Documentation

Quickstart

Send your text and your provider key to one endpoint. The response matches OpenAI’s embeddings format.

curl https://www.embedroute.com/api/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "X-Provider-Key: $OPENAI_API_KEY" \
  -d '{
    "model": "openai/text-embedding-3-small",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

import OpenAI from 'openai'

// True drop-in: just point baseURL at EmbedRoute and use YOUR provider key.
const client = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,   // your provider key (must match the model)
  baseURL: 'https://www.embedroute.com/api/v1',
})

const res = await client.embeddings.create({
  model: 'openai/text-embedding-3-small',
  input: 'Your text to embed',
})

console.log(res.data[0].embedding)

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["VOYAGE_API_KEY"],   # your provider key (Voyage here)
    base_url="https://www.embedroute.com/api/v1",
)

res = client.embeddings.create(
    model="voyage/voyage-4",                 # switch providers by changing this
    input="Your text to embed",
)

print(res.data[0].embedding)

Bring your own key

EmbedRoute is bring-your-own-key: you pass the API key for the target provider on every request, and we use it only to make that one call — never storing it. There are two ways to send it:

• OpenAI-SDK drop-in: put your provider key in the SDK’s apiKey (it becomes the Authorization header). Nothing else needed.
• Explicit header: send X-Provider-Key: <your key>. Use this when you also want to send an EmbedRoute er_ key in Authorization for usage tracking.

# Drop-in: provider key as the bearer
Authorization: Bearer <your provider key>

# Or, explicit — plus an optional EmbedRoute key for usage history:
X-Provider-Key: <your provider key>
Authorization: Bearer er_your_embedroute_key

Create embeddings

POST https://www.embedroute.com/api/v1/embeddings

Request body

Example response

{
  "object": "list",
  "data": [
    { "object": "embedding", "index": 0, "embedding": [0.0023, -0.0142, ...] }
  ],
  "model": "openai/text-embedding-3-small",
  "usage": { "prompt_tokens": 9, "total_tokens": 9 }
}

Supported models

Use the provider/model format. Prices are the provider’s own list price per 1M input tokens; you pay them directly. The live catalog is also available at GET https://www.embedroute.com/api/v1/models.

Error handling

Standard HTTP status codes with a JSON error body.

{
  "error": {
    "message": "Incorrect API key provided",
    "type": "provider_error",
    "provider_status": 401
  }
}

Accounts & usage

You don’t need an account to use the router or the Lab. A free account gives you an EmbedRoute key (er_…) that you can pass in the Authorization header to record usage history in your dashboard. It never replaces your provider key — you still bring that.

Rate limits. Anonymous requests are limited per IP; requests made with an EmbedRoute key get a higher per-account limit. Every response includes X-RateLimit-Limit, X-RateLimit-Remaining, and X-RateLimit-Reset; a 429 also returns Retry-After.