Every model, unlimited possibilities
Frontier and open models, pre-warmed and ready. Route to any of them from a single Claws endpoint, swap providers without rewriting a line. Here’s what’s powering agents this week.

gpt-6.2-astra-proGPT-6.2 Astra Pro is the same underlying model as [GPT-6.2 Astra](https://openrouter.ai/openai/gpt-6.2-astra), served with `reasoning.mod…
Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning,…

gpt-astra-latestThis model always redirects to the latest model in the GPT Astra family.
Gemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work.
Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks.

fugu-ultra-v2Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family.
MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro.
Qwen4 Max is the flagship model in Alibaba's Qwen4 series.

ernie-light-dt-1.0-intlERNIE-Light-DT-1.0 is based on open-source GLM models and includes research findings from Baidu Search's Lightning large model.

pareto-26.9Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance acr…

ember-1Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3).

aion-3.5Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.
Hy4 flash is a cost-efficient variant of [Hy4](https://openrouter.ai/tencent/hy4) from Tencent, served with roughly a quarter of the flag…

claude-fable-latestThis model always redirects to the latest model in the Claude Fable family.

inkling-2-smallInkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters ou…

ling-3.2-flash:freeLing 3.2 Flash is a hybrid reasoning model from inclusionAI that accepts text and image input, with a 1M-token context window and up to 2…

nex-n2.6Nex-N2.6 is an agentic model from Nex AGI, built on [GLM-5.3-Flash](https://huggingface.co/zai-org/GLM-5.3-Flash-BF16) with about 321B pa…
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, an…

midm-k-3.0-proMi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters.

motif-3Motif 3 is a Mixture-of-Experts language model from Motif Technologies, with 314B total and 13.2B active parameters.

lfm-3-1.7bA compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs.

ripple-65b-previewRipple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.
Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6.

kimi-k3.1-pro:batchKimi 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 c…

pareto-latestThis model always redirects to the latest model in the Pareto family.

particle-1Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash.

glimpseGlimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical…

step-5-previewStep 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total p…

minimax-m3.1-flashMiniMax-M3.1-Flash is a multimodal model from MiniMax.

flint-v1.0:freeFlint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's…

moondream3-previewMoondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts).

beam-1.0-501b-a23bBeam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows.
Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.
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…

nemotron-3.5-super-vlNVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.

ternary-bonsai-2-9bTernary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use.

summarizeSummarize is an abstractive summarization model from ScaleDown.
Command A+ is Cohere's flagship model for enterprise agentic workflows.

perceptron-mk1.5Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents.

solar-mini4Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K…

deepseek-pro-latestThis model always redirects to the latest model in the DeepSeek Pro family.

schematron-v2-smallSchematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net.

granite-4.2-8bGranite 4.2 8B is a dense reasoning model from IBM.

glm-flash-latestThis model always redirects to the latest model in the GLM Flash family.

seed-2-1-turboSeed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows.

grok-latestThis model always redirects to the latest Grok model from xAI.

dots-3-note-preview:freeDots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total.

longcat-2.0LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total.

gemini-pro-latestThis model always redirects to the latest model in the Gemini Pro family.

kimi-latestThis model always redirects to the latest model in the Kimi family.

reka-edgeReka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs.

palmyra-x5Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise.

freeThe simplest way to get free inference.

sonar-pro-searchExclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system.

nova-premier-v1Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for dis…

magnum-v4-72bThis is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anth…

relace-searchThe relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user re…

hermes-4-405bHermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research.

morph-v3-largeMorph's high-accuracy apply model for complex code edits.

l3.1-euryale-70bEuryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k).
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors.

skyfall-36b-v2Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-pla…

weaverAn attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory.

remm-slerp-l2-13bA recreation trial of the original MythoMax-L2-B13 but with updated models.

dolphin-mistral-24b-venice-editionVenice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in…

ui-tars-1.5-7bUI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobil…

mythomax-l2-13bOne of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay.
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations w…

jev-routerJev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost.

gpt-6.2-astraGPT-6.2 Astra is the flagship model in the GPT-6.2 series from OpenAI, built for the hardest projects.
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, a…

gpt-sol-latestThis model always redirects to the latest model in the GPT Sol family.
Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work.
Muse Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat…

fugu-maxFugu Max is the cost-performance model in Sakana AI's Fugu family.
MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi.
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.

ernie-5.5-flash-preview:freeERNIE 5.5 Flash Preview is the latest foundation model in the ERNIE family, with comprehensive improvements in coding, agentic capabiliti…

pareto-26.10Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance acr…

aion-3.5-miniAion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.
The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agent…

claude-opus-latestThis model always redirects to the latest model in the Claude Opus family.

