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

# Embeddings

> Create vector embeddings with OpenAI-compatible embedding models.

## Endpoint

```bash theme={"system"}
POST https://inference.phala.com/v1/embeddings
```

Generate vector embeddings for retrieval, semantic search, clustering, and similarity workloads.

## Request Body

<ParamField body="model" type="string" required>
  Embedding model ID.

  Examples: `qwen/qwen3-embedding-8b`, `sentence-transformers/all-minilm-l6-v2`.
</ParamField>

<ParamField body="input" type="string | array" required>
  Input text or list of inputs to embed.
</ParamField>

<ParamField body="encoding_format" type="string">
  Embedding encoding format. Common values are `float` and `base64`.
</ParamField>

<ParamField body="dimensions" type="integer">
  Requested output dimensions, when supported by the selected model.
</ParamField>

<ParamField body="provider" type="object">
  Routing constraints for this request. Embedding requests accept the same `provider` routing block as chat completions, including `zdr`, `aci_verified`, and `aci_session_ids`.

  Set `provider: {"zdr": true}` to route only to serving routes that operate under zero data retention. If no route for the selected embedding model satisfies the constraint, the request fails before input text is sent. See [Zero Data Retention](/phala-cloud/confidential-ai/confidential-model/zero-data-retention) and [Attested Routing](/phala-cloud/confidential-ai/confidential-model/attested-routing).
</ParamField>

## Examples

<CodeGroup>
  ```bash cURL theme={"system"}
  curl https://inference.phala.com/v1/embeddings \
    -H "Authorization: Bearer <API_KEY>" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "qwen/qwen3-embedding-8b",
      "input": "Confidential AI keeps inference data private."
    }'
  ```

  ```python Python theme={"system"}
  from openai import OpenAI

  client = OpenAI(
      api_key="<API_KEY>",
      base_url="https://inference.phala.com/v1",
  )

  response = client.embeddings.create(
      model="qwen/qwen3-embedding-8b",
      input="Confidential AI keeps inference data private.",
  )

  vector = response.data[0].embedding
  print(len(vector))
  ```

  ```typescript TypeScript theme={"system"}
  import OpenAI from "openai";

  const client = new OpenAI({
    apiKey: "<API_KEY>",
    baseURL: "https://inference.phala.com/v1",
  });

  const response = await client.embeddings.create({
    model: "qwen/qwen3-embedding-8b",
    input: "Confidential AI keeps inference data private.",
  });

  console.log(response.data[0].embedding.length);
  ```
</CodeGroup>

## Response

```json theme={"system"}
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023, -0.0015, 0.0042]
    }
  ],
  "model": "qwen/qwen3-embedding-8b",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}
```

## Common Models

| Model                                    | Dimensions | Context | Notes                              |
| ---------------------------------------- | ---------- | ------- | ---------------------------------- |
| `qwen/qwen3-embedding-8b`                | 4096       | 32K     | Large confidential embedding model |
| `sentence-transformers/all-minilm-l6-v2` | 384        | 512     | Low-cost compact embedding model   |

Use [List Embedding Models](/phala-cloud/confidential-ai/confidential-model/api-reference/embedding-models) for the live embedding catalog.