Video Models

Text-to-video and image-to-video generation. Video models typically run as background jobs — submit a request, then poll for the result.

How video generation works

Submit a prompt (and optionally a first-frame image) to the video route. The model returns a task/job ID; poll until the status is completed, then download the returned clip URL promptly — provider URLs can expire. Exact fields are defined by the upstream model.

Capabilities

ParameterTypeRequiredDescription
Text-to-videomodeoptionalGenerate a clip from a text prompt.
Image-to-videomodeoptionalAnimate from a reference/first-frame image.
Duration & resolutioncontroloptionalClip length and size are model-dependent (commonly a few seconds, up to 720p/1080p).

Where to find video models

Browse the Models page and filter by video capability for current model IDs and pricing, then call the Video API with the chosen ID. Video pricing is by duration, resolution, or clip count — confirm cost before generating at scale.

Model-dependent features

OneRouter keeps protocol compatibility and forwards model-specific parameters where supported. Features such as tool calling, structured output, reasoning, prompt caching, web search, image input, audio input, video generation, and provider-specific options depend on the selected model and upstream provider. Check the model detail page before relying on a feature in production.