Pricing
API pricing for video generation
Video generation is billed per second of output video. Higher resolution and premium models have proportionally higher costs. For enterprise plans, please contact our sales team.
Generate videos from text prompts. Pricing is based on the duration of the generated video in seconds. Available as v2/text-to-video (async) and v1/text-to-video (sync).
Generate videos from an input image. Pricing is based on the duration of the generated video in seconds. Available as v2/image-to-video (async) and v1/image-to-video (sync).
Generate videos synchronized to audio input. Pricing is based on the duration of the input audio in seconds. Available as v2/audio-to-video (async) and v1/audio-to-video (sync).
Edit and regenerate portions of an existing video. Pricing is based on the duration of the input video. Available as v2/retake (async) and v1/retake (sync).
Extend a video by generating additional frames at the beginning or end. Pricing is based on the duration of the extended portion plus context frames from the input video, capped at a total of 505 billed frames. The resulting billed seconds depend on the input video’s frame rate (~21 seconds at 24fps). Available as v2/extend (async) and v1/extend (sync).
Convert SDR videos into HDR. Pricing is tiered by input pixel count — the input snaps to the smallest tier that can contain it. Billed per second of input video. Available as v2/video-to-video-hdr (async only).