# InferenceIndex

> The Compiled Agent Model turns your agent’s repeated work into a custom model.

InferenceIndex learns from the first agent runs and compiles what repeats into a Compiled Agent Model: a reusable way to carry out the same kind of work on new inputs. Repeat runs are faster and cheaper, with checks and a path back to the full agent. Request access at https://inferenceindex.com/#waitlist by signing up with Google. Once you have access, call it from an OpenAI-compatible client and swap your base URL and model name.

## Docs

- [What it does and when to use it](https://inferenceindex.com/docs/index.md): Same job, new inputs, after a full agent has done that job once.
- [Install and quickstart](https://inferenceindex.com/docs/quickstart.md): Request access with Google. Once you have access, swap your base URL and model name.

## Optional

- [Home](https://inferenceindex.com/): Product page and waitlist.
- [Why Compiled Agent Models](https://inferenceindex.com/blog/compiled-agent-models): Long-form explanation of the idea.
- [Full docs for agents](https://inferenceindex.com/llms-full.txt): The docs pages in one file.