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

# How the Suiri API Works

> Overview of the Suiri inference API and request model.

Suiri provides a stateless inference API accessible over HTTPS.

***

## Supported OpenAI-Compatible Endpoint

In the current Suiri environment, the following OpenAI-compatible endpoint is supported:

POST [https://pulse.suiri.ai/v1/chat/completions](https://pulse.suiri.ai/v1/chat/completions)

This endpoint follows the OpenAI Chat Completions request and response schema.

For full request and response details, refer to the official OpenAI API reference:

[https://platform.openai.com/docs/api-reference/chat](https://platform.openai.com/docs/api-reference/chat)

***

## Authentication

All requests to the Suiri API must be authenticated using an API key.
Include the API key in the request header:

```
Authorization: Bearer YOUR_API_KEY
```

***

## Stateless Request Model

Each inference request to Suiri is processed independently:

* Conversation history must be provided by the client in the `messages` array
* No server-side session state is maintained
* Prompts and responses are not stored after the request completes

***

## Token Usage

Each response includes token usage information:

* `prompt_tokens`
* `completion_tokens`
* `total_tokens`

Token usage is reported for observability and billing purposes.

***

## Example Request (Python)

Below is a minimal Python example demonstrating how to send a chat completion request to the Suiri API.

```python theme={null}
import requests

url = "https://pulse.suiri.ai/v1/chat/completions"

headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer YOUR_API_KEY"
}

data = {
    "model": "<MODEL_ID>",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
}

response = requests.post(url, headers=headers, json=data)
print(response.json())
```