POST /v1/embeddings

OpenAI-compatible embeddings with the same keys and billing as the rest of the API.

POST https://api.refuseless.com/v1/embeddings

Where the model supports embeddings, vectors are returned and usage is billed at the catalog rate. Models without embedding support return 404 model_not_found — nothing is billed.

Request

Field	Type	Required	Notes
`model`	string	Yes	Catalog id
`input`	string / array	Yes	Text (or array of texts) to embed
`encoding_format`	string	No	`float` (default) or `base64`, where supported
`dimensions`	number	No	Requested dimensions, where supported
`user`	string	No	Passed through

Response

{
  "object": "list",
  "data": [{ "object": "embedding", "index": 0, "embedding": [0.012, -0.44] }],
  "model": "glm-5.3-abliterated",
  "usage": { "prompt_tokens": 12, "total_tokens": 12 }
}

Example

curl https://api.refuseless.com/v1/embeddings \
  -H "Authorization: Bearer $REFUSELESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3-abliterated",
    "input": "Write a tight system prompt."
  }'

Errors

400 missing model/input · 401 bad key · 402 out of credits · 404 unknown model or no embedding support on this model · 429 busy/warming · 503 model unavailable.