inkling-smallInkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B to…

ling-3.1-flashLing 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.

nex-n2.5-proNex-N2.5 is an agentic model built to turn goals into working, verified outcomes.
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…

lfm-3-1.7b:freeA compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs.
Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6.

kimi-k3.1-proKimi 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 c…

particle-1:freeParticle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash.

step-3.7-flashStep 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model.

minimax-m3MiniMax-M3 is a multimodal foundation model from MiniMax.

moondream3.1-9b-a2bMoondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mi…
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.
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…

nemotron-3.5-super-vl:freeNVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.

ternary-bonsai-2-27bBonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B.

extractExtract is a description-driven entity extraction model from ScaleDown.
North Mini Code is Cohere's first agentic coding model and the debut of its North family.

perceptron-mk1Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and…

solar-pro4Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window.

deepseek-flash-latestThis model always redirects to the latest model in the DeepSeek Flash family.

schematron-v2-turboSchematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net.

glm-latestThis model always redirects to the latest GLM model from Z.ai.

seed-2.0-liteSeed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering n…

gemini-flash-latestThis model always redirects to the latest model in the Gemini Flash family.

reka-flash-3Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka.

autoAuto is OpenRouter’s flagship model router, built for general-purpose usage.

sonar-proNote: Sonar Pro pricing includes Perplexity search pricing.

nova-2-lite-v1Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text.

relace-apply-3Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files.

morph-v3-fastMorph's fastest apply model for code edits.

l3-lunaris-8bLunaris 8B is a versatile generalist and roleplaying model based on Llama 3.
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).

unslopnemo-12bUnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.

gpt-6-astraGPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.
Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning,…

gpt-terra-latestThis model always redirects to the latest model in the GPT Terra family.
Gemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work.
Muse Spark Open is a coding-optimized open-weight model.

fugu-ultraFugu Ultra is the higher-performance model in Sakana AI's Fugu family.
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi.
Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team.

pareto-26.10-previewPareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance acr…

aion-3.0Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total.

claude-sonnet-latestThis model always redirects to the latest model in the Claude Sonnet family.

inkling-small:batchInkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B to…

ling-3.0-flash-vlLing 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabiliti…

nex-n2.5-miniNex-N2.5 is an agentic model built to turn goals into working, verified outcomes.
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 toke…

lfm-2.5-24b-a2bLFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters.
Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

kimi-k3:batchKimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.

minimax-m3:batchMiniMax-M3 is a multimodal foundation model from MiniMax.
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.
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)…

nemotron-3.5-lightningNVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.
Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, mult…

deepseek-v4-flash-latestThis model always redirects to the latest model in the DeepSeek V4 Flash family.

seed-2.0-miniSeed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference…

auto-codeAuto Code is OpenRouter’s router built specifically for coding agents and harnesses.

sonar-reasoning-proNote: Sonar Pro pricing includes Perplexity search pricing.

nova-pro-v1Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide…

morph-v3-large:batchMorph's high-accuracy apply model for complex code edits.
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architec…

cydonia-24b-v4.1Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.

gpt-6-astra-proGPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set…
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding.

gpt-luna-latestThis model always redirects to the latest model in the GPT Luna family.
Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows,…
Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows.

sakana-namazuSakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language…
MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, an…
Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team.

aion-3.0-miniAion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models.
Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family.

claude-haiku-latestThis model always redirects to the latest model in the Claude Haiku family.

inklingInkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.

ling-3.0-tinyLing 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total.
GLM-5.3-Flash is a native multimodal model from Z.ai.
Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

kimi-k3Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.

minimax-m2.7MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement.
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into…
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)…

nemotron-3.5-lightning:freeNVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.
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 l…

auto-betaThe experimental version of our Auto Router where we test new improvements.

sonar-deep-researchSonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics.

nova-lite-v1Amazon 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…

morph-v3-fast:batchMorph's fastest apply model for code edits.
Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification.

gpt-5.5-proGPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads.
Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.

gpt-mini-latestThis model always redirects to the latest model in the GPT Mini family.
Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash.
Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and…
MiMo-V2.5 is a native omnimodal model by Xiaomi.
Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audi…

aion-2.0Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling.
Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent.

ling-3.0-flash*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*.
GLM-5.3-Flash is a native multimodal model from Z.ai.
Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

kimi-k2.7-codeMoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reli…

minimax-m2.5MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.
This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407).
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepsee…

nemotron-3-ultra-550b-a55bNVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (…
command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmente…

fusionFusion turns your prompt into a small multi-model deliberation.

sonarSonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources.

