GET

/v1/schemas/fal/chat/nvidia%2Fnemotron-3-5-super%2Fvision

kind inputactivity chathash 6f02d41d…extracted Oct 16, 2026version currentsource upstream spec ↗

Request body

8 properties · 2 required · 0 $defs
propertytypedescriptionconstraints
prompt*stringText prompt to send to the model.length ≥ 1
image_url*stringURL of the image to reason about. RGB JPEG or PNG.
reasoning_modeenum`think` emits an explicit reasoning trace before the final answer; `no_think` returns a direct answer.think | no_think · default: "no_think"
top_pnumberNucleus sampling probability mass.0 < n ≤ 1 · default: 0.95
temperaturenumberSampling temperature. NVIDIA recommends 1.0 for all tasks.0 ≤ n ≤ 2 · default: 1
enable_safety_checkerbooleanWhether to enable the safety checker.default: true
max_tokensintegerMaximum number of tokens to generate.1 ≤ n ≤ 32000 · default: 1024
system_promptstringOptional 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/vision","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}