GET
/v1/schemas/fal/chat/nvidia%2Fnemotron-3-nano-omni%2Fvision
Accept:
Request body
8 properties · 2 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| image_url* | string | URL of the image to reason about. RGB JPEG or PNG. | |
| prompt* | string | Text prompt to send to the model. English only. | length ≥ 1 |
| top_p | number | Nucleus sampling probability mass. | 0 ≤ n ≤ 1 · default: 0.95 |
| temperature | number | Sampling temperature. Lower is more deterministic. | 0 ≤ n ≤ 2 · default: 0.7 |
| reasoning_mode | enum | Whether the model should emit an explicit reasoning trace. `no_think` returns a direct answer; `think` returns chain-of-thought followed by the final answer. | think | no_think · default: "no_think" |
| enable_safety_checker | boolean | Whether to enable the safety checker. | default: true |
| system_prompt | string | Optional system prompt to steer the model. Reasoning behavior is controlled by the separate `reasoning_mode` field. | nullable |
| max_tokens | integer | Maximum number of tokens to generate. | 1 ≤ n ≤ 20000 · default: 1024 |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"nvidia/nemotron-3-nano-omni/vision","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}