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

# API Overview

> OpenAI-compatible REST API with transparent prompt compression.

## Base URL

```
https://www.opencompress.ai/api/v1
```

## Authentication

All requests require a Bearer token:

```
Authorization: Bearer sk-occ-your-key-here
```

Get your API key from the [dashboard](https://www.opencompress.ai/dashboard).

## Compatibility

The OpenCompress API is **fully compatible** with the [OpenAI Chat Completions API](https://platform.openai.com/docs/api-reference/chat). Any SDK, library, or tool that works with OpenAI will work with OpenCompress by changing the base URL.

## Available endpoints

| Method | Endpoint               | Description                                 |
| ------ | ---------------------- | ------------------------------------------- |
| `POST` | `/v1/chat/completions` | Create a chat completion (with compression) |

## Request format

```json theme={null}
{
  "model": "gpt-4o-mini",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Your prompt here."}
  ],
  "stream": false
}
```

## Response format

```json theme={null}
{
  "id": "gen-abc123",
  "object": "chat.completion",
  "created": 1772341560,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "Response content here."
      }
    }
  ],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 145,
    "total_tokens": 163
  }
}
```

<Note>
  Token counts in `usage` reflect the **compressed** token counts — what the model actually processed. This is what you're billed for.
</Note>