-code",
"object": "model",
"created": 1776816009,
"owned_by": "openrouter",
"context_length": 2000000,
"description": "The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how..."
},
{
"id": "particle-ai/particle-1",
"object": "model",
"created": 1793232009,
"owned_by": "particle-ai",
"context_length": 1048576,
"description": "Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data..."
},
{
"id": "perceptron/perceptron-mk1",
"object": "model",
"created": 1778600551,
"owned_by": "perceptron",
"context_length": 32768,
"description": "Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding..."
},
{
"id": "perceptron/perceptron-mk1.5",
"object": "model",
"created": 1791211614,
"owned_by": "perceptron",
"context_length": 36864,
"description": "Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,..."
},
{
"id": "perplexity/sonar",
"object": "model",
"created": 1774608817,
"owned_by": "perplexity",
"context_length": 127072,
"description": "Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features..."
},
{
"id": "perplexity/sonar-deep-research",
"object": "model",
"created": 1774608817,
"owned_by": "perplexity",
"context_length": 128000,
"description": "Sonar 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..."
},
{
"id": "perplexity/sonar-pro",
"object": "model",
"created": 1774608817,
"owned_by": "perplexity",
"context_length": 200000,
"description": "Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like..."
},
{
"id": "perplexity/sonar-pro-search",
"object": "model",
"created": 1774608817,
"owned_by": "perplexity",
"context_length": 200000,
"description": "Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based..."
},
{
"id": "perplexity/sonar-reasoning-pro",
"object": "model",
"created": 1774608817,
"owned_by": "perplexity",
"context_length": 128000,
"description": "Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for..."
},
{
"id": "prism-ml/ternary-bonsai-2-27b",
"object": "model",
"created": 1791211614,
"owned_by": "prism-ml",
"context_length": 262144,
"description": "Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks..."
},
{
"id": "prism-ml/ternary-bonsai-2-9b",
"object": "model",
"created": 1793145604,
"owned_by": "prism-ml",
"context_length": 262144,
"description": "Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient..."
},
{
"id": "qwen/qwen-2.5-72b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 32768,
"description": "Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and..."
},
{
"id": "qwen/qwen-2.5-7b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 32768,
"description": "Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and..."
},
{
"id": "qwen/qwen-2.5-coder-32b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 32768,
"description": "Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**..."
},
{
"id": "qwen/qwen-plus",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 1000000,
"description": "Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination."
},
{
"id": "qwen/qwen2.5-vl-72b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 128000,
"description": "Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images."
},
{
"id": "qwen/qwen3-14b",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 40960,
"description": "Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for..."
},
{
"id": "qwen/qwen3-235b-a22b-2507",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 262144,
"description": "Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,..."
},
{
"id": "qwen/qwen3-235b-a22b-thinking-2507",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 128000,
"description": "Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144..."
},
{
"id": "qwen/qwen3-30b-a3b",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 40960,
"description": "Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique..."
},
{
"id": "qwen/qwen3-30b-a3b-instruct-2507",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 262144,
"description": "Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and..."
},
{
"id": "qwen/qwen3-32b",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 131072,
"description": "Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for..."
},
{
"id": "qwen/qwen3-coder",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 262144,
"description": "Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over..."
},
{
"id": "qwen/qwen3-coder-30b-a3b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 262144,
"description": "Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the..."
},
{
"id": "qwen/qwen3-coder-flash",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 1000000,
"description": "Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling..."
},
{
"id": "qwen/qwen3-coder-next",
"object": "model",
"created": 1774600871,
"owned_by": "qwen",
"context_length": 262144,
"description": "Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per..."
},
{
"id": "qwen/qwen3-next-80b-a3b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 262144,
"description": "Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual..."
},
{
"id": "qwen/qwen3-vl-235b-a22b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 262144,
"description": "Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table..."
},
{
"id": "qwen/qwen3-vl-30b-a3b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 262144,
"description": "Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception..."
},
{
"id": "qwen/qwen3-vl-30b-a3b-thinking",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 262144,
"description": "Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels..."
