Supported AI models.

Tencent: Hy4 preview is a mixture-of-experts model from Tencent…

Ling 3.0 Flash Fin is a finance-focused mixture-of-experts mode…

Gemini Omni 1.1 Flash

Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It…

Gemini 3.5 Transcribe

Multimodal Flash on a new 320B MoE base (18B activated, hybrid…

Muse Spark 1.2 contributor tier is a reasoning model from Meta…

Experimental vision variant of V4 Flash with 1M context, releas…

Hy-MT2-30B-A3B is Tencent's flagship translation model in the H…

Hy-MT2-1.8B is a compact 1.8B-parameter translation model from…

Ox Alpha is a reasoning model designed for coding, sustained ag…

Hy-MT2-7B is a 7B-parameter translation model from Tencent. It…

This model always redirects to the latest GLM model from Z.ai.

Open-weights 27B dense vision-language model of the Qwen3.8 lin…

Z.ai 1M-context flagship, post-trained on the GLM-5.2 base for…

Gemini 3.7 Flash Video Understanding EAP

Dots3-Note Preview is an open-weight mixture-of-experts model f…

This model always redirects to the latest model in the Google G…

Gemini 3.7 Flash

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

Open-weights release of the Qwen3.8 flagship: 2.4T sparse MoE,…

xAI's frontier model for coding, agentic tasks, and knowledge w…

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model…

Seed 2.0 Code is a model from ByteDance Seed optimized for agen…

Seed 2.1 Turbo is a multimodal model from ByteDance Seed for co…

Sakana Namazu is a Japanese-specialized reasoning model from Sa…

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts mod…

Fastest Nemotron MoE (30B, 3B active), 1M context, reasoning an…

LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is…

Solar Pro 4 is Upstage's cost-efficient large language model, f…

Muse Glimmer 30B is a dense, open-weight multimodal model from…

Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, w…

Muse Spark 1.2 is a reasoning model from Meta, designed for com…

Japanese-specialized LLM built on Moonshot AI's Kimi K2.6 and a…

Japanese-specialized LLM with built-in web search and code exec…

This model always redirects to the latest model in the DeepSeek…

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model fro…

Inkling Small is an open-weight multimodal mixture-of-experts m…

Gemini Robotics-ER 2 Preview

Translation-specialized model (37 languages, few-shot prompting…

Fast-mode variant of Opus 5 - identical capabilities with highe…

Step-change improvement over Opus 4.8 for complex agentic codin…

This model always redirects to the latest model in the Claude O…

*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE)…

Multi-agent conductor system routing 1-3 expert agents for comp…

Orchestrator specialized for cybersecurity reasoning: security…

Laguna S 2.1 is the latest coding agent model from Poolside. La…

Gemini 3.6 Flash

Gemini 3.5 Flash Lite

LongCat 2.0 is a sparse mixture-of-experts language model from…

NVIDIA quantum-calibration VLM, preview (domain-specific, not f…

Flagship 2.4T-parameter sparse MoE multimodal model with 1M con…

Inkling is an open-weight multimodal mixture-of-experts model f…

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

This model always redirects to the latest model in the Moonshot…

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

Native multimodal flagship (text, image, video inputs) with thi…

Latest fast multimodal model with 1M context, thinking (on by d…

Prism Ml chat model. https://huggingface.co/api/models/prism-ml…

KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model tha…

KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model tha…

GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra…

GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, se…

GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna,…

This model always redirects to the latest model in the OpenAI G…

Balanced model for efficient, high-volume everyday work. Compet…

Flagship next-generation model. Strongest yet for agentic codin…

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

xAI's July 2026 flagship with frontier performance on coding, k…

Aion-3.0 Mini is a multi-model roleplaying and storytelling sys…

Aion-3.0 is a multi-model roleplaying and storytelling system f…

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (…

Laguna XS 2.1 is the latest coding agent model in the 33B-A3B c…

Gemini 3.1 Flash Lite Image.

A mid & post-trained version of mistral small 4 for Lean (26061…

A mid & post-trained version of mistral small 4 for Lean (26061…

Gemini Omni Flash Preview

Best combination of speed and intelligence, with the largest ga…

This model always redirects to the latest model in the Anthropi…

Qwen chat model.

Qwen chat model.

