Example Usage
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 | :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 | :heavy_minus_sign: | N/A | { “allow_fallbacks”: true } |
trace | models.TraceConfig | :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. | { “trace_id”: “trace-abc123”, “trace_name”: “my-app-trace” } |
user | string | :heavy_minus_sign: | A unique identifier for the end-user | user-1234 |