},
{
"id": "qwen/qwen3-vl-8b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "qwen",
"context_length": 262144,
"description": "Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon..."
},
{
"id": "qwen/qwen3.5-122b-a10b",
"object": "model",
"created": 1774600871,
"owned_by": "qwen",
"context_length": 262144,
"description": "The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of..."
},
{
"id": "qwen/qwen3.5-27b",
"object": "model",
"created": 1774600871,
"owned_by": "qwen",
"context_length": 262144,
"description": "The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of..."
},
{
"id": "qwen/qwen3.5-35b-a3b",
"object": "model",
"created": 1774600871,
"owned_by": "qwen",
"context_length": 262144,
"description": "The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall..."
},
{
"id": "qwen/qwen3.5-397b-a17b",
"object": "model",
"created": 1774600871,
"owned_by": "qwen",
"context_length": 262144,
"description": "The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers..."
},
{
"id": "qwen/qwen3.5-9b",
"object": "model",
"created": 1774600871,
"owned_by": "qwen",
"context_length": 262144,
"description": "Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design..."
},
{
"id": "qwen/qwen3.5-flash-02-23",
"object": "model",
"created": 1774600871,
"owned_by": "qwen",
"context_length": 1000000,
"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..."
},
{
"id": "qwen/qwen3.5-plus-02-15",
"object": "model",
"created": 1774600871,
"owned_by": "qwen",
"context_length": 1000000,
"description": "The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of..."
},
{
"id": "qwen/qwen3.5-plus-20260420",
"object": "model",
"created": 1777269631,
"owned_by": "qwen",
"context_length": 1000000,
"description": "Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This..."
},
{
"id": "qwen/qwen3.6-27b",
"object": "model",
"created": 1777269631,
"owned_by": "qwen",
"context_length": 262144,
"description": "Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs..."
},
{
"id": "qwen/qwen3.6-35b-a3b",
"object": "model",
"created": 1777269631,
"owned_by": "qwen",
"context_length": 262144,
"description": "Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated..."
},
{
"id": "qwen/qwen3.6-flash",
"object": "model",
"created": 1777269631,
"owned_by": "qwen",
"context_length": 1000000,
"description": "Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in..."
},
{
"id": "qwen/qwen3.6-plus",
"object": "model",
"created": 1775628055,
"owned_by": "qwen",
"context_length": 1000000,
"description": "Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers..."
},
{
"id": "qwen/qwen3.7-flash",
"object": "model",
"created": 1785218465,
"owned_by": "qwen",
"context_length": 1000000,
"description": "Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world..."
},
{
"id": "qwen/qwen3.7-max",
"object": "model",
"created": 1779386402,
"owned_by": "qwen",
"context_length": 1000000,
"description": "Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,..."
},
{
"id": "qwen/qwen3.7-plus",
"object": "model",
"created": 1780509623,
"owned_by": "qwen",
"context_length": 1000000,
"description": "Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its..."
},
{
"id": "qwen/qwen3.7-plus:batch",
"object": "model",
"created": 1792216810,
"owned_by": "qwen",
"context_length": 262144,
"description": "Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its..."
},
{
"id": "qwen/qwen3.8-2.4t-a95b",
"object": "model",
"created": 1786557637,
"owned_by": "qwen",
"context_length": 1048576,
"description": "Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is..."
},
{
"id": "qwen/qwen3.8-27b",
"object": "model",
"created": 1786773634,
"owned_by": "qwen",
"context_length": 1024000,
"description": "Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be..."
},
{
"id": "qwen/qwen3.8-flash",
"object": "model",
"created": 1787788843,
"owned_by": "qwen",
"context_length": 1000000,
"description": "Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis."
},
{
"id": "qwen/qwen3.8-max-0902",
"object": "model",
"created": 1788588033,
"owned_by": "qwen",
"context_length": 1000000,
"description": "Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,..."
},
{
"id": "qwen/qwen3.8-max-prime",
"object": "model",
"created": 1791211614,
"owned_by": "qwen",
"context_length": 1000000,
"description": "Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video..."
