GET

/v1/schemas/together/video/v2%2Fvideos

kind inputactivity videohash fbb50bbe…extracted Oct 22, 2026version currentsource upstream spec ↗

Request body

16 properties · 1 required · 5 $defs
propertytypedescriptionconstraints
model*stringThe model to be used for the video creation request.
promptstringText prompt that describes the video to generate.length ≥ 1 · length ≤ 32000
heightinteger
widthinteger
resolutionstringVideo resolution.
ratiostringAspect ratio of the video.
secondsstringClip duration in seconds.
fpsintegerFrames per second. Defaults to 24.
stepsintegerThe number of denoising steps the model performs during video generation. More steps typically result in higher quality output but require longer processing time.10 ≤ n ≤ 50
seedintegerSeed to use in initializing the video generation. Using the same seed allows deterministic video generation. If not provided a random seed is generated for each request.
guidance_scaleintegerControls how closely the video generation follows your prompt. Higher values make the model adhere more strictly to your text description, while lower values allow more creative freedom. guidence_scale affects both visual content and temporal consistency.Recom…
output_formatenumSpecifies the format of the output video. Defaults to MP4.MP4 | WEBM
output_qualityintegerCompression quality. Defaults to 20.
negative_promptstringSimilar to prompt, but specifies what to avoid instead of what to include
generate_audiobooleanWhether to generate audio for the video.
mediaVideoMediaMedia inputs for video generation. The accepted fields depend on the model type (e.g. i2v, r2v, t2v, videoedit).

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"together","endpointId":"v2/videos","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}