Supported AI models.

LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48…

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Mac…

Auto Router (Beta) is a task-aware router from OpenRouter. It classifies each r…

Native multimodal flagship (text, image, video inputs) with thinking on by defa…

Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tas…

KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly h…

KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly h…

GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with `r…

GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with `reaso…

GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with `rea…

This model always redirects to the latest Grok model from xAI.

xAI's smartest and fastest model with frontier performance on coding, knowledge…

Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLab…

Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, bu…

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192…

Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from Poo…

Gemini 3.1 Flash Lite Image.

Google Gemma 4 31B on Cerebras - first multimodal model on wafer-scale inferenc…

Gemini Omni Flash Preview

Qwen chat model.

Qwen chat model.

Best combination of speed and intelligence, with the largest gains in coding an…

Best combination of speed and intelligence, with the largest gains in coding an…

Balanced model for efficient, high-volume everyday work. Competitive with GPT-5…

Flagship next-generation model. Strongest yet for agentic coding, science, and…

Fastest, most affordable GPT-5.6 model for high-volume work. Strong capability…

Zhipu GLM-5.2 served via Alibaba Model Studio. 1M context, thinking.

Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather t…

Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, th…

Orchestrator specialized for cybersecurity reasoning: security analysis, vulner…

Fast orchestration model routing tasks across a swappable pool of frontier LLMs…

Flagship agent model with native extended thinking and 1M context. Text-only; s…

North Mini Code is Cohere's first agentic coding model and the debut of its Nor…

Fusion turns your prompt into a small multi-model deliberation. A panel of expe…

Z.ai 1M-context flagship (744B MoE, 40B activated). Agentic coding with reasoni…

Most capable widely released model for the most demanding reasoning and long-ho…

Most capable widely released model for the most demanding reasoning and long-ho…

This model always redirects to the latest model in the Claude Fable family.

Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active…

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardra…

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model f…

Meta chat model. https://huggingface.co/api/models/RedHatAI/Llama-4-Maverick-17…

Zai Org chat model.

Multimodal agent model with 1M context, native thinking, and vision/video under…

High-speed code variant with ~180 tok/s output (up to 260 in short contexts). N…

Code-focused multimodal model (text, image, video inputs) with always-on thinki…

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, ima…

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Expert…

Gemini 3 Pro Image

Gemini 3.1 Flash Image.

Most capable Opus-tier model for complex reasoning and agentic coding (Bedrock…

Most capable Opus-tier model for complex reasoning and agentic coding

Fast-mode variant of Opus 4.8 - identical capabilities with higher output speed…

Flagship agent model with native extended thinking and 1M context. Text-only; s…

xAI fast coding model with reasoning, function calling, and structured outputs.…

Meta chat model.

Gemini 3.5 Flash

Preview release of Antigravity Agent (05-2026)

Google chat model. https://huggingface.co/api/models/google/gemma-4-31B-it

Google chat model.

Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model…

Fast-mode variant of Opus 4.7 - identical capabilities with higher output speed…

Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters,…

Mistral AI chat model.

Google chat model.

Gemini 3.1 Flash Lite

Meta chat model.

GPT Chat Latest

Cohere flagship. Agentic reasoning with vision, tool use, and long-context RAG.…

Current vision-language model with strong visual reasoning and thinking. Tiered…

Official mistral-medium-latest Mistral AI model

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from…

Laguna XS.2 is the second-generation model in the XS size class from Poolside,…

Laguna M.1 is the flagship coding agent model from Poolside, optimized for comp…

Owl Alpha is a high-performance foundation model designed for agentic workloads…

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to fun…

Nvidia chat model.

Official mistral-medium-latest Mistral AI model

Official mistral-medium-latest Mistral AI model

Alibaba model (not yet curated).

Fast, cost-effective multimodal model with 1M context, near-flagship quality, v…

Alibaba model (not yet curated).

Alibaba model (not yet curated).

Alibaba model (not yet curated).

This model always redirects to the latest model in the OpenAI GPT Mini family.

This model always redirects to the latest model in the OpenAI GPT family.

This model always redirects to the latest model in the MoonshotAI Kimi family.

This model always redirects to the latest model in the Google Gemini Pro family.

This model always redirects to the latest model in the Google Gemini Flash fami…

This model always redirects to the latest model in the Anthropic Claude Sonnet…

This model always redirects to the latest model in the Anthropic Claude Haiku f…

Premium reasoning model with 1M context. Supports extended thinking modes, JSON…

Fast general-purpose model with 1M context. Supports extended thinking modes, J…

Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s t…

Most capable model for complex tasks. Uses more compute for smarter, more preci…

New baseline for complex production workflows. Stronger task execution, more pr…

MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in gene…

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic…

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed…

Qwen chat model. https://huggingface.co/api/models/Qwen/Qwen3.6-35B-A3B-FP8

The Pareto Router maintains a tiered shortlist of strong coding models, ranked…

GPT-5.4 Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image gen…

Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total…

Google chat model. https://huggingface.co/api/models/google/gemma-4-E2B-it

Preview release (April 21th, 2026) of Deep Research

Preview release (April 21st, 2026) of Deep Research Max

This model always redirects to the latest model in the Claude Opus family.

