Embeddings

Create Embeddings

post

Creates vector embeddings for text input. Supports models from OpenAI, Google, and DeepInfra. Compatible with OpenAI SDK.

Authorizations

bearerAuth

AuthorizationstringRequired

FastRouter API Key. Get yours at https://fastrouter.ai

Format: Authorization: Bearer YOUR_API_KEY

Body

application/json

modelstring · enumRequired

The fully qualified model slug. Choose from supported models (openai/text-embedding-3-small, openai/text-embedding-3-large, openai/text-embedding-ada-002, google/gemini-embedding-001, deepinfra/intfloat-e5-base-v2)

Example: openai/text-embedding-3-largePossible values:

inputone ofRequired

The input text or list of text items to embed. Can be a single string or array of strings for batch processing.

stringOptional

Single text string to embed

or

string[]Optional

Array of text strings to embed (batch processing)

dimensionsinteger · min: 1Optional

Optional: Requested embedding size/dimensions. Supported only in text-embedding-3 series and newer models. Allows you to reduce embedding size for efficiency.

Example: 256

encoding_formatstring · enumOptional

Format for the embedding vector. 'float' returns array of numbers, 'base64' returns base64-encoded string.

Default: floatPossible values:

userstringOptional

Optional: A unique identifier representing your end-user, for monitoring and abuse detection.

Responses

200

Embeddings created successfully

application/json

400

Bad Request - Invalid parameters or model

401

Invalid Credentials - Your API key is invalid, disabled, or your OAuth session has expired. Check your credentials.

application/json

429

Rate Limited - You have exceeded your request limits (TPM/RPM). Slow down or increase your limits.

application/json

500

Internal Server Error

post

/embeddings

HTTPcURLJavaScriptPython

POST /api/v1/embeddings HTTP/1.1
Host: api.fastrouter.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 78

{
  "model": "openai/text-embedding-3-large",
  "input": "Your text string goes here"
}

Single Text (OpenAI)With Custom DimensionsBatch Processing (Multiple Texts)Google Gemini EmbeddingsDeepInfra E5 ModelCost-Effective (Ada-002)

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        0.0023,
        0.0492,
        -0.0123,
        -0.0187
      ]
    }
  ],
  "model": "openai/text-embedding-3-large",
  "usage": {
    "prompt_tokens": 5,
    "total_tokens": 5
  }
}