v8

latestOpenAPI 3.1.1LicenseRef-Proprietaryraw.githubusercontent.com2026-05-19280916.6 KB

Runs

Start a generation run

Starts a model generation run in a project canvas using a prompt, workspace, project, optional model, and optional model parameters. Mutating public API requests support an optional Idempotency-Key header for client retries; duplicate keys within two hours return idempotency_duplicate.

post/runs/generation

Request body

type'image' | 'video' | 'audio' | 'text' required

Generation type

promptstring required

Generation prompt

modelstring

Model endpoint ID

workspace_idstring required

Workspace identifier

project_idstring required

Project identifier

paramsobject

Model parameters

Example request

{
  "prompt": "A cinematic product photo of a ceramic mug on a sunlit table",
  "model": "t2i-flux-2-pro",
  "workspace_id": "ws_abc123",
  "project_id": "prj_abc123"
}

Response

Generation run started.

run_idstring required

Run identifier

type'generation' | 'technique' | 'action' required

Run type

estimated_secondsinteger nullable required

charged_costnumber required

Cost charged in USD

poll_urlstring uri nullable

project_idstring nullable

Project identifier

Example response

{
  "run_id": "run_abc123",
  "model": {
    "model_id": "t2i-flux-2-pro"
  },
  "technique": {
    "technique_id": "tech_abcd1234"
  },
  "action": {
    "action_id": "split-text"
  },
  "project_id": "prj_abc123"
}