POST /v1/data/ai/videos/run
Pricing: Metered: you pay exactly each call’s cost at the selected model’s rates (default Google: Veo 3.1 Lite: the model’s own rate).
Request
Send the inputs underparams. Only the keys below are accepted; any other key returns 422 invalid_params.
What happens in the video, one prompt per line. Each prompt is one video, one job and one row.
The video model. Pick from the list (popular models first). Each model shows its own rates, mostly per second of video at each resolution, and that is exactly what each video costs.29 allowed values, for example
google/veo-3.1-lite (Google: Veo 3.1 Lite), google/veo-3.1-fast (Google: Veo 3.1 Fast), google/veo-3.1 (Google: Veo 3.1), kwaivgi/kling-v3.0-pro (Kling: Video v3.0 Pro), kwaivgi/kling-v3.0-std (Kling: Video v3.0 Standard), bytedance/seedance-2.5-flash (ByteDance: Seedance 2.5 Flash), bytedance/seedance-2.0-mini (ByteDance: Seedance 2.0 Mini), alibaba/wan-3.0-prime (Alibaba: Wan 3.0 Prime), minimax/hailuo-3-max (MiniMax: H3 Max), runway/gen-4.5 (Runway: Gen-4.5). Fetch the full list with GET /v1/data/ai/videos?expand=options.The clip length in seconds. Leave blank for the model’s default. Only the lengths the selected model offers are accepted.31 allowed values, for example
-1 (-1 seconds), 1 (1 seconds), 2 (2 seconds), 3 (3 seconds), 4 (4 seconds), 5 (5 seconds), 6 (6 seconds), 7 (7 seconds), 8 (8 seconds), 9 (9 seconds). Fetch the full list with GET /v1/data/ai/videos?expand=options.The video resolution, e.g. 480p or 720p. Leave blank for the model’s default.Allowed values:
360p, 480p, 720p, 768p, 1080p, 2K, 4K.The frame shape, e.g. 16:9 or 9:16. Leave blank for the model’s default.Allowed values:
16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21, 3:2, 2:3, 5:2, 2:1.Optional public image URL used as the first frame, for image-to-video models. The same image starts every prompt’s video.
Example
Response fields
Each row indata is one video, keyed by these fields.