Skip to main content
Every agent runs on a large language model. When you create an agent, you choose where the model calls go:

​
How Atako inference works

Atako inference is powered by OpenRouter, which gives access to hundreds of models from many providers (Anthropic, OpenAI, Google, Mistral, and others). When your agent calls a model, the request goes through OpenRouter to a provider that serves that model. A model can be served by several providers, and OpenRouter picks one for each request.

​
Each provider has its own terms

The provider serving a model sets the terms of use, not Atako. Terms differ from one provider to another, including on data retention and on whether the data you send may be used to train models. The prompts, files, and tool results your agent sends to the model reach that provider. Atako is not responsible for how a provider uses that data.
Review the terms of the providers behind the models you pick before sending them sensitive or confidential data. OpenRouter lists every provider with a link to its terms and privacy policy: openrouter.ai/providers.
The provider information published by OpenRouter may be incomplete or out of date. Checking the terms that apply to your use is your responsibility.

​
Need contractual guarantees?

Run your agents on your own provider key. Your existing contract with the provider then governs how your data is handled.