> ## Documentation Index
> Fetch the complete documentation index at: https://docs.freeplay.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Observe, evaluate, and iterate toward great AI applications

The Freeplay REST API enables you to integrate observability and prompt management into your AI applications.

<Card title="OpenAPI Specification" icon="file-code" href="https://app.freeplay.ai/openapi.json">
  Access the raw OpenAPI 3.0 specification for use with code generators, API clients, or LLM tools.
</Card>

<Tip>
  **Using a coding agent?** Point it to [docs.freeplay.ai/llms.txt](https://docs.freeplay.ai/llms.txt) for LLM-optimized documentation.
</Tip>

## Base URL

Your API root is your Freeplay instance URL plus `/api/v2/`:

```
https://app.freeplay.ai/api/v2
```

For private deployments, use your custom domain (e.g., `https://acme.freeplay.ai/api/v2`).

## Authentication

Freeplay authenticates requests using API keys, which you can manage at `https://app.freeplay.ai/settings/api-access`.

Include your API key in the `Authorization` header:

```
Authorization: Bearer {freeplay_api_key}
```

## Error Handling

Freeplay uses standard HTTP status codes:

| Code | Meaning                                     |
| ---- | ------------------------------------------- |
| 200  | Success                                     |
| 400  | Bad request — check your request parameters |
| 401  | Unauthorized — invalid or missing API key   |
| 500  | Server error — safe to retry                |

<Note>
  Errors in the 400-499 range are client errors and won't resolve with retries.
  For 500 errors, retry up to 3 times with at least a 5-second delay between
  attempts.
</Note>