Embeddings

POST /api/v1/embeddings — OpenAI-compatible vector embeddings.

POSThttps://orux.top/api/v1/embeddings

Request

Note: no embedding model is currently enabled on the gateway, so this endpoint returns model_not_routed for every alias. Call GET /api/v1/models to check availability before integrating against it — the request and response shapes below are final and will work unchanged once a model is enabled.

Send one string or an array of strings as input, along with an embedding model alias. The response mirrors the OpenAI Embeddings API shape.

Supported request fields

model (required) — an embedding-capable model alias.
input (required) — a string or array of strings.
encoding_format — optional, passed through to the upstream model.

Chat completions Images

Code examples

Request

curl https://orux.top/api/v1/embeddings \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-large",
    "input": ["Orux AI is a unified model gateway"]
  }'

Swipe horizontally to view the full content