Skip to main content
OpenAI’s Sora 2 video generation. Text-to-video and image-to-video with high coherence and cinematic quality. 4-12 second output.

Request

Required: prompt
Optional: aspect_ratio, duration_seconds, quality, reference_images
Reference inputs take asset ids from POST /v1/uploads or an earlier output’s asset_id. Prices and allowed values come from the live catalog; GET /v1/models/sora-2-fal is always current.