nova-micro-v1Amazon 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 c…
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of…

gpt-5.5-pro:batchGPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads.
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, a…
Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni…
Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks.
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-…

aion-rp-llama-3.1-8bAion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant…
Hy-MT2-7B is a 7B-parameter translation model from Tencent.
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows.

kimi-k2.6Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-…
Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b).
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.

nemotron-3.5-content-safetyNVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B.
Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024.

pareto-codeThe Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) c…
Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like di…

gpt-6.2-astra-pro:batchGPT-6.2 Astra Pro is the same underlying model as [GPT-6.2 Astra](https://openrouter.ai/openai/gpt-6.2-astra), served with `reasoning.mod…
Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.
Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work.
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.
Qwen3.8 Flash is a multimodal reasoning model from Alibaba.
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic w…
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
Grok 4.3 is a reasoning model from SpaceXAI.

kimi-k2.5Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm…
This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`).
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.

nemotron-3-ultra-550b-a55b:freeNVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (…

bodybuilderTransform your natural language requests into structured OpenRouter API request objects.
Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dia…

gpt-6.2-astra:batchGPT-6.2 Astra is the flagship model in the GPT-6.2 series from OpenAI, built for the hardest projects.
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.
Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows,…
Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for a…
Qwen3.8 27B is an open-weight dense vision-language model from Qwen.
Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use.
GLM 5.2 is a large-scale reasoning model from Z.ai.
Grok 4.3 is a reasoning model from SpaceXAI.

kimi-k2-thinkingKimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.
Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding.
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.

nemotron-3-nano-omni-30b-a3b-reasoning:freeNVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise…
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors.

gpt-5.4-proGPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex,…
Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.
Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem sol…
Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for a…
Qwen3.8 27B is an open-weight dense vision-language model from Qwen.
GLM 5.2 is a large-scale reasoning model from Z.ai.
Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows.

kimi-k2-0905Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2).
Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active paramete…
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporti…

nemotron-3-super-120b-a12bNVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accu…

gpt-5.4-pro:batchGPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex,…
Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.
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 N…
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks.
Qwen3.7 Flash is a vision-language reasoning model from Alibaba.
GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks.
Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities.

kimi-k2Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters…
The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistra…
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated paramete…

nemotron-3-nano-30b-a3bNVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build special…

gpt-6.2-sol-proGPT-6.2 Sol Pro is the same underlying model as [GPT-6.2 Sol](https://openrouter.ai/openai/gpt-6.2-sol), served with `reasoning.mode` set…
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.
Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem sol…
Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series.
GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks.
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use pe…

switchyardSwitchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests.

gpt-6.2-solGPT-6.2 Sol is an upgrade to GPT-6.1 Sol from OpenAI, positioned below the flagship GPT-6.2 Astra in the GPT-6.2 series.
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic task…
Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series.
GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw sce…
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced an…

gpt-6-astra:batchGPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding.
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic task…
Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series.
GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows.
Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to del…
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.

gpt-6-astra-pro:batchGPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set…
Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks.
Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.
Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.
As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency.
Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly r…
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectu…

gpt-6.2-sol-pro:batchGPT-6.2 Sol Pro is the same underlying model as [GPT-6.2 Sol](https://openrouter.ai/openai/gpt-6.2-sol), served with `reasoning.mode` set…
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.
Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.
Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba.
GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-ste…
Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal…
DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities whi…

gpt-6.2-sol:batchGPT-6.2 Sol is an upgrade to GPT-6.1 Sol from OpenAI, positioned below the flagship GPT-6.2 Astra in the GPT-6.2 series.
Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.
Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development.
Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series.
GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents,…
Mistral's cutting-edge language model for coding released end of July 2025.
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous vers…

gpt-6.1-terra-proGPT-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.mod…
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.
Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development.
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters pe…
GLM-4.5V is a vision-language foundation model for multimodal agent applications.
Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextu…
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prom…

gpt-6.1-terraGPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol.
Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro.
Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling s…
GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications.
Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class…

gpt-6.1-sol-proGPT-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…
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.
Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities.
Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understandi…
Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from…
Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduct…

gpt-6.1-solGPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series.
Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.
Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities.
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a…
GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications.
Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks.

gpt-6.1-terra-pro:batchGPT-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.mod…
Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity dev…
The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balanc…
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.

gpt-6.1-terra:batchGPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol.
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.
Gemini 3.1 Flash Image, a.k.a.
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechani…

gpt-6-sol-proGPT-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 `p…
Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.
Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed.
The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sp…

gpt-6-solGPT-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…
Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks.
Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed.
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism…

gpt-6.1-sol-pro:batchGPT-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…
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.
Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.
The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with…

gpt-6.1-sol:batchGPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series.
Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.
Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows.

