Embeddings

Vector representations for retrieval.

Use embeddings for semantic search, clustering, and retrieval-augmented generation (RAG). The request/response format follows common OpenAI conventions.

Endpoint

POST /api/v1/embeddings

Request

{
  "model": "provider/embedding-model",
  "input": "Text to embed"
}

Response

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0123, -0.0456, 0.0789]
    }
  ],
  "model": "provider/embedding-model",
  "usage": { "prompt_tokens": 8, "total_tokens": 8 }
}