Generate an image or a video

Generates an image or a video from a text prompt, grounded in reference material found by search.

post/v1/grounded-generation

Request

  • Base URL: https://api.octen.ai
  • URL: https://api.octen.ai/v1/grounded-generation
  • Auth: one of:
    • HTTP bearer
    • API key in header x-api-key

Request body

modality'image' | 'video' required

The type of output to generate.

promptstring required

The text description of what to generate.

model'google/gemini-3-pro-image' | 'google/gemini-3.1-flash-image' | 'minimax/hailuo-3'

The model to use. When omitted, the model default applies.

aspect_ratio'16:9' | '1:1' | '9:16'

Aspect ratio of the output.

durationinteger

Video length in seconds. Applies when modality is video. Values outside the allowed range are adjusted to the nearest bound.

Response

Successful grounded generation response. The task starts in queued.

request_idstring

Unique identifier for the request.

generation_idstring required

Unique task id, used to retrieve the result.

modality'image' | 'video' required

The type of output this task generates.

status'queued' required

Task state.

created_atinteger required

Unix timestamp in seconds when the task was created.

Changes

No recorded changes to this operation across all 1 revision of this API.