POST
/
v1
/
image
/
generate

Authorizations

Authorization
string
headerrequired

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

Body

application/json

Request to the VLM API (i.e. structured prediction).

image
string
required

Base64 encoded image.

id
string

Unique identifier of the request.

created_at
string

Date and time when the request was created (in UTC timezone)

callback_url
string | null

The URL to call when the request is completed.

Minimum length: 1
model
string
default: vlm-1

The model to use for generating the response.

Allowed value: "vlm-1"
domain
enum<string> | null

The domain identifier.

Available options:
document.generative,
document.invoice,
document.markdown,
document.presentation,
document.receipt,
document.resume,
document.utility-bill,
video.tv-news,
video.tv-intelligence
json_schema
object | null

The JSON schema to use for the model.

detail
enum<string>
default: auto

The detail level to use for the model.

Available options:
auto,
hi,
lo
metadata
object

Optional metadata to pass to the model.

Response

200 - application/json

Base prediction response for all API responses.

id
string

Unique identifier of the response.

created_at
string

Date and time when the request was created (in UTC timezone)

completed_at
string | null

Date and time when the response was completed (in UTC timezone)

response
any | null

The response from the model.

status
string
default: pending

The status of the job.