Create Embedding

Create vector embeddings for text input using embedding models.

POST /v1/embeddings

cURL

curl https://router.requesty.ai/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_REQUESTY_API_KEY" \
  -d '{
    "model": "openai/text-embedding-3-small",
    "input": "Requesty is a unified LLM gateway."
  }'

Response 200

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023, -0.0091, 0.0153, -0.0028, 0.0074]
    }
  ],
  "model": "openai/text-embedding-3-small",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}

cURL

curl https://router.requesty.ai/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_REQUESTY_API_KEY" \
  -d '{
    "model": "openai/text-embedding-3-small",
    "input": "Requesty is a unified LLM gateway."
  }'

Response 200

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023, -0.0091, 0.0153, -0.0028, 0.0074]
    }
  ],
  "model": "openai/text-embedding-3-small",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}

Create vector embeddings for text input. Embeddings are useful for semantic search, similarity matching, clustering, and retrieval-augmented generation (RAG).

Supported Models

Browse the full catalog on the Embedding model library.

Model	Dimensions	Best for
openai/text-embedding-3-small	1536	Cost-efficient, general purpose
openai/text-embedding-3-large	3072	Higher accuracy, multilingual
openai/text-embedding-ada-002	1536	Legacy compatibility

Authorizations

Authorization · string · header · required

API key for authentication

Body

application/json

input · string string[] integer<int64>[] integer<int64>[][] · required

Input text to embed, encoded as a string, array of strings, array of tokens, or array of token arrays

model · string · required

The model name to use for embedding generation

Example:

"openai/text-embedding-3-small"

dimensions · integer<int64>

The number of dimensions the resulting output embeddings should have

encoding_format · enum<string> · default: float

The format to return the embeddings in. Can be either float or base64.

Available options: float, base64

user · string

A unique identifier representing your end-user.

Response

200

application/json

Embedding response

data · object[] · required

The list of embeddings generated by the model

Show child attributes

model · string · required

The name of the model used to generate the embedding

object · string · required

The object type, which is always 'list'

usage · object · required

Show child attributes