Endpoints / Vectors

Embeddings

POST/v1/embeddings

Create vector embeddings with OpenAI-compatible clients. Use the model catalog to discover which models support embeddings and whether they accept custom dimensions.

Request body

modelstring

required

Embedding model ID from /api/models/catalog.

inputstring | string[]

required

Text input or ordered batch of text inputs. The response preserves order.

dimensionsinteger

nullable

Optional vector dimension for models that support truncation.

encoding_formatstring

nullable

floatbase64

Output encoding format when supported by the upstream provider.

Response

objectstring

Usually list.

dataobject[]

One embedding item per input.

data[].embeddingnumber[] | string

Vector values or base64-encoded vector depending on encoding_format.

usage.prompt_tokensinteger

Input tokens used for embedding.

Batch guidance

Pass an array for small batches. For large data jobs, chunk client-side so each request stays within provider body-size and token limits.

Common models

Model	Dim	Notes
`BAAI/bge-m3`	1024	Multilingual
`text-embedding-3-small`	1536	OpenAI cheap default
`text-embedding-3-large`	3072	OpenAI high quality
`gemini-embedding-001`	768	Google default

Embeddings

Request body

Response

Batch guidance

Common models

See also