Embeddings

POST/v1/embeddings

OpenAI-compatible vector embeddings API. Input forms, dimensions, encoding, and additional fields remain subject to the selected model and provider.

Request body

stringmodelrequired

Embedding model ID, for example alibaba/text-embedding-v4

string | string[] | integer[] | integer[][]inputrequired

Text, token IDs, or a batch of texts or token-ID arrays to embed

Optional<integer>dimensions

Output vector dimension when supported by the selected model; there is no universal dimension list

Optional<string>encoding_format

Embedding encoding format. Provider support determines whether float or base64 is available

POST https://api.sandbase.ai/v1/embeddings
Authorization: Bearer sk-your-api-key
Content-Type: application/json

{"model":"alibaba/text-embedding-v4","input":"SandBase provides a unified API for AI models, agents, and developer tools.","dimensions":1024,"encoding_format":"float"}

Response200 OK

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        0.0123,
        -0.0045,
        0.0312
      ]
    }
  ],
  "model": "alibaba/text-embedding-v4",
  "usage": {
    "prompt_tokens": 16,
    "total_tokens": 16
  }
}