Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...
No provider description is available for this model yet.
Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...
No provider description is available for this model yet.
No provider description is available for this model yet.
Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...
No provider description is available for this model yet.
No provider description is available for this model yet.
Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.
DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...
No provider description is available for this model yet.
LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference and broad runtime support.
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...
Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and...
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is...
No provider description is available for this model yet.
No provider description is available for this model yet.
Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...
GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...
No provider description is available for this model yet.
Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning...
No provider description is available for this model yet.
No provider description is available for this model yet.
Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...
No provider description is available for this model yet.
No provider description is available for this model yet.
GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...
No provider description is available for this model yet.
MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...
Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.
The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...
Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...
GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...
MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...
No provider description is available for this model yet.
No provider description is available for this model yet.
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...
Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...
GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Qwen: Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507 | Alibaba Qwen |
262.144K | $0.09 | $0.3 | — | ||
| eu-west-3/mistral.mistral-7b-instruct-v0:2bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2 | 32K | $0.2 | $0.26 | — | |||
| Qwen: Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instruct | Alibaba Qwen |
262.144K | $0.15 | $0.6 | — | ||
| eu-west-2/qwen.qwen3-coder-nextbedrock/eu-west-2/qwen.qwen3-coder-next | 262.144K | $0.78 | $1.86 | — | |||
| eu-west-2/minimax.minimax-m2.5bedrock/eu-west-2/minimax.minimax-m2.5 | 1M | $0.47 | $1.86 | — | |||
| Perplexity: Sonar Pro Searchperplexity/sonar-pro-search | Perplexity |
200K | $3 | $15 | — | ||
| eu-west-2/minimax.minimax-m2.1bedrock/eu-west-2/minimax.minimax-m2.1 | 196K | $0.47 | $1.86 | — | |||
| eu-west-1/qwen.qwen3-coder-nextbedrock/eu-west-1/qwen.qwen3-coder-next | 262.144K | $0.6 | $1.44 | — | |||
| Amazon: Nova Premier 1.0amazon/nova-premier-v1 | Amazon |
1M | $2.5 | $12.5 | — | ||
| DeepSeek: DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus | DeepSeek |
131.072K | $0.27 | $1 | — | ||
| qwen/qwen3-14bopenrouter/qwen/qwen3-14b | Openrouter |
131.072K | $0.12 | $0.24 | — | ||
| LiquidAI: LFM2.5-1.2B-Instruct (free)liquid/lfm-2.5-1.2b-instruct:free | 32.768K | Free | Free | — | |||
| Inception: Mercury 2.5inception/mercury-2.5 | Inception |
260K | $0.04 | $0.15 | — | ||
