Embeddings API

1024 dimension vector embedding at a lower cost.

Get API Key View Quickstart

What You Get

Production-ready vector embeddings with enterprise controls.

Secure by Default

Bearer auth with hashed API keys, scoped usage, and per-key rate limits.

Lower cost

Maavee embeddings are much lower cost compared to LLM providers.

API Quickstart

Use the embeddings endpoint in production.

Embed

curl -X POST https://api.synapse.maavee.ai/api/embed \
  -H "Authorization: Bearer <API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{"payload": "The quick brown fox jumps over the lazy dog."}'

Returns a base64-encoded float32 vector and dimensions.



Headers

  • Authorization: Bearer <API_KEY>
  • Content-Type: application/json
  • Rate limit headers: X-RateLimit-Limit, X-RateLimit-Remaining

Response

{
  "endpoint": "embed",
  "payload": {
    "object": "embedding",
    "embedding": "",
    "dimensions": 1536
  },
  "usage": {
    "limit": 1000,
    "used": 1,
    "remaining": 999
  }
}

How It Works

REST API Or Maavee Synapse SDK in Node or Pyhton.

Authentication & Metering

  • Bearer API keys stored as hashes.
  • Per-key rate limiting; limits returned in headers.
  • Metering per payload bytes.

Model

  • Embedding model: Qwen/Qwen3-Embedding-0.6B.
  • Runs on CPU by default; can be tuned for GPU.

Start Embedding With Synapse

Get secure, metered embeddings with enterprise controls.

Request Access