Embeddings

POST /v1/embeddings

Converts input into a high-dimensional vector representation (embedding). Embeddings are used for semantic search, clustering, classification, and retrieval-augmented generation (RAG). The gateway supports text, image, and video embedding inputs depending on the provider. The response always includes a data array with embedding vectors indexed to match the input.

Request headers

string

The provider to route the request to (e.g. openai, cohere, google-vertex-ai). Required when not using a config.

string

Your provider API key.

string

A JSON config object or config ID that defines routing, fallbacks, retries, and more.

string

A virtual key ID from Portkey Cloud.

Request body

string

required

The embedding model to use (e.g. text-embedding-3-small, embed-english-v3.0).

string | string[] | object[]

required

The text or texts to embed. Accepts:

A single string
An array of strings for batch embedding
An array of EmbedInput objects with text, image, or video fields for multimodal providers

string

default:"float"

The format of the returned embeddings. One of float or base64.

integer

The number of dimensions in the output embedding. Only supported by models that accept a dimensions parameter (e.g. text-embedding-3-small).

string

A unique identifier for the end user, used for monitoring.

Response

string

Always list.

object[]

An array of embedding objects, one per input item, in the same order as the input.

Show properties

string

Always embedding.

integer

The index of this embedding in the input array.

number[]

The embedding vector as an array of floats. Length equals the model’s embedding dimension (or the requested dimensions).

string

The model used to generate the embeddings.

object

Token usage for this request.

Show properties

integer

Number of tokens in the input.

integer

Total tokens consumed.

Code examples

curl http://localhost:8787/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "x-portkey-provider: openai" \
  -H "x-portkey-api-key: $OPENAI_API_KEY" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "The Portkey AI Gateway routes requests to 250+ LLMs.",
    "encoding_format": "float"
  }'

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8787/v1",
    api_key="$OPENAI_API_KEY",
    default_headers={
        "x-portkey-provider": "openai",
    },
)

response = client.embeddings.create(
    model="text-embedding-3-small",
    input="The Portkey AI Gateway routes requests to 250+ LLMs.",
)

print(response.data[0].embedding[:5])  # first 5 dimensions

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "http://localhost:8787/v1",
  apiKey: process.env.OPENAI_API_KEY,
  defaultHeaders: {
    "x-portkey-provider": "openai",
  },
});

const response = await client.embeddings.create({
  model: "text-embedding-3-small",
  input: "The Portkey AI Gateway routes requests to 250+ LLMs.",
});

console.log(response.data[0].embedding.slice(0, 5)); // first 5 dimensions

Overview

Chat

Multimodal

Files & Batches

Other

POST /v1/embeddings

Request headers

Request body

Response

Code examples

​POST /v1/embeddings

​Request headers

​Request body

​Response

​Code examples

POST /v1/embeddings

Request headers

Request body

Response

Code examples