Nex-N2-Mini is an open-source agentic mixture-of-experts model…

Fast orchestration model routing tasks across a swappable pool…

North Mini Code is Cohere's first agentic coding model and the…

Official Z.ai GLM 5.2 model

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

Multi-agent conductor system routing 1-3 expert agents for comp…

Multi-agent conductor system routing 1-3 expert agents for comp…

Fusion turns your prompt into a small multi-model deliberation.…

High-speed code variant with ~180 tok/s output (up to 260 in sh…

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

Experimental diffusion language model. CAUTION: prone to hangin…

Compact agentic coding MoE (30B total, 3B active, Apache 2.0) f…

Most capable widely released model for the most demanding reaso…

This model always redirects to the latest model in the Claude F…

Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI,…

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

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orche…

Meta chat model. https://huggingface.co/api/models/RedHatAI/Lla…

Zai Org chat model.

Multimodal agent model with 1M context, native thinking, and vi…

MiniMax-M3 is a multimodal foundation model from MiniMax. It su…

Step 3.7 Flash is StepFun's latest high-efficiency multimodal M…

Gemini 3 Pro Image

Gemini 3.1 Flash Image.

Previous most capable Opus-tier model for complex reasoning and…

Fast-mode variant of Opus 4.8 - identical capabilities with hig…

Flagship agent model with native extended thinking and 1M conte…

xAI fast coding model with reasoning, function calling, and str…

Cohere flagship MoE (218B total, 25B active, Apache 2.0). Agent…

Meta chat model.

Gemini 3.5 Flash

Preview release of Antigravity Agent (05-2026)

Google chat model. https://huggingface.co/api/models/google/gem…

Google chat model.

Perceptron Mk1 (Mark One) is Perceptron's highest-quality visio…

Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B act…

Mistral AI chat model.

Google chat model.

Gemini 3.1 Flash Lite

Meta chat model.

GPT Chat Latest

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter lan…

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

Laguna M.1 is the flagship coding agent model from Poolside, op…

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

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

Nvidia chat model.

Official mistral-medium-latest Mistral AI model

Official mistral-medium-latest Mistral AI model

Official mistral-medium-latest Mistral AI model

Official mistral-medium-latest Mistral AI model

Official mistral-medium-latest Mistral AI model

Mistral frontier-class multimodal model with adjustable reasoni…

Official mistral-medium-latest Mistral AI model

Official mistral-medium-latest Mistral AI model

Qwen3.6 Max preview (never GA; superseded by Qwen3.7 Max). 256K…

Fast, cost-effective multimodal model with 1M context, near-fla…

Open 35B-A3B MoE multimodal with thinking. 256K context.

Open 27B dense multimodal with thinking. 256K context.

Premium reasoning model with 1M context, released GA by DeepSee…

Fast general-purpose model with 1M context, re-post-trained by…

Ling-2.6-1T is an instant (instruct) model from inclusionAI and…

Most capable model for complex tasks. Uses more compute for sma…

New baseline for complex production workflows. Stronger task ex…

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

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pr…

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

Qwen chat model. https://huggingface.co/api/models/Qwen/Qwen3.6…

The Pareto Router maintains a tiered shortlist of strong coding…

GPT-5.4 Image 2 combines OpenAI's GPT-5.4 model with state-of-t…

Ling-2.6-flash is an instant (instruct) model from inclusionAI…

Google chat model. https://huggingface.co/api/models/google/gem…

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

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

Native multimodal flagship (text, image, video inputs) with thi…

xAI's latest flagship model with reasoning and a 1M token conte…

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

Previous most capable model for complex reasoning and agentic c…

Fast-mode variant of Opus 4.7 - identical capabilities with hig…

Gemini 3.1 Flash TTS Preview

NVIDIA quantum-calibration VLM (domain-specific, not for genera…

Gemini Robotics-ER 1.6 Preview

Nvidia chat model. https://huggingface.co/api/models/nvidia/NVI…

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

Previous Plus tier, superseded by Qwen3.7 Plus. 1M context, thi…

Gemma 4 31B IT

Gemma 4 26B A4B IT

First multimodal GLM-5 model. Vision-based coding agent with im…

Trinity Large Thinking is a powerful open source reasoning mode…

Grok 4.20 is a reasoning model from SpaceXAI with industry-lead…

Hcompany chat model. https://huggingface.co/api/models/Hcompany…

Full-length songs are priced at $0.08 per song. Lyria 3 is Goog…

30 second duration clips are priced at $0.04 per clip. Lyria 3…

KAT-Coder-Pro V2 is the latest high-performance model in KwaiKA…

Qwen chat model.

