GET

/v1/schemas/fal/video/blackforestlabs/flux-3-max/text-to-video?kind=output

Accept:

kind outputactivity videohash b146ee4f…extracted Oct 20, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `34886827082e8f8cc093fed83e25e95f7b8ebd2fce453fe026cd82e8497e9973` { "fetchedAt": 1792472410, "extractorVersion": "1", "verifiedAt": null }

Response body

3 properties · 2 required · 1 $defs

property	type	description
seed*	integer	The seed used for the generation.
video*	VideoFile	The generated video.
timings	object	`inference`: seconds the model spent denoising the video. Excludes prompt expansion, decoding and upload.

Types

1 $defs

VideoFileobject

content_type	string	The mime type of the file.	nullable
file_size	integer	The size of the file in bytes.	nullable
fps	number	The FPS of the video	nullable
url*	string	The URL where the file can be downloaded from.
height	integer	The height of the video	nullable
duration	number	The duration of the video	nullable
num_frames	integer	The number of frames in the video	nullable
width	integer	The width of the video	nullable
file_name	string	The name of the file. It will be auto-generated if not provided.	nullable

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"blackforestlabs/flux-3-max/text-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}