GET

/v1/schemas/fal/chat/nvidia/nemotron-3-5-super/video

Accept:

kind inputactivity chathash 0e027b2c…extracted Oct 16, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `5fa9c12e15853c71f152b8dc1e1af9f7293d2991bbd8f69c6a041911242f4214` { "fetchedAt": 1792126843, "extractorVersion": "1", "verifiedAt": null }

Request body

8 properties · 2 required · 0 $defs

property	type	description	constraints
prompt*	string	Text prompt to send to the model.	length ≥ 1
video_url*	string	URL of the video to reason about. mp4, max 2 minutes, max 3840 pixels per side and 3840x2160 total pixels.
reasoning_mode	enum	`think` emits an explicit reasoning trace before the final answer; `no_think` returns a direct answer.	think \| no_think · default: "no_think"
top_p	number	Nucleus sampling probability mass.	0 < n ≤ 1 · default: 0.95
temperature	number	Sampling temperature. NVIDIA recommends 1.0 for all tasks.	0 ≤ n ≤ 2 · default: 1
enable_safety_checker	boolean	Whether to enable the safety checker.	default: true
max_tokens	integer	Maximum number of tokens to generate.	1 ≤ n ≤ 32000 · default: 1024
system_prompt	string	Optional system prompt to steer the model.	nullable

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"nvidia/nemotron-3-5-super/video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}