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

# Embeddings

> Generate vector embeddings with catalog-backed pricing.

Embeddings use the OpenAI-style `/v1/embeddings` shape.

| Method | Path                      |
| ------ | ------------------------- |
| `POST` | `/v1/embeddings`          |
| `POST` | `/external/v1/embeddings` |

## Request

```json theme={null}
{
  "model": "text-embedding-3-large",
  "input": [
    "Compose routes paid model calls.",
    "x402 turns payment into an HTTP concern."
  ],
  "dimensions": 1024
}
```

## Response

```json theme={null}
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [0.0123, -0.0456],
      "index": 0
    }
  ],
  "model": "text-embedding-3-large",
  "usage": {
    "prompt_tokens": 12,
    "total_tokens": 12
  }
}
```

## Metering

Embedding calls are metered from input usage. The adapter normalizes provider output into an embeddings array plus usage.

## Related

* [Metering](/inference/metering)
* [Inference API reference](/inference/reference/specification)