Atla-1 is an LLM trained to test & evaluate generative AI applications. Our model helps you run fast and accurate evaluations, so you can ship quickly and with confidence. Atla-1 is available via our simple API.

Atla supports evaluations for a wide range of generative AI applications, including chat, RAG, agents, and content generation. You can use our model to evaluate your app, built on any LLM — OpenAI, Anthropic, Mistral, Meta, or your own.

Atla usage diagram

Get started with Atla

Start with the following resources to get our eval model up and running: