Embeddings

The /v1/embeddings endpoint generates numerical vector representations for semantic search, retrieval-augmented generation (RAG), and clustering. It routes across OpenAI, Cohere, Voyage, and Google Vertex AI at exact provider token rates with zero markup.

POST https://api.nrouter.ai/v1/embeddings

Requests run preflight as Chat Completions: key validation, rate limits, and content inspection (x-nr-guardrails: blocked returns HTTP 400 with zero spend). Input tokens reserve credits that settle upon provider return.

Request Parameters

Response

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [-0.0069, -0.0053, 0.0084]
    }
  ],
  "model": "text-embedding-3-small",
  "usage": { "prompt_tokens": 8, "total_tokens": 8 }
}

Examples

curl -X POST https://api.nrouter.ai/v1/embeddings \
  -H "Authorization: Bearer $NROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"text-embedding-3-small","input":"Vector embedding search."}'

Headers & Errors

Required request headers: Authorization: Bearer sk-nrouter-... and Content-Type: application/json. Response telemetry includes x-nr-request-id, x-nr-latency-ms, x-nr-request-cost, x-nr-model. See Chat Completions.

curl -X POST "https://example.com/v1/embeddings" \  -H "Content-Type: application/json" \  -d '{    "model": "text-embedding-3-small",    "input": "The quick brown fox jumps over the lazy dog."  }'

{  "object": "list",  "model": "text-embedding-3-small",  "data": [    {      "object": "embedding",      "index": 0,      "embedding": [        0.0023,        -0.009,        0.015      ]    }  ],  "usage": {    "prompt_tokens": 5,    "total_tokens": 5  }}