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

# Overview

> Endpoints for chat, embeddings, audio, images, and more

Requesty normalizes the schema across models and providers through a single API. All inference endpoints use the base URL `https://router.requesty.ai/v1`.

<Note>
  **Download the OpenAPI spec** to use with your favorite API client or code generator:
  [Inference API spec](/api-reference/requesty_inference-openapi.json)
</Note>

<CardGroup cols={2}>
  <Card title="Chat" icon="comments" href="/api-reference/endpoint/chat-completions-create">
    Generate text completions and conversations using OpenAI Chat Completions, Anthropic Messages, or the Responses API.
  </Card>

  <Card title="Embedding" icon="vector-square" href="/api-reference/endpoint/embeddings-create">
    Create vector embeddings from text for semantic search, similarity matching, and retrieval-augmented generation.
  </Card>

  <Card title="Text to Speech" icon="volume-high" href="/api-reference/endpoint/audio-speech-create">
    Convert text into natural-sounding spoken audio with supported TTS models.
  </Card>

  <Card title="Speech to Text" icon="microphone" href="/api-reference/endpoint/audio-transcriptions-create">
    Transcribe audio files into text using speech recognition models.
  </Card>

  <Card title="Images" icon="image" href="/api-reference/endpoint/images-generations-create">
    Generate and edit images using DALL-E, Stable Diffusion, and other image models.
  </Card>

  <Card title="Models" icon="list" href="/api-reference/endpoint/models-list">
    List all available models across providers, with pricing and capability metadata.
  </Card>
</CardGroup>

## Web Search

All three inference endpoints support web search. Pass the `web_search` tool and Requesty translates it to the correct provider format (Vertex, Azure, OpenAI, Anthropic, xAI, Perplexity).

| Endpoint                    | Tool definition                                                                     |
| --------------------------- | ----------------------------------------------------------------------------------- |
| `POST /v1/chat/completions` | `"tools": [{ "type": "web_search" }]`                                               |
| `POST /v1/responses`        | `"tools": [{ "type": "web_search" }]`                                               |
| `POST /v1/messages`         | `"tools": [{ "type": "web_search_20250305", "name": "web_search", "max_uses": 5 }]` |

See the [Web Search guide](/features/web-search) for full examples, response formats, and streaming details for each endpoint.