Inference

Create embeddings

OpenAI Embeddings-compatible endpoint. Generates vector embeddings for one or more input strings for semantic search, retrieval, and RAG. Up to 512 strings per request, 2 MB total; oversized input returns 400 rather than being truncated.

post/v1/embeddings

Request

  • Base URL: https://api.consus.io
  • URL: https://api.consus.io/v1/embeddings
  • Auth: API key in header x-api-key

Request body

modelstring required

An embedding model ID, e.g. titan-embed-text-v2:il5.

encoding_format'float' | 'base64'

Response

Embedding vectors, one per input string, in input order.

objectstring
modelstring

Example response

{
  "object": "list",
  "data": [
    {
      "object": "embedding"
    }
  ]
}

Changes

No recorded changes to this operation across all 1 revision of this API.