Native multimodal flagship (text, image, video inputs) with thinking and non-th…

xAI's latest flagship model with reasoning and a 1M token context window. Suppo…

Google chat model. https://huggingface.co/google/gemma-4-E4B-it

Previous most capable model for complex reasoning and agentic coding (Bedrock I…

Previous most capable model for complex reasoning and agentic coding

Gemini 3.1 Flash TTS Preview

Gemini Robotics-ER 1.6 Preview

Nvidia chat model. https://huggingface.co/api/models/nvidia/NVIDIA-Nemotron-3-S…

Z.ai flagship (744B MoE, 40B activated). Post-training upgrade over GLM-5 with…

Alibaba model (not yet curated).

Gemma 4 31B IT

Gemma 4 26B A4B IT

First multimodal GLM-5 model. Vision-based coding agent with image/video/file i…

Trinity Large Thinking is a powerful open source reasoning model from the team…

Grok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborativ…

Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic…

Hcompany chat model. https://huggingface.co/api/models/Hcompany/Holo3-35B-A3B

Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of m…

30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's fami…

KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder se…

Qwen chat model.

DeepSeek chat model. https://huggingface.co/deepseek-ai/DeepSeek-V3.1

Reka Edge is an extremely efficient 7B multimodal vision-language model that ac…

Qwen chat model.

MiniMax-M2.7 is a next-generation large language model designed for autonomous,…

Cheapest GPT-5.4-class model for simple high-volume tasks like classification a…

Strongest mini model for coding, computer use, and subagents. GPT-5.4-class int…

Qwen chat model. https://huggingface.co/api/models/Qwen/Qwen3.5-122B-A10B-FP8

Mistral Small 4.

Mistral Small 4.

A mid & post-trained version of mistral small 4 for Lean

Speed-optimized GLM-5 variant for agent workflows. Enhanced tool invocation and…

Deepseek chat model. https://huggingface.co/api/models/deepseek-ai/DeepSeek-OCR…

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating j…

Nvidia chat model. https://huggingface.co/api/models/nvidia/NVIDIA-Nemotron-3-S…

Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed t…

Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers…

xAI flagship reasoning model with a 1M token context window. Deep reasoning and…

Multi-agent model that runs specialized agents in parallel for collaborative ve…

xAI flagship model with a 1M token context window. Non-reasoning variant for fa…

Qwen chat model. https://huggingface.co/api/models/togethercomputer/Qwen3.5-9B-…

Most capable model for complex tasks. Uses more compute for smarter, more preci…

Most capable and efficient frontier model for professional work. Native compute…

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion…

GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conv…

GPT-5.3 Instant model, previously powering ChatGPT. Replaced by GPT-5.5 Instant.

Zai Org chat model. https://huggingface.co/api/models/zai-org/GLM-4.7-FP8

Gemini 3.1 Flash Lite Preview

Gemini 3.1 Flash Image Preview.

Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive s…

Alibaba model (not yet curated).

Alibaba model (not yet curated).

Alibaba model (not yet curated).

The Qwen3.5 native vision-language Flash models are built on a hybrid architect…

LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures de…

Best voice model for audio in, audio out with Chat Completions. Accepts audio i…

Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and…

Gemini 3.1 Pro Preview optimized for custom tool usage

Gemini 3.1 Pro Preview

Best combination of speed and intelligence for everyday tasks (Bedrock Inferenc…

Best combination of speed and intelligence for everyday tasks

Alibaba model (not yet curated).

The Qwen3.5 native vision-language series Plus models are built on a hybrid arc…

MiniMaxAI chat model.

MiniMax-M2.5 is a SOTA large language model designed for real-world productivit…

Zai Org chat model. https://huggingface.co/api/models/togethercomputer/GLM-5-FP4

Z.ai flagship foundation model (744B MoE, 40B activated). Designed for Agentic…

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designe…

Most capable agentic coding model. Combines frontier coding performance of GPT-…

Previous most intelligent model for complex agents and coding, with adaptive th…

Previous most intelligent model for complex agents and coding, with adaptive th…

Alibaba model (not yet curated).

Specialized OCR model for text extraction from images and documents.

The simplest way to get free inference. openrouter/free is a router that select…

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on…

Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With…

Supports vision (images/videos), thinking mode, and Agent tasks. 256K context.

MiniMax M2-her is a dialogue-first large language model built for immersive rol…

Palmyra X5 is Writer's most advanced model, purpose-built for building and scal…

LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for age…

LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model bui…

Fast GLM-4.7 variant with priority routing and higher concurrency. Same model a…

Free GLM-4.7 variant. Same model as FlashX but with limited concurrency (1 conc…

Z.AI model via OpenAI-Compatible API (Bedrock Foundation Model)

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized…

Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance See…

Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It inc…

Latest-gen GLM model with 128K context. Thinking mode activated by default.

