Video Generation


Our Video Generation API creates videos based on text prompts. These text prompts have a character limit of 250, and the model produces one video per prompt. Each video is two seconds long and has a frame rate of 8 frames per second (16 frames total).

Before returning any video, we first run that video through our visual moderation model in order to prevent violent, sexually explicit, or otherwise harmful results. If the generated images do not pass this moderation step, the API call will fail and an error message will be returned in place of a normal response.


The output of our Generative Vision API consists of a link to the generated video. Each video is 512x512 and is in mp4 format. To see an annotated example of an API response object for this model, you can visit our API reference page.