| AllenAI: Olmo 3 32B Thinkallenai/olmo-3-32b-think | 65.536K | $0.15 | $0.5 | — | |||
| Mistral: Ministral 3 3B 2512mistralai/ministral-3b-2512 | Mistral AI |
131.072K | $0.1 | $0.1 | — | ||
| LiquidAI: LFM2.5-1.2B-Thinking (free)liquid/lfm-2.5-1.2b-thinking:free | 32.768K | Free | Free | — | |||
| eu-west-1/minimax.minimax-m2.5bedrock/eu-west-1/minimax.minimax-m2.5 | 1M | $0.36 | $1.44 | — | |||
| eu-west-1/minimax.minimax-m2.1bedrock/eu-west-1/minimax.minimax-m2.1 | 196K | $0.36 | $1.44 | — | |||
| Body Builder (beta)openrouter/bodybuilder | Openrouter |
128K | — | — | — | ||
| Z.ai: GLM 4.6Vz-ai/glm-4.6v | Z Ai |
131.072K | $0.3 | $0.9 | — | ||
| qwen/qwen3-next-80b-a3b-thinkingopenrouter/qwen/qwen3-next-80b-a3b-thinking | Openrouter |
262.144K | $0.15 | $1.2 | — | ||
| qwen/qwen3-vl-8b-thinkingopenrouter/qwen/qwen3-vl-8b-thinking | Openrouter |
131.072K | $0.18 | $2.1 | — | ||
| eu-central-1/qwen.qwen3-coder-nextbedrock/eu-central-1/qwen.qwen3-coder-next | 262.144K | $0.6 | $1.44 | — | |||
| eu-central-1/minimax.minimax-m2.5bedrock/eu-central-1/minimax.minimax-m2.5 | 1M | $0.36 | $1.44 | — | |||
| Relace: Relace Searchrelace/relace-search | 256K | $1 | $3 | — | |||
| eu-central-1/minimax.minimax-m2.1bedrock/eu-central-1/minimax.minimax-m2.1 | 196K | $0.36 | $1.44 | — | |||
| Deep Cogito: Cogito v2.1 671Bdeepcogito/cogito-v2.1-671b | 128K | $1.25 | $1.25 | — | |||
| @cf/zai-org/glm-5.2cloudflare/@cf/zai-org/glm-5.2 | Cloudflare |
262.144K | $1.4 | $4.4 | — | ||
| eu-central-1/anthropic.claude-v2:1bedrock/eu-central-1/anthropic.claude-v2:1 | 100K | $8 | $24 | — | |||
| Amazon: Nova 2 Liteamazon/nova-2-lite-v1 | Amazon |
1M | $0.3 | $2.5 | — | ||
| eu-central-1/anthropic.claude-v1bedrock/eu-central-1/anthropic.claude-v1 | 100K | $8 | $24 | — | |||
| eu-central-1/anthropic.claude-instant-v1bedrock/eu-central-1/anthropic.claude-instant-v1 | 100K | $2.48 | $8.38 | — | |||
| OpenAI: GPT-5.2 Chatopenai/gpt-5.2-chat | OpenAI |
128K | $1.75 | $14 | — | ||
| Mistral: Ministral 3 8B 2512 (batch)mistralai/ministral-8b-2512:batch | Mistral AI |
262.144K | $0.075 | $0.075 | — | ||
| qwen/qwen3-8bopenrouter/qwen/qwen3-8b | Openrouter |
131.072K | $0.117 | $0.455 | — | ||
| eu-central-1/6-month-commitment/anthropic.claude-v2:1bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1 | 100K | — | — | — | |||
| eu-central-1/6-month-commitment/anthropic.claude-v1bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1 | 100K | — | — | — | |||
| Z.ai: GLM 4.7z-ai/glm-4.7 | Z Ai |
202.752K | $0.4 | $1.75 | — | ||
| eu-central-1/6-month-commitment/anthropic.claude-instant-v1bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1 | 100K | — | — | — | |||
| MiniMax: MiniMax M2.1minimax/minimax-m2.1 | MiniMax |
204.8K | $0.3 | $1.2 | — | ||
| Qwen: Qwen-Plusqwen/qwen-plus | Alibaba Qwen |
1M | $0.26 | $0.78 | — | ||
| OpenAI: GPT Audioopenai/gpt-audio | OpenAI |
128K | $2.5 | $10 | — | ||
| AionLabs: Aion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b | 32.768K | $0.8 | $1.6 | — | |||
| Z.ai: GLM 4.5 Airz-ai/glm-4.5-air | Z Ai |
131.072K | $0.13 | $0.85 | — | ||
| MiniMax: MiniMax M2-herminimax/minimax-m2-her | MiniMax |
65.536K | $0.3 | $1.2 | — | ||
| qwen/qwen3-30b-a3bopenrouter/qwen/qwen3-30b-a3b | Openrouter |
131.072K | $0.12 | $0.5 | — | ||
| qwen/qwen3-coder-flashopenrouter/qwen/qwen3-coder-flash | Openrouter |
1M | $0.195 | $0.975 | — | ||
| Nous: Hermes 4 405Bnousresearch/hermes-4-405b | 131.072K | $1 | $3 | — | |||
| Upstage: Solar Pro 3upstage/solar-pro-3 | Upstage |
131.072K | $0.15 | $0.6 | — | ||
| OpenAI: GPT-5 Pro (batch)openai/gpt-5-pro:batch | OpenAI |
400K | $7.5 | $60 | — |