Embeddings API

Generate high-quality vector embeddings for text using FastRouter.ai’s unified embeddings interface.

FastRouter.ai supports a unified Embeddings API to generate high-quality vector representations for your text using supported model providers. Access models from OpenAI, Google, DeepInfra, and more — all through a single endpoint.

---

Endpoint

POST https://go.fastrouter.ai/api/v1/embeddings

Base URL

https://go.fastrouter.ai/api/v1

---

Supported Models

Model	Description
openai/text-embedding-3-small	Fast, lightweight embedding model
openai/text-embedding-3-large	High-quality embeddings for semantic search & advanced tasks
openai/text-embedding-ada-002	Most cost-effective option
google/gemini-embedding-001	Versatile Google model for text & multimodal embeddings
deepinfra/intfloat-e5-base-v2	Efficient, high-performance embedding model based on the E5 architecture

---

Parameters

Field	Type	Description
model	string	The fully qualified model slug — choose from the Supported Models above
input	string or string[]	The input text or list of text items to embed
dimensions	integer (optional)	Requested embedding size. Supported only in text-embedding-3 series and newer

---

Request Format

Provide input text and (optionally) specify the embedding dimensions.

Request Example

curl --location 'https://go.fastrouter.ai/v1/embeddings' \
--header 'Authorization: Bearer FASTROUTER_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
    "model": "openai/text-embedding-3-large",
    "input": "Your text string goes here",
    "dimensions": 4
}'

---

Sample Response

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

---

Python Example

You can use the OpenAI Python SDK with FastRouter by overriding the base URL.

from openai import OpenAI

client = OpenAI(
    base_url="https://go.fastrouter.ai/v1",  # FastRouter base URL
    api_key="FASTROUTER_API_KEY",           # Replace with your API key
)

resp = client.embeddings.create(
    model="openai/text-embedding-3-large",
    input="Your text string goes here",
    dimensions=4
)

print("Embeddings:", resp.data[0].embedding)