Gemini 3 Flash Preview

Nvidia chat model. https://huggingface.co/api/models/nvidia/NVIDIA-Nemotron-3-N…

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compu…

GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, o…

Smartest and most trustworthy option for difficult questions. Uses more compute…

GPT-5.2 Instant model, previously powering ChatGPT. Replaced by GPT-5.5 Instant.

GPT-5.2 optimized for long-horizon, agentic coding tasks in Codex or similar en…

Most capable model for professional work and long-running agents. Improvements…

Preview release (December 12th, 2025) of Deep Research Pro

Mobile phone automation agent. Understands phone screens via multimodal percept…

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing i…

Official mistral-medium-latest Mistral AI model

Official devstral-2512 Mistral AI model

Official devstral-2512 Mistral AI model

The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to e…

Fast vision GLM-4.6 with priority routing and higher concurrency. Image/video/f…

Free vision GLM-4.6. Same model as FlashX but with limited concurrency (1 concu…

Vision-enabled GLM-4.6 model. Supports image/video/file inputs, 32K output, hyb…

Essential AI chat model. https://huggingface.co/api/models/togethercomputer/Ess…

Transform your natural language requests into structured OpenRouter API request…

Official mistral-large-2512 Mistral AI model

Ministral 3 (a.k.a. Tinystral) 8B Instruct.

Ministral 3 (a.k.a. Tinystral) 3B Instruct.

Ministral 3 (a.k.a. Tinystral) 14B Instruct.

Ministral 3 (a.k.a. Tinystral) 8B Instruct.

Ministral 3 (a.k.a. Tinystral) 3B Instruct.

Mistralai chat model. https://huggingface.co/api/models/mistralai/Ministral-3-1…

Ministral 3 (a.k.a. Tinystral) 14B Instruct.

Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads th…

Official mistral-large-2512 Mistral AI model

DeepSeek-V3.2 is a large language model designed to harmonize high computationa…

Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language…

Previous most intelligent model with advanced reasoning for complex agentic wor…

Previous most intelligent model with advanced reasoning for complex agentic wor…

Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for…

Gemini 3 Pro Image Preview

Gemini 3 Pro Image Preview

Our most intelligent coding model optimized for long-horizon, agentic coding ta…

Smaller, faster version of GPT-5.1 Codex for efficient coding tasks.

A version of GPT-5.1 optimized for agentic coding tasks in Codex or similar env…

The best model for coding and agentic tasks with configurable reasoning effort.

Cogito v2.1 671B MoE represents one of the strongest open models globally, matc…

GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, op…

GPT-5.1 Instant with adaptive reasoning. More conversational with improved inst…

Qwen chat model. https://huggingface.co/api/models/Qwen/Qwen3-VL-235B-A22B-Inst…

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, e…

Amazon Nova Premier is the most capable of Amazon’s multimodal models for compl…

Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is…

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-…

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-os…

NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning m…

Google chat model. https://huggingface.co/api/models/google/medgemma-27b-text-it

Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designe…

MiniMax-M2 is a compact, high-efficiency large language model optimized for end…

Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. Thes…

Phi-4-mini-instruct is a lightweight open model built upon synthetic data and f…

Fastest model with exceptional speed and performance (Bedrock Inference Profile)

Fastest model with exceptional speed and performance

Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B mult…

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL se…

Updated web search model in Chat Completions API. 60% cheaper with domain filte…

Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning…

Gemini 2.5 Computer Use Preview 10-2025

Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text genera…

Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text genera…

Version of GPT-5 that uses more compute to produce smarter and more precise res…

Cost-efficient audio model. Accepts audio inputs and outputs via Chat Completio…

Gemini 2.5 Flash Preview Image

GLM-4.6 model with 128K context/output. Hybrid thinking: auto-determines whethe…

Google chat model. https://huggingface.co/api/models/google/gemma-3-270m-it

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek…

Previous best combination of speed and intelligence for complex agents and codi…

Previous best combination of speed and intelligence for complex agents and codi…

Uncensored and creative writing model based on Mistral Small 3.2 24B with good…

Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edit…

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family…

Qwen chat model. https://huggingface.co/api/models/Qwen/Qwen3-Next-80B-A3B-Inst…

Alibaba model (not yet curated).

Alibaba model (not yet curated).

Alibaba model (not yet curated).

Agentic coding model with very long context. Tiered pricing by input length (up…

DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's…

Alibaba model (not yet curated).

Nvidia chat model. https://huggingface.co/api/models/nvidia/NVIDIA-Nemotron-Nan…

Mistral Small 4.

Our frontier-class reasoning model release candidate September 2025.

Our efficient reasoning model released September 2025.

Our frontier-class reasoning model release candidate September 2025.

A version of GPT-5 optimized for agentic coding in Codex.

Alibaba model (not yet curated).