Create Embeddings
OpenAI-compatible embeddings endpoint.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
OpenAI-compatible POST /v1/embeddings request body, plus minimal Eden extensions.
Unknown top-level fields are forwarded to the underlying provider.
Input to embed: string, list of strings, pre-tokenized list of ints, or pre-tokenized batch (list of int lists). Max 2048 items for OpenAI.
Model identifier in 'provider/model' format, e.g. 'openai/text-embedding-3-small'.
Output encoding: 'float' (default) or 'base64'.
float, base64 Reduce output vector size. 3-series models only.
x > 0End-user identifier for abuse tracking.
Arbitrary metadata attached to the request.
Additional HTTP headers forwarded to the provider API.
Response
Successful Response
OpenAI-compatible embeddings response + Eden cost and provider fields.
EmbeddingsDataClass (from edenai-apis) already widens
data[].embedding to list[float] | str so the base64 wire format
validates here too.