},
{
"id": "qwen/qwen3.8-omni-flash",
"object": "model",
"created": 1791211614,
"owned_by": "qwen",
"context_length": 1000000,
"description": "Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,..."
},
{
"id": "recursive/flint-v1.0:free",
"object": "model",
"created": 1792627226,
"owned_by": "recursive",
"context_length": 262144,
"description": "Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited..."
},
{
"id": "reflection/beam-1.0-501b-a23b",
"object": "model",
"created": 1792173613,
"owned_by": "reflection",
"context_length": 1048576,
"description": "Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a..."
},
{
"id": "rekaai/reka-edge",
"object": "model",
"created": 1775066420,
"owned_by": "rekaai",
"context_length": 16384,
"description": "Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,..."
},
{
"id": "rekaai/reka-flash-3",
"object": "model",
"created": 1774936839,
"owned_by": "rekaai",
"context_length": 65536,
"description": "Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a..."
},
{
"id": "relace/relace-apply-3",
"object": "model",
"created": 1774608817,
"owned_by": "relace",
"context_length": 256000,
"description": "Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at..."
},
{
"id": "relace/relace-search",
"object": "model",
"created": 1774600871,
"owned_by": "relace",
"context_length": 256000,
"description": "The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic..."
},
{
"id": "sakana/fugu-max",
"object": "model",
"created": 1789106416,
"owned_by": "sakana",
"context_length": 1000000,
"description": "Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route..."
},
{
"id": "sakana/fugu-ultra",
"object": "model",
"created": 1782280856,
"owned_by": "sakana",
"context_length": 1000000,
"description": "Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route..."
},
{
"id": "sakana/fugu-ultra-v2",
"object": "model",
"created": 1789106416,
"owned_by": "sakana",
"context_length": 1000000,
"description": "Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to..."
},
{
"id": "sakana/sakana-namazu",
"object": "model",
"created": 1786428041,
"owned_by": "sakana",
"context_length": 262144,
"description": "Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,..."
},
{
"id": "sao10k/l3-lunaris-8b",
"object": "model",
"created": 1774608817,
"owned_by": "sao10k",
"context_length": 8192,
"description": "Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge...."
},
{
"id": "sao10k/l3.1-euryale-70b",
"object": "model",
"created": 1774608817,
"owned_by": "sao10k",
"context_length": 131072,
"description": "Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b)."
},
{
"id": "scaledown/extract",
"object": "model",
"created": 1791914481,
"owned_by": "scaledown",
"context_length": 1000000,
"description": "Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the..."
},
{
"id": "scaledown/summarize",
"object": "model",
"created": 1791914481,
"owned_by": "scaledown",
"context_length": 1000000,
"description": "Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for..."
},
{
"id": "shared-local/up_00c282483b914e0e85d97c00a1885b9c/openai/gpt-4o-mini",
"object": "model",
"created": 1793383341,
"owned_by": "shared-local",
"context_length": 131072,
"description": "Hosted by a UAI user via a shared custom upstream."
},
{
"id": "shared-local/up_00c282483b914e0e85d97c00a1885b9c/wg-i4905-probe",
"object": "model",
"created": 1793383341,
"owned_by": "shared-local",
"context_length": 131072,
"description": "Hosted by a UAI user via a shared custom upstream."
},
{
"id": "shared-local/up_546be683db8840809905566e76670a0b/openai/gpt-4o-mini",
"object": "model",
"created": 1793382805,
"owned_by": "shared-local",
"context_length": 131072,
"description": "Hosted by a UAI user via a shared custom upstream."
},
{
"id": "shared-local/up_546be683db8840809905566e76670a0b/wg-i4905-probe",
"object": "model",
"created": 1793382805,
"owned_by": "shared-local",
"context_length": 131072,
"description": "Hosted by a UAI user via a shared custom upstream."
