{
"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": "~deepseek/deepseek-v4-flash-latest",
"object": "model",
"created": 1785628804,
"owned_by": "~deepseek",
"context_length": 1310720,
"description": "This model always redirects to the latest model in the DeepSeek V4 Flash 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-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": "~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": 1310720,
"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": 1310720,
"description": "This model always redirects to the latest GLM model from Z.ai."
},
{
"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": "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-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-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": "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": "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-v4-flash-0731",
"object": "model",
"created": 1785499247,
"owned_by": "deepseek",
"context_length": 1310720,
"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-0731:batch",
"object": "model",
"created": 1787961643,
"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-flash-vision-exp:batch",
"object": "model",
"created": 1788890424,
"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-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-pro-0813:batch",
"object": "model",
"created": 1787961643,
"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": "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": "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-3.1-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-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-3.5-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-3.6-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": "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-2.5",
"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": "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-fin",
"object": "model",
"created": 1788458433,
"owned_by": "inclusionai",
"context_length": 262144,
"description": "Ling 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for real-world investment..."
},
{
"id": "inclusionai/ling-3.0-flash-fin:free",
"object": "model",
"created": 1787853643,
"owned_by": "inclusionai",
"context_length": 262144,
"description": "Ling 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for real-world investment..."
},
{
"id": "inclusionai/ling-3.0-flash-sante:free",
"object": "model",
"created": 1788566433,
"owned_by": "inclusionai",
"context_length": 262144,
"description": "Ling 3.0 Flash Sante is a health and medicine-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for..."
},
{
"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-3.0-flash-vl:free",
"object": "model",
"created": 1789063210,
"owned_by": "inclusionai",
"context_length": 262144,
"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": "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": "kwaipilot/kat-coder-pro-v2.5",
"object": "model",
"created": 1784008815,
"owned_by": "kwaipilot",
"context_length": 262144,
"description": "KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make..."
},
{
"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": "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/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-glimmer-30b:batch",
"object": "model",
"created": 1787961643,
"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, audio, and PDF documents and returns text, with a 1M-token context..."
},
{
"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, audio, and PDF documents, returns text, and offers a 1M-token context..."
},
{
"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": "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": "nex-agi/nex-n2.5-mini:free",
"object": "model",
"created": 1788912022,
"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:free",
"object": "model",
"created": 1788912022,
"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": "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-3.5-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": "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.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode"
},
{
"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.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode"
},
{
"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.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode"
},
{
"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.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode"
},
{
"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.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode"
},
{
"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.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode"
},
{
"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.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode"
},
{
"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.\n\nLearn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode"
},
{
"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": "openrouter/auto-beta",
"object": "model",
"created": 1784332856,
"owned_by": "openrouter",
"context_length": 2000000,
"description": "Auto Router (Beta) is a task-aware router from OpenRouter. It classifies each request, then routes it the [most popular model](/rankings#task-spend) for that task based on aggregate spend, filtered by your..."
},
{
"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": "poolside/laguna-s-2.1",
"object": "model",
"created": 1784656832,
"owned_by": "poolside",
"context_length": 1048576,
"description": "Laguna S 2.1 is the latest coding agent model from [Poolside](). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and..."
},
{
"id": "poolside/laguna-s-2.1:free",
"object": "model",
"created": 1784656832,
"owned_by": "poolside",
"context_length": 262144,
"description": "Laguna S 2.1 is the latest coding agent model from [Poolside](). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and..."
},
{
"id": "poolside/laguna-xs-2.1",
"object": "model",
"created": 1783015223,
"owned_by": "poolside",
"context_length": 262144,
"description": "Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines..."
},
{
"id": "poolside/laguna-xs-2.1:free",
"object": "model",
"created": 1783015223,
"owned_by": "poolside",
"context_length": 262144,
"description": "Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines..."
},
{
"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/qwen3.8-2.4t-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/qwen3.8-2.4t-a95b:batch",
"object": "model",
"created": 1787940044,
"owned_by": "qwen",
"context_length": 1010000,
"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": 1000000,
"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": "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": "shared-local/up_lenovo_rtx8000_ollama/nomic-embed-text",
"object": "model",
"created": 1779790870,
"owned_by": "nomic",
"context_length": 8192,
"description": "nomic-embed-text v1.5 — 768-dim embeddings, running on Lenovo RTX 8000 GPU."
},
{
"id": "shared-local/up_lenovo_rtx8000_ollama/qwen3:8b",
"object": "model",
"created": 1778324440,
"owned_by": "shared-local",
"context_length": 131072,
"description": "Hosted by a UAI user via a shared custom upstream."
},
{
"id": "shared-local/up_lenovo_rtx8000_ollama/qwen3:8b-cpu",
"object": "model",
"created": 1778324440,
"owned_by": "shared-local",
"context_length": 131072,
"description": "Hosted by a UAI user via a shared custom upstream."
},
{
"id": "shared-local/up_lenovo_rtx8000_ollama/qwen3.6:35b-a3b",
"object": "model",
"created": 1779790870,
"owned_by": "qwen",
"context_length": 262144,
"description": "Qwen3.6 35B A3B MoE model running on dual Quadro RTX 8000 (92 GB total VRAM) on Lenovo server. noThink mode. Fast inference with GPU load balancing across both cards."
},
{
"id": "shared-local/up_mac_ultra_local_ollama/nomic-embed-text",
"object": "model",
"created": 1779792719,
"owned_by": "nomic",
"context_length": 8192,
"description": "Nomic Embed Text 768-dim embeddings on Mac Ultra (M1 Ultra, 64 GB)."
},
{
"id": "shared-local/up_mac_ultra_local_ollama/qwen3.6:35b-a3b",
"object": "model",
"created": 1779792719,
"owned_by": "qwen",
"context_length": 262144,
"description": "Qwen3.6 35B A3B MoE model on Mac Ultra (M1 Ultra, 64 GB). Fast inference."
},
{
"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/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": "thinkingmachines/inkling",
"object": "model",
"created": 1784332856,
"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": "thinkingmachines/inkling-small",
"object": "model",
"created": 1785520847,
"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-small:batch",
"object": "model",
"created": 1787961643,
"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:batch",
"object": "model",
"created": 1786039230,
"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: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": "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": "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 SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM."
},
{
"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-5.2:batch",
"object": "model",
"created": 1786039230,
"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": 1310720,
"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": 1310720,
"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: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..."
}
]
}