# FAQ

> Short answers for the early-access API.

The API is in early access, a private preview.

![Four question cards on a dark plate](/docs/figures/faq.svg)

## What is a Compiled Agent Model?

A Compiled Agent Model is a model for agent work. It is much cheaper and faster than frontier models on work you already run. On our tests, repeat runs are often 10-100x cheaper, and the home page shows early repeat runs as 5–10× faster.

## How do I get an API key?

Open the dashboard at https://inferenceindex-app.web.app. Sign in with the same Google account as the InferenceIndex site, enter your invite code, and get an API key there. Each invite code works once.

## What base URL and model do I send?

The base URL is https://api.inferenceindex.com/v1. The model is workflow/auto. The call is OpenAI-compatible chat completions. Python uses base_url. TypeScript uses baseURL.

## Can I use it from Cursor, Claude Code, or Codex?

Cursor takes the OpenAI-compatible base URL in Settings, then Models. Codex takes it in ~/.codex/config.toml. Claude Code's own base URL speaks the Anthropic Messages API, so use the quickstart call from the code you are writing. The coding-agents page is https://inferenceindex.com/docs/coding-agents.

## What do calls cost?

Calls spend credits. The dashboard shows the balance. Published tests are the figures to quote: often 10-100x cheaper on our tests, with one invoice run roughly 450x versus Opus 5.5.

## What is a fallback model?

A fallback model is a model you choose in the dashboard, alongside workflow/auto.

## Where are logs?

Logs are in the dashboard. They list your API calls: when the call ran, the model name, and whether it completed.

## Is the API generally available?

The API is in early access. It is a private preview. Get a key at https://inferenceindex-app.web.app. The home page waitlist is https://inferenceindex.com/#waitlist.

## What about security reviews?

SOC 2 is in progress.