},
{
"id": "shared-local/up_7813652c75e34a05b1cd04db6d0f8555/canary/qa-canary-model-124096",
"object": "model",
"created": 1792071795,
"owned_by": "shared-local",
"context_length": 131072,
"description": "Hosted by a UAI user via a shared custom upstream."
},
{
"id": "shared-local/up_7813652c75e34a05b1cd04db6d0f8555/qa-canary-model-124096",
"object": "model",
"created": 1792071795,
"owned_by": "shared-local",
"context_length": 131072,
"description": "Hosted by a UAI user via a shared custom upstream."
},
{
"id": "shared-local/up_876c55ea2f924dcb9d1e55dd67e47e4a/orcarouter/Qwen3.8-27B-Uncensored:q4_K_M",
"object": "model",
"created": 1791208335,
"owned_by": "shared-local",
"context_length": 131072,
"description": "Hosted by a UAI user via a shared custom upstream."
},
{
"id": "shared-local/up_mac_ultra_local_ollama/qwen3.6:35b-a3b",
"object": "model",
"created": 1779792719,
"owned_by": "qwen",
"context_length": 131072,
"description": "Qwen3.6 35B A3B MoE model on Mac Ultra (M1 Ultra, 64 GB). Fast inference."
},
{
"id": "stepfun/step-3.5-flash",
"object": "model",
"created": 1774600871,
"owned_by": "stepfun",
"context_length": 262144,
"description": "Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token...."
},
{
"id": "stepfun/step-3.7-flash",
"object": "model",
"created": 1780034434,
"owned_by": "stepfun",
"context_length": 262144,
"description": "Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters..."
},
{
"id": "stepfun/step-5-preview",
"object": "model",
"created": 1791482468,
"owned_by": "stepfun",
"context_length": 1048576,
"description": "Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional..."
},
{
"id": "tencent/hunyuan-a13b-instruct",
"object": "model",
"created": 1774608817,
"owned_by": "tencent",
"context_length": 131072,
"description": "Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark..."
},
{
"id": "tencent/hy-mt2-1.8b",
"object": "model",
"created": 1787248854,
"owned_by": "tencent",
"context_length": 8192,
"description": "Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided..."
},
{
"id": "tencent/hy-mt2-30b-a3b",
"object": "model",
"created": 1787248854,
"owned_by": "tencent",
"context_length": 8192,
"description": "Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and..."
},
{
"id": "tencent/hy-mt2-7b",
"object": "model",
"created": 1787443208,
"owned_by": "tencent",
"context_length": 8192,
"description": "Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation."
},
{
"id": "tencent/hy3",
"object": "model",
"created": 1783360861,
"owned_by": "tencent",
"context_length": 262144,
"description": "Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:..."
},
{
"id": "tencent/hy3-preview",
"object": "model",
"created": 1778284805,
"owned_by": "tencent",
"context_length": 262144,
"description": "Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to..."
},
{
"id": "tencent/hy4-preview",
"object": "model",
"created": 1787918443,
"owned_by": "tencent",
"context_length": 1048576,
"description": "Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that..."
},
{
"id": "thedrummer/cydonia-24b-v4.1",
"object": "model",
"created": 1774608817,
"owned_by": "thedrummer",
"context_length": 131072,
"description": "Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence."
},
{
"id": "thedrummer/skyfall-36b-v2",
"object": "model",
"created": 1774608817,
"owned_by": "thedrummer",
"context_length": 32768,
"description": "Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling."
},
{
"id": "thedrummer/unslopnemo-12b",
"object": "model",
"created": 1774608817,
"owned_by": "thedrummer",
"context_length": 1024000,
"description": "UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios."
},
{
"id": "thinkingmachines/inkling",
"object": "model",
"created": 1784332856,
"owned_by": "thinkingmachines",
"context_length": 524288,
"description": "Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,..."
},
{
"id": "thinkingmachines/inkling-small",
"object": "model",
"created": 1785520847,
"owned_by": "thinkingmachines",
"context_length": 524288,
"description": "Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of..."