Deepseek model via OpenAI-Compatible API on AWS Bedrock Mantle

Reka Edge is an extremely efficient 7B multimodal vision-langua…

Qwen chat model.

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

This model always redirects to the latest model in the OpenAI G…

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

Strongest mini model for coding, computer use, and subagents. G…

Qwen chat model. https://huggingface.co/api/models/Qwen/Qwen3.5…

Mistral Small 4.

Mistral Small 4.

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 too…

Deepseek chat model. https://huggingface.co/api/models/deepseek…

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE mod…

Nvidia chat model. https://huggingface.co/api/models/nvidia/NVI…

Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 fa…

Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhor…

Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 desi…

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

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

xAI flagship model with a 1M token context window. Non-reasonin…

Qwen chat model. https://huggingface.co/api/models/togethercomp…

Most capable model for complex tasks. Uses more compute for sma…

Most capable and efficient frontier model for professional work…

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

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

GPT-5.3 Instant model, previously powering ChatGPT.

Zai Org chat model. https://huggingface.co/api/models/zai-org/G…

Gemini 3.1 Flash Lite Preview

Gemini 3.1 Flash Image Preview.

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

Open 35B-A3B MoE multimodal with thinking. 256K context.

Open 27B dense multimodal with thinking. 256K context.

Open 122B-A10B MoE multimodal with thinking. 256K context.

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

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

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

Former Flash tier, superseded by Qwen3.6/3.7 Flash. 1M context,…

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

This model always redirects to the latest model in the Google G…

Gemini 3.1 Pro Preview optimized for custom tool usage

Gemini 3.1 Pro Preview

Tiny Aya (3.35B) region-specialized for European and Asia-Pacif…

Tiny multilingual research model (3.35B), best balance across 7…

Tiny Aya (3.35B) region-specialized for South Asian languages.…

Tiny Aya (3.35B) region-specialized for West Asian and African…

Best combination of speed and intelligence for everyday tasks

Open 397B-A17B MoE multimodal with thinking. 256K context.

The Qwen3.5 native vision-language series Plus models are built…

Former Plus tier, superseded by Qwen3.6/3.7 Plus. 1M context, t…

MiniMaxAI chat model.

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

Zai Org chat model. https://huggingface.co/api/models/togetherc…

Z.ai flagship foundation model (744B MoE, 40B activated). Desig…

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3…

Most capable agentic coding model. Combines frontier coding per…

Previous most intelligent model for complex agents and coding,…

Budget agentic coder on the Qwen3-Next architecture. 256K conte…

Specialized OCR model for text extraction from images and docum…

The simplest way to get free inference. openrouter/free is a ro…

Step 3.5 Flash is StepFun's most capable open-source foundation…

Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) lang…

Supports vision (images/videos), thinking mode, and Agent tasks…

MiniMax M2-her is a dialogue-first large language model built f…

Palmyra X5 is Writer's most advanced model, purpose-built for b…

LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model o…

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

Fast GLM-4.7 variant with priority routing and higher concurren…

Free GLM-4.7 variant. Same model as FlashX but with limited con…

Z.ai GLM 4.7 (355B) on Cerebras (~1,000 tok/s). Strong agentic…

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

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

Seed 1.6 is a general-purpose model released by the ByteDance S…

Latest-gen GLM model with 200K context. Thinking mode activated…

Gemini 3 Flash Preview

Nvidia chat model. https://huggingface.co/api/models/nvidia/NVI…

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model wi…

Translation-specialized model, 8K context.

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

GPT-5.2 Instant model, previously powering ChatGPT.

GPT-5.2 optimized for long-horizon, agentic coding tasks in Cod…

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

Mobile phone automation agent. Understands phone screens via mu…

Smartest and most trustworthy option for difficult questions. U…

Most capable model for professional work and long-running agent…

Devstral 2 is a state-of-the-art open-source model by Mistral A…

Official devstral-2512 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…

Fast vision GLM-4.6 with priority routing and higher concurrenc…

Free vision GLM-4.6. Same model as FlashX but with limited conc…

Vision-enabled GLM-4.6 model. Supports image/video/file inputs,…

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

Transform your natural language requests into structured OpenRo…