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

# Generate Embeddings

> Generate vector embeddings for input text(s).

<RequestExample>
  ```bash cURL theme={null}
  curl https://gateway.bud.studio/v1/embeddings \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "text-embedding-3-small",
      "input": "Machine learning is transforming industries",
      "dimensions": 1536,
      "priority": "normal"
    }'
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={null}
  {
    "object": "list",
    "data": [
      {
        "object": "embedding",
        "embedding": [0.0023064255, -0.009327292, ...],
        "index": 0
      }
    ],
    "model": "text-embedding-3-small",
    "usage": {
      "prompt_tokens": 8,
      "total_tokens": 8
    }
  }
  ```
</ResponseExample>

## Headers

| Parameter     | Type   | Required | Description                                                                               |
| ------------- | ------ | -------- | ----------------------------------------------------------------------------------------- |
| Authorization | string | Yes      | Bearer authentication header of the form `Bearer <token>` where `<token>` is your API key |

## Body

| Parameter        | Type            | Required | Description                                                                   |
| ---------------- | --------------- | -------- | ----------------------------------------------------------------------------- |
| model            | string          | Yes      | Embedding model identifier                                                    |
| input            | string or array | Yes      | Text(s) to embed. Can be a single string or array of strings                  |
| encoding\_format | string          | No       | Format of the embedding. Options: `float`, `base64`. Default: `float`         |
| dimensions       | integer         | No       | Matryoshka dimensions for output embeddings. Default: model's full dimensions |
| modality         | string          | No       | Modality type: `text`, `image`, `audio`. Default: `text`                      |
| priority         | string          | No       | Priority level: `high`, `normal`, `low`. Default: `normal`                    |
| include\_input   | boolean         | No       | Include original input text in response. Default: `false`                     |
| chunking         | object          | No       | Chunking configuration for long texts (see Chunking Configuration below)      |

### Chunking Configuration

The `chunking` parameter accepts an object with the following fields:

| Parameter      | Type    | Description                                                                                        |
| -------------- | ------- | -------------------------------------------------------------------------------------------------- |
| enabled        | boolean | Enable text chunking. Default: `false`                                                             |
| strategy       | string  | Chunking strategy: `token`, `sentence`, `recursive`, `semantic`, `code`, `table`. Default: `token` |
| chunk\_size    | integer | Max tokens per chunk (1-8192). Default: `512`                                                      |
| chunk\_overlap | integer | Token overlap between chunks. Default: `0`                                                         |
| tokenizer      | string  | Tokenizer: `cl100k_base`, `p50k_base`, `r50k_base`, `gpt2`. Default: `cl100k_base`                 |
| min\_sentences | integer | \[sentence strategy] Minimum sentences per chunk. Default: `1`                                     |

## Supported Providers

<CardGroup cols={4}>
  <Card title="OpenAI" icon="openai">
    text-embedding-3-small, text-embedding-3-large, ada-002
  </Card>

  <Card title="Azure OpenAI" icon="microsoft">
    Enterprise text embeddings with global availability
  </Card>

  <Card title="Cohere" icon="sparkles">
    embed-english-v3.0, embed-multilingual-v3.0
  </Card>

  <Card title="Voyage AI" icon="ship">
    voyage-2, voyage-code-2 specialized embeddings
  </Card>

  <Card title="Together AI" icon="arrow-progress">
    Nomic Embed and open-source embedding models
  </Card>

  <Card title="Google" icon="google">
    text-embedding-004 and multimodal embeddings
  </Card>
</CardGroup>