},
{
"id": "thinkingmachines/inkling-small:free",
"object": "model",
"created": 1787356808,
"owned_by": "thinkingmachines",
"context_length": 1048576,
"description": "Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of..."
},
{
"id": "thinkingmachines/inkling:free",
"object": "model",
"created": 1787356808,
"owned_by": "thinkingmachines",
"context_length": 1048576,
"description": "Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,..."
},
{
"id": "typesafe/jev-router",
"object": "model",
"created": 1791211614,
"owned_by": "typesafe",
"context_length": 1000000,
"description": "Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on [Jev](https://openrouter.ai/~typesafe/jev-latest), TypeSafe's first System One model, and adapts as your..."
},
{
"id": "unbiased/pareto-26.10",
"object": "model",
"created": 1792281610,
"owned_by": "unbiased",
"context_length": 1048576,
"description": "Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks."
},
{
"id": "unbiased/pareto-26.9",
"object": "model",
"created": 1791936060,
"owned_by": "unbiased",
"context_length": 262144,
"description": "Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks."
},
{
"id": "undi95/remm-slerp-l2-13b",
"object": "model",
"created": 1774608817,
"owned_by": "undi95",
"context_length": 6144,
"description": "A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge"
},
{
"id": "upstage/solar-mini4",
"object": "model",
"created": 1791211614,
"owned_by": "upstage",
"context_length": 524288,
"description": "Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response..."
},
{
"id": "upstage/solar-pro4",
"object": "model",
"created": 1786428041,
"owned_by": "upstage",
"context_length": 524288,
"description": "Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive..."
},
{
"id": "writer/palmyra-x5",
"object": "model",
"created": 1774600871,
"owned_by": "writer",
"context_length": 1040000,
"description": "Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million..."
},
{
"id": "x-ai/grok-4.20",
"object": "model",
"created": 1775001622,
"owned_by": "x-ai",
"context_length": 2000000,
"description": "Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering..."
},
{
"id": "x-ai/grok-4.20-multi-agent",
"object": "model",
"created": 1775001622,
"owned_by": "x-ai",
"context_length": 2000000,
"description": "Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information..."
},
{
"id": "x-ai/grok-4.3",
"object": "model",
"created": 1777593632,
"owned_by": "x-ai",
"context_length": 1000000,
"description": "Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual..."
},
{
"id": "x-ai/grok-4.3:batch",
"object": "model",
"created": 1788501633,
"owned_by": "x-ai",
"context_length": 1000000,
"description": "Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual..."
},
{
"id": "x-ai/grok-4.5",
"object": "model",
"created": 1783555259,
"owned_by": "x-ai",
"context_length": 500000,
"description": "Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM."
},
{
"id": "x-ai/grok-4.6",
"object": "model",
"created": 1786557637,
"owned_by": "x-ai",
"context_length": 500000,
"description": "Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7)."
},
{
"id": "x-ai/grok-4.7",
"object": "model",
"created": 1791211614,
"owned_by": "x-ai",
"context_length": 500000,
"description": "Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and..."
},
{
"id": "x-ai/grok-build-0.1",
"object": "model",
"created": 1779300061,
"owned_by": "x-ai",
"context_length": 256000,
"description": "Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding..."
},
{
"id": "xiaomi/mimo-v2.5",
"object": "model",
"created": 1776880863,
"owned_by": "xiaomi",
"context_length": 1050000,
"description": "MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding..."
},
{
"id": "xiaomi/mimo-v2.5-pro",
"object": "model",
"created": 1776880863,
"owned_by": "xiaomi",
"context_length": 1050000,
"description": "MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro...."
},
{
"id": "xiaomi/mimo-v2.6-flash",
"object": "model",
"created": 1791211614,
"owned_by": "xiaomi",
"context_length": 1050000,
"description": "MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for..."
},
{
"id": "xiaomi/mimo-v2.6-pro",
"object": "model",
"created": 1791211614,
"owned_by": "xiaomi",
"context_length": 1050000,
"description": "MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding..."
