Skip to main content
Manifest is an open-source LLM router for agents and AI apps. Connect the providers you already use — subscriptions like ChatGPT or Claude, pay-per-token API keys, local models, and custom endpoints — and route every request through one OpenAI- and Anthropic-compatible URL. You choose which model handles each request. Add fallbacks so a rate limit or a retired model returns a working response instead of an error, cap spending per agent, and see the cost of every call.

​
Key features

All your providers

Connect API keys, subscriptions you already pay for, local models, or any custom endpoint.

Routing

Send each request to your default model, or match a request header to a custom tier.

Fallbacks

Fall back to another model when one fails, so your agent keeps working.

Set limits

Get email alerts or block requests when spending crosses a threshold.

​
Cloud or self-hosted?

Manifest is an open source project that comes in 2 ways: cloud and self-hosted. We recommend the cloud version for newcomers and the self-hosted version for advanced users. The key difference is that the cloud version runs on our servers, making it easy to setup whereas the self-hosted version must be installed in your local machine of infrastructure.