Creates a new job that samples thumbnails from a Mux Video asset, scores them with AI, and selects the best thumbnail candidates. Optional output steering can guide scoring strategy, explicit user intent, audience, brand terms, and campaign style without changing the response schema.
Arbitrary string stored with the job and returned in responses. Useful for correlating jobs with your own systems.
Mux asset ID.
Maximum number of candidate thumbnails to return (1-5). Defaults to 1.
Curated output_steering controls for thumbnail scoring strategy, explicit user intent, audience, brand terms, campaign style, and scoring priorities. These controls guide model behavior but do not guarantee exact output.
Best-effort guidance for what kind of thumbnail candidate should score highest.
Open-ended description of what the user is explicitly looking for in candidate thumbnails. Best-effort guidance only.
Intended audience used as best-effort scoring guidance. Does not change the output schema.
Short description of the campaign/channel thumbnail style to prefer when supported by the frame.
Rubric criteria to emphasize in close calls. Best-effort guidance only.