Skip to main content
POST
/
v1
/
embeddings
Create embeddings
curl --request POST \
  --url https://api.aurous-labs.com/v1/embeddings \
  --header 'Content-Type: application/json' \
  --header 'X-Api-Key: <api-key>' \
  --data '
{
  "model": "aurous-embed-vision",
  "input": "<string>",
  "dimensions": 1024,
  "encoding_format": "float",
  "user": "<string>"
}
'
{
  "data": [
    {
      "index": 0,
      "embedding": [
        0.0123,
        -0.0456,
        0.0789
      ]
    }
  ],
  "model": "aurous-embed-vision",
  "usage": {
    "prompt_tokens": 7000,
    "total_tokens": 7000,
    "credits_charged": 0.19125,
    "breakdown": {
      "input": {
        "text": 0.09375,
        "visual": 0.0975,
        "video": 0
      },
      "model": "aurous-embed-vision"
    }
  }
}

Authorizations

​
X-Api-Key
string
header
required

Your team API key (starts with al_live_).

Headers

​
Idempotency-Key
string

Stripe-style idempotency key. Replays return the cached response with Aurous-Idempotent-Replayed: true. Same key + different canonical body returns 409 idempotency_key_in_use. Replay window is 24 hours.

​
Aurous-Version
string

Optional API version pin (YYYY-MM-DD). Defaults to your team's pinned version, or the system default 2026-05-15 for unauthenticated requests.

Pattern: ^\d{4}-\d{2}-\d{2}$
Example:

"2026-05-15"

Body

application/json
​
model
string
required

Public model slug (e.g. "aurous-embed-vision"). Pass exactly as listed by GET /v1/models.

Example:

"aurous-embed-vision"

​
input
required

Input — accepts a string OR an array of content parts ({type: "text"|"image_url"|"video_url"}) for multimodal. String-array (string[]) batch input is NOT accepted on v1: the underlying model concatenates batched text into a single embedding, so a customer expecting OpenAI-style N→N would get one combined vector. Loop client-side or pass a multimodal-parts array (returns one combined embedding).

​
dimensions
integer

Output vector dimensions. Most models return a fixed dimension and reject this parameter. If the model does not support dimensions, the request returns 400 embeddings_unsupported_dimensions.

Example:

1024

​
encoding_format
enum<string>
default:float

Vector encoding format. Accepted for OpenAI SDK compatibility (the Node SDK sends base64 by default); v1 always returns float vectors regardless of the value sent. base64 support (returning base64-encoded float buffers) is reserved for a future release.

Available options:
float,
base64
​
user
string

End-user identifier for your records (optional). Stored on the inference row; no Aurous-side behavior. Mirrors OpenAI compat.

Maximum string length: 256

Response

Embedding created.

​
object
enum<string>
required

OpenAI envelope discriminator.

Available options:
list
​
data
object[]
required

Embedding items. Always a single-element array on v1.

​
model
string
required

Model slug used for this request (echoed from the request).

Example:

"aurous-embed-vision"

​
usage
object
required

Token + credit accounting for this request.