gpt-6-sol-pro:batchGPT-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 `p…
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon c…
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 gener…
Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects.

gpt-6-sol:batchGPT-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…
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows.
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen).

gpt-5.2-proGPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro.
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon c…
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning…

gpt-5.4-image-2[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 capabiliti…
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows.
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
Qwen2.5 72B is the latest series of Qwen large language models.

gpt-5.6-sol-proGPT-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…
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and lat…
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team.

gpt-5.6-solGPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series.
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and lat…
Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic relia…
Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.

gpt-6-luna-proGPT-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…
Full-length songs are priced at $0.08 per song.
Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning…

gpt-6-lunaGPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.
30 second duration clips are priced at $0.04 per clip.
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across image…

gpt-6-luna-pro:batchGPT-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…
Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic relia…
Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus.

gpt-6-luna:batchGPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.
Gemini 3.1 Flash Image Preview, a.k.a.
Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos.

gpt-5-proGPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.
Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases.
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed f…

o3-proThe o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning.
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro.
Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture…

gpt-4OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy tha…
Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance.
Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to e…

gpt-5.6-terra-proGPT-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.mod…
Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance.
Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialo…

gpt-5.6-terraGPT-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.
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thi…

gpt-5.6-sol-pro:batchGPT-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…
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference.

gpt-5.6-sol:batchGPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series.
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).
Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dial…

gpt-chat-latestGPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT.
Gemini 2.5 Flash Image, a.k.a.

gpt-5.5GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher relia…
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and sci…

gpt-5.6-terra-pro:batchGPT-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.mod…
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency.

gpt-5.6-terra:batchGPT-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.
Gemma 3 introduces multimodality, supporting vision-language input and text outputs.

gpt-5.6-luna-proGPT-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`…
Gemma 3 introduces multimodality, supporting vision-language input and text outputs.

gpt-5.6-lunaGPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.
Gemma 3 introduces multimodality, supporting vision-language input and text outputs.

gpt-5.6-luna-pro:batchGPT-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`…

gpt-5.6-luna:batchGPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.

gpt-5.2-pro:batchGPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro.

gpt-5.5:batchGPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher relia…

gpt-5-image[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities.

gpt-5.4GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.

gpt-5-pro:batchGPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.

gpt-5.4-miniGPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.

gpt-5.3-codexGPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex wi…

gpt-5.4:batchGPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.

gpt-5.4-mini:batchGPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.

gpt-5.4-nanoGPT-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.

gpt-5.4-nano:batchGPT-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.

gpt-audioThe gpt-audio model is OpenAI's first generally available audio model.

gpt-4o-2024-05-13GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.

gpt-4-turbo:batchThe latest GPT-4 Turbo model with vision capabilities.

gpt-5.2-codexGPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows.

gpt-audio-miniA cost-efficient version of GPT Audio.

gpt-3.5-turbo-16kThis model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single reque…

gpt-5.2-chatGPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong gener…

gpt-5.2GPT-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.

gpt-5-image-miniGPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with…

gpt-4o-2024-11-20The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improv…

gpt-4o-2024-08-06The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respo…

gpt-4oGPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.

gpt-5.1-codex-maxGPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks.

o3o3 is a well-rounded and powerful model across domains.

gpt-4.1GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-contex…

gpt-5.2:batchGPT-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.

gpt-5.1GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adheren…

gpt-5.1-codexGPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows.

gpt-5GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.

gpt-4o:batchGPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.

o3:batcho3 is a well-rounded and powerful model across domains.

gpt-4.1:batchGPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-contex…

gpt-3.5-turbo-0613GPT-3.5 Turbo is OpenAI's fastest model.

gpt-5.1:batchGPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adheren…

gpt-5:batchGPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.

o4-mini:batchOpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multim…

o3-mini:batchOpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and…

gpt-4.1-miniGPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost.

gpt-5.1-codex-miniGPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex

gpt-5-miniGPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks.

gpt-4.1-mini:batchGPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost.

gpt-oss-120bgpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic,…

gpt-4o-miniGPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.

gpt-4o-mini-2024-07-18GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.

gpt-5-mini:batchGPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks.

gpt-4.1-nanoFor tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series.

gpt-oss-safeguard-20bgpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b.

gpt-4o-mini:batchGPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.

gpt-5-nanoGPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low late…

gpt-4.1-nano:batchFor tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series.

gpt-oss-120b:batchgpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic,…

gpt-5-nano:batchGPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low late…

gpt-oss-20b:batchgpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.

gpt-oss-20bgpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.
Pick a model and ship today.
Spin up any agent framework free, route to any of these models, and only pay for the tokens you use.