},
{
"id": "xiaomi/mimo-v2.6-pro-ultraspeed",
"object": "model",
"created": 1791211614,
"owned_by": "xiaomi",
"context_length": 1048576,
"description": "MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x..."
},
{
"id": "xingchen-agi/xing4.0-29b-a4b:free",
"object": "model",
"created": 1792195211,
"owned_by": "xingchen-agi",
"context_length": 262144,
"description": "Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It has 29B total parameters with 4B active per token..."
},
{
"id": "z-ai/glm-4.5",
"object": "model",
"created": 1774608817,
"owned_by": "z-ai",
"context_length": 131072,
"description": "GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly..."
},
{
"id": "z-ai/glm-4.5-air",
"object": "model",
"created": 1774608817,
"owned_by": "z-ai",
"context_length": 131072,
"description": "GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter..."
},
{
"id": "z-ai/glm-4.5v",
"object": "model",
"created": 1774608817,
"owned_by": "z-ai",
"context_length": 65536,
"description": "GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,..."
},
{
"id": "z-ai/glm-4.6",
"object": "model",
"created": 1774608817,
"owned_by": "z-ai",
"context_length": 204800,
"description": "Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex..."
},
{
"id": "z-ai/glm-4.6v",
"object": "model",
"created": 1774600871,
"owned_by": "z-ai",
"context_length": 131072,
"description": "GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts..."
},
{
"id": "z-ai/glm-4.7",
"object": "model",
"created": 1774600871,
"owned_by": "z-ai",
"context_length": 204800,
"description": "GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while..."
},
{
"id": "z-ai/glm-4.7-flash",
"object": "model",
"created": 1774600871,
"owned_by": "z-ai",
"context_length": 200000,
"description": "As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,..."
},
{
"id": "z-ai/glm-5",
"object": "model",
"created": 1774600871,
"owned_by": "z-ai",
"context_length": 204800,
"description": "GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading..."
},
{
"id": "z-ai/glm-5-turbo",
"object": "model",
"created": 1774600871,
"owned_by": "z-ai",
"context_length": 202752,
"description": "GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows..."
},
{
"id": "z-ai/glm-5.1",
"object": "model",
"created": 1775584829,
"owned_by": "z-ai",
"context_length": 204800,
"description": "GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on..."
},
{
"id": "z-ai/glm-5.2",
"object": "model",
"created": 1781632857,
"owned_by": "z-ai",
"context_length": 1048576,
"description": "GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,..."
},
{
"id": "z-ai/glm-5.3",
"object": "model",
"created": 1787097633,
"owned_by": "z-ai",
"context_length": 1048576,
"description": "GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves..."
},
{
"id": "z-ai/glm-5.3-flash",
"object": "model",
"created": 1787767243,
"owned_by": "z-ai",
"context_length": 1048576,
"description": "GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while..."
},
{
"id": "z-ai/glm-5.3-flash:batch",
"object": "model",
"created": 1787961643,
"owned_by": "z-ai",
"context_length": 1048576,
"description": "GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while..."
},
{
"id": "z-ai/glm-5.3-flashx",
"object": "model",
"created": 1791211614,
"owned_by": "z-ai",
"context_length": 1048576,
"description": "GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture..."
},
{
"id": "z-ai/glm-5.3-flashx-legal",
"object": "model",
"created": 1793642422,
"owned_by": "z-ai",
"context_length": 1048576,
"description": "GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement..."
},
{
"id": "z-ai/glm-5.3-prime",
"object": "model",
"created": 1791211614,
"owned_by": "z-ai",
"context_length": 1000000,
"description": "GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token..."
},
{
"id": "z-ai/glm-5.3:batch",
"object": "model",
"created": 1788890424,
"owned_by": "z-ai",
"context_length": 1048576,
"description": "GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves..."
},
{
"id": "z-ai/glm-5v-turbo",
"object": "model",
"created": 1775066420,
"owned_by": "z-ai",
"context_length": 202752,
"description": "GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,..."
}
]
}