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

# Quickstart

> Integrate the Halesis API into your application in minutes.

## Introduction

Our **RESTful, OpenAI-compatible API** is designed to be simple, efficient, and developer-friendly. This guide will help you quickly understand how to start integrating our services into your applications using standard HTTP conventions.

## API Requests

Our API uses only the two most common HTTP methods:

* **`GET`**: Retrieve data from the server
* **`POST`**: Send data to the server

> [accordion] Headers
>
> All requests should include these headers:
>
> * `Content-Type`: `application/json`
> * `Authorization`: `Bearer {api_key}`

> [accordion] Authentication
>
> Interacting with the API requires a **Bearer token**:
>
> ```http theme={null}
> Authorization: Bearer sk-abc123yourapikey
> ```
>
> You can generate API keys from [here](https://app.halesis.com/api). Tokens are tied to your organization.

> [accordion] Formatting Requests
>
> ```json theme={null}
> {
>   "model": "b1-fast",
>   "messages": [
>     {
>       "role": "user",
>       "content": "Hello world"
>     }
>   ],
>   "stream": false,
>   "temperature": 0.7
> }
> ```
>
> All responses are **JSON**. Sample response:
>
> ```json theme={null}
> {
>   "id": "0e382a68-7444-477c-9bff-20f87081499f",
>   "object": "chat.completion",
>   "created": 1792599573,
>   "model": "b1-fast",
>   "choices": [
>     {
>       "index": 0,
>       "message": {
>         "role": "assistant",
>         "content": "Hello. I'm B1 Fast, Halesis's AI assistant. How can I help you today?"
>       },
>       "finish_reason": "stop"
>     }
>   ],
>   "usage": {
>     "prompt_tokens": 1,
>     "completion_tokens": 22,
>     "total_tokens": 23
>   }
> }
> ```
>
> All responses also include meaningful HTTP status codes (`200`, `400`, `403`, `429`).

> [accordion] Rate Limiting
>
> We enforce limits per organization and API key. Exceeding the limit returns a **`429 Too Many Requests`** response. Rate limits reset automatically after a short cooldown.

> [card] [Playground](https://app.halesis.com/playground)
>
> Experiment with API calls directly in your browser.

> [card] [SDK Integrations](https://docs.halesis.com/integrations.md)
>
> Connect Halesis to the AI SDKs and tooling you already use.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.