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

# CreateEmbeddingsRequestBody

Embeddings request input

## Example Usage

```typescript theme={null}
import { CreateEmbeddingsRequestBody } from "@openrouter/sdk/models/operations";

let value: CreateEmbeddingsRequestBody = {
  input: "The quick brown fox jumps over the lazy dog",
  model: "openai/text-embedding-3-small",
};
```

## Fields

| Field            | Type                                                                    | Required             | Description                                                                                                                                                                                                                                    | Example                                                                        |
| ---------------- | ----------------------------------------------------------------------- | -------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------ |
| `dimensions`     | *number*                                                                | :heavy\_minus\_sign: | The number of dimensions for the output embeddings                                                                                                                                                                                             | 1536                                                                           |
| `encodingFormat` | [operations.EncodingFormat](../../models/operations/encodingformat.mdx) | :heavy\_minus\_sign: | The format of the output embeddings                                                                                                                                                                                                            | float                                                                          |
| `input`          | *operations.InputUnion*                                                 | :heavy\_check\_mark: | Text, token, or multimodal input(s) to embed                                                                                                                                                                                                   | The quick brown fox jumps over the lazy dog                                    |
| `inputType`      | *string*                                                                | :heavy\_minus\_sign: | The type of input (e.g. search\_query, search\_document)                                                                                                                                                                                       | search\_query                                                                  |
| `model`          | *string*                                                                | :heavy\_check\_mark: | The model to use for embeddings                                                                                                                                                                                                                | openai/text-embedding-3-small                                                  |
| `provider`       | [models.ProviderPreferences](../../models/providerpreferences.mdx)      | :heavy\_minus\_sign: | N/A                                                                                                                                                                                                                                            | \{<br />"allow\_fallbacks": true<br />}                                        |
| `trace`          | [models.TraceConfig](../../models/traceconfig.mdx)                      | :heavy\_minus\_sign: | Metadata for observability and tracing. Known keys (trace\_id, trace\_name, span\_name, generation\_name, parent\_span\_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations. | \{<br />"trace\_id": "trace-abc123",<br />"trace\_name": "my-app-trace"<br />} |
| `user`           | *string*                                                                | :heavy\_minus\_sign: | A unique identifier for the end-user                                                                                                                                                                                                           | user-1234                                                                      |