Skip to main content
POST
Create embeddings
Generate embedding vectors for one or more input strings. Pass a non-empty input string, or an array of strings for batch embedding. The request and response are OpenAI-compatible, so the OpenAI SDK works unchanged by pointing base_url at the AIsa relay. Available models (both 1024-dim output):
  • jina-embeddings-v3
  • jina-embeddings-v5-text-small
Served via the AIsa relay path /v1/embeddings — OpenAI-compatible. Billing is token-based at $0.050 per 1M tokens; the usage.total_tokens field reports the tokens billed for each request.

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
model
enum<string>
required

Embedding model name. Available: jina-embeddings-v3 or jina-embeddings-v5-text-small (both 1024-dim).

Available options:
jina-embeddings-v3,
jina-embeddings-v5-text-small
Example:

"jina-embeddings-v3"

input
required

A non-empty string, or an array of non-empty strings, to embed.

Example:

"A fast, OpenAI-compatible embeddings endpoint."

Response

200 - application/json

Embedding list.

object
string
Example:

"list"

data
object[]
model
string
Example:

"jina-embeddings-v3"

usage
object