Image -> JSON - VLM Run

Authorizations

Authorization

string

header

required

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.

callback_url

string | null

The URL to call when the request is completed.

Minimum length: 1

created_at

string

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

detail

enum<string>

default:

auto

The detail level to use for the model.

Available options:

auto,

hi,

lo

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

string

Unique identifier of the request.

json_schema

object | null

The JSON schema to use for the model.

metadata

object

Optional metadata to pass to the model.

model

string

default:

vlm-1

The model to use for generating the response.

Allowed value: "vlm-1"

Response

200 - application/json

Base prediction response for all API responses.

completed_at

string | null

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

created_at

string

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

string

Unique identifier of the response.

response

any | null

The response from the model.

status

string

default:

pending

The status of the job.