# API Reference (/docs/reference)



Explore and test all gateway endpoints. Each operation page includes an interactive playground for live requests.

Use `https://api.stogas.ai` as the base URL. Endpoint paths include their API version.

## Endpoints [#endpoints]

<Cards>
  <Card title="Catalog" description="Inspect public model aliases, routes, providers, and prices." href="/docs/reference/catalog/getCatalog" />

  <Card title="Models" description="List OpenAI-compatible model IDs accepted by the gateway." href="/docs/reference/catalog/listModels" />

  <Card title="Chat Completions" description="Create an OpenAI-compatible chat completion" href="/docs/reference/openai-compatible/createChatCompletion" />

  <Card title="Responses" description="Create an OpenAI-compatible response" href="/docs/reference/openai-compatible/createResponse" />
</Cards>

## Guides [#guides]

<Cards>
  <Card title="Provider Behavior" description="Provider differences and compatibility notes." href="/docs/reference/provider-behavior" />

  <Card title="Security" description="Authentication, request limits, CORS, and header policies." href="/docs/reference/security" />
</Cards>

## Authentication [#authentication]

Inference endpoints require a gateway API key:

```http
Authorization: Bearer <api_key>
Content-Type: application/json
```

`/v1/catalog` and `/v1/models` are public. Get your key from the [dashboard](https://app.stogas.ai).