Home/Models
15 models from 7 providers, all reachable through the same /v1/chat/completions endpoint. Switch models with one parameter — no new contract, no new SDK.
Flagship
OpenAI's flagship multimodal model for text, vision and audio.
Cost-efficient small model for high-volume tasks.
Flagship
Reasoning model that thinks step by step on hard problems.
Fast, affordable reasoning tuned for coding and STEM.
Flagship
Anthropic's most capable model for complex agentic work.
Flagship
Balanced frontier intelligence and speed for production.
Anthropic's fastest model for near-instant responses.
Flagship
Google's flagship model with a 1M-token context window.
Low-latency multimodal model at a fraction of the cost.
Flagship
Meta's open-weight MoE model with 1M-token context.
The workhorse open-weight model for self-hosted workloads.
Strong open-weight generalist at commodity pricing.
Flagship
Open reasoning model competitive with frontier labs.
European flagship model with strong multilingual performance.
Alibaba's multilingual model with excellent coding ability.
Highest capability, longest context, and the ones our routing layer keeps the most warm capacity behind.
OpenAI
OpenAI's flagship multimodal model for text, vision and audio.
OpenAI
Reasoning model that thinks step by step on hard problems.
Anthropic
Anthropic's most capable model for complex agentic work.
Anthropic
Balanced frontier intelligence and speed for production.
Google's flagship model with a 1M-token context window.
Meta
Meta's open-weight MoE model with 1M-token context.
DeepSeek
Open reasoning model competitive with frontier labs.
Start routing in minutes
Create an account, pick a plan, and point your existing OpenAI client at our base URL. No SDK rewrite, no lock-in.