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

# Reflection API overview

> Call Reflection models over HTTPS with the Reflection API

The Reflection API serves Reflection models over HTTPS.

| Endpoint | Base URL |
| - | - |
| Reflection client | `https://api.reflection.ai/v1` |
| OpenAI-compatible | `https://api.reflection.ai/openai/v1` |

The OpenAI-compatible endpoint implements Chat Completions and Models, so code that uses them through the official OpenAI SDKs works after you change the base URL and API key. See [OpenAI compatibility](/openai-compatibility) for what is supported.

<Tip>
  To work with Reflection models from your terminal instead of writing code, try [Mirror](/mirror-overview), Reflection's coding agent. Other coding agents can use the API too: see the [Mirror CLI quickstart](/coding-agents-quickstart), which also covers them.
</Tip>

## Start here

<CardGroup cols={3}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Make your first request in a few minutes.
  </Card>

  <Card title="Authentication" icon="key" href="/authentication">
    Create an API key and send it with your requests.
  </Card>

  <Card title="Models" icon="cube" href="/models">
    See which models you can use.
  </Card>
</CardGroup>

## Guides

<CardGroup cols={2}>
  <Card title="Text generation" icon="message" href="/text-generation">
    Send a conversation and get a response.
  </Card>

  <Card title="Streaming" icon="bars-staggered" href="/streaming">
    Receive a response as it is generated.
  </Card>

  <Card title="Reasoning" icon="brain" href="/reasoning">
    Control how much the model thinks before it answers.
  </Card>

  <Card title="Tool calling" icon="wrench" href="/tool-calling">
    Let the model call functions in your code.
  </Card>

  <Card title="Structured outputs" icon="brackets-curly" href="/structured-outputs">
    Get JSON that matches a schema.
  </Card>
</CardGroup>

## Resources

<CardGroup cols={2}>
  <Card title="OpenAI compatibility" icon="plug" href="/openai-compatibility">
    Use the OpenAI SDKs, and see what differs.
  </Card>

  <Card title="Errors" icon="triangle-exclamation" href="/errors">
    Error codes, and when to retry.
  </Card>

  <Card title="Rate limits" icon="gauge" href="/rate-limits">
    How limits apply and how to handle them.
  </Card>

  <Card title="API reference" icon="book" href="/api-reference/overview">
    Every endpoint, parameter, and response field.
  </Card>
</CardGroup>