Embeddings - Planck

Endpoint

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

Request

Field	Type	Required	Description
`model`	string	Yes	Embedding model. A provider prefix selects a provider explicitly.
`input`	string or string[]	Yes	One input string or a batch of strings.
`encoding_format`	string	No	Output encoding supported by the selected model.
`dimensions`	integer	No	Requested dimensions for models that support it.
`user`	string	No	End-user identifier stored with request attribution.

curl https://api.inquantum.ai/v1/embeddings \
  -H "Authorization: Bearer $PLANCK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": ["first document", "second document"]
  }'

Response

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [0.0123, -0.0456],
      "index": 0
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 4,
    "total_tokens": 4
  }
}

See the Embeddings guide for SDK examples, routing, billing, and tracking.

This endpoint uses the shared AI Gateway error envelope. See the Error Handling & Fallback guide for response examples, retry rules, fallback behavior, and streaming errors.