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

# API Overview

> OpenAI-compatible API gateway for unified AI provider access

## Introduction

switchAILocal provides an OpenAI-compatible HTTP API that works with any OpenAI SDK or tool. Point your client to `http://localhost:18080/v1` and use your existing code without modifications.

## Base URL

```
http://localhost:18080/v1
```

All API endpoints use this base URL. The server runs locally on your machine by default.

## Key Features

<CardGroup cols={2}>
  <Card title="OpenAI Compatible" icon="code">
    Works with OpenAI SDKs in Python, Node.js, and more without code changes
  </Card>

  <Card title="Multi-Provider" icon="layer-group">
    Access Gemini, Claude, Ollama, and other providers through a single endpoint
  </Card>

  <Card title="Auto-Routing" icon="route">
    Omit provider prefixes to let switchAILocal choose the best available provider
  </Card>

  <Card title="Local-First" icon="shield">
    Everything runs on your machine - your data never leaves
  </Card>
</CardGroup>

## Quick Example

<CodeGroup>
  ```bash cURL theme={null}
  curl http://localhost:18080/v1/chat/completions \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer sk-test-123" \
    -d '{
      "model": "gemini-2.5-pro",
      "messages": [{"role": "user", "content": "Hello!"}]
    }'
  ```

  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(
      base_url="http://localhost:18080/v1",
      api_key="sk-test-123"
  )

  response = client.chat.completions.create(
      model="gemini-2.5-pro",
      messages=[{"role": "user", "content": "Hello!"}]
  )
  print(response.choices[0].message.content)
  ```

  ```javascript Node.js theme={null}
  import OpenAI from 'openai';

  const client = new OpenAI({
    baseURL: 'http://localhost:18080/v1',
    apiKey: 'sk-test-123'
  });

  const response = await client.chat.completions.create({
    model: 'gemini-2.5-pro',
    messages: [{ role: 'user', content: 'Hello!' }]
  });

  console.log(response.choices[0].message.content);
  ```
</CodeGroup>

## Available Endpoints

| Endpoint               | Method    | Description                                |
| ---------------------- | --------- | ------------------------------------------ |
| `/v1/chat/completions` | POST      | Send chat messages and receive completions |
| `/v1/completions`      | POST      | Legacy completions endpoint                |
| `/v1/models`           | GET       | List all available models                  |
| `/v1/providers`        | GET       | List provider status and capabilities      |
| `/v1/embeddings`       | POST      | Generate text embeddings                   |
| `/v1/ws`               | WebSocket | Real-time bidirectional streaming          |
| `/v1/messages`         | POST      | Claude-compatible messages endpoint        |

## Provider Support

switchAILocal supports multiple AI providers through a unified interface:

### CLI Providers (Use Your Subscriptions)

* **Gemini CLI** (`geminicli:`) - Google Gemini via local CLI
* **Claude CLI** (`claudecli:`) - Anthropic Claude via local CLI
* **Codex** (`codex:`) - OpenAI Codex
* **Vibe** (`vibe:`) - Mistral Vibe CLI
* **OpenCode** (`opencode:`) - OpenCode CLI

### Local Models

* **Ollama** (`ollama:`) - Local open-source models
* **LM Studio** (`lmstudio:`) - Local model hosting

### Cloud APIs

* **switchAI** (`switchai:`) - Traylinx unified gateway
* **Gemini API** (`gemini:`) - Google AI Studio
* **Claude API** (`claude:`) - Anthropic API
* **OpenAI API** (`openai:`) - OpenAI platform
* **OpenAI Compatible** (`openai-compat:`) - OpenRouter, etc.

## Error Handling

All errors follow the OpenAI error format:

```json theme={null}
{
  "error": {
    "message": "Invalid API key provided",
    "type": "authentication_error",
    "code": "invalid_api_key"
  }
}
```

### Common Error Types

| Type                    | HTTP Code | Description                       |
| ----------------------- | --------- | --------------------------------- |
| `authentication_error`  | 401       | Invalid or missing API key        |
| `invalid_request_error` | 400       | Malformed request body            |
| `permission_error`      | 403       | Insufficient quota or permissions |
| `rate_limit_error`      | 429       | Too many requests                 |
| `server_error`          | 500       | Internal server error             |

## Next Steps

<CardGroup cols={2}>
  <Card title="Authentication" icon="key" href="/api/authentication">
    Learn how to authenticate API requests
  </Card>

  <Card title="Chat Completions" icon="messages" href="/api/chat-completions">
    Send messages and receive AI responses
  </Card>

  <Card title="Provider Prefixes" icon="tag" href="/api/provider-prefixes">
    Route requests to specific providers
  </Card>

  <Card title="Management API" icon="gear" href="/api/management/overview">
    Configure and monitor your server
  </Card>
</CardGroup>