Nemotron 3 Nano Omni

nemotron-3-nano-omni-vision

Visionby NVIDIA

Vision reasoning variant of NVIDIA's Nemotron 3 Nano Omni. 30B A3B hybrid Transformer-Mamba MoE - accepts an image plus a prompt and returns text.

Prices in credits (1 credit = $0.01).

Data schema

Field	Type	Description
top_p	number	Nucleus sampling probability mass.
promptrequired	string	Text prompt to send to the model. English only.
image_urlrequired	string	URL of the image to reason about. RGB JPEG or PNG.
max_tokens	integer	Maximum number of tokens to generate.
temperature	number	Sampling temperature. Lower is more deterministic.
system_prompt	—	Optional system prompt to steer the model. Reasoning behavior is controlled by the separate `reasoning_mode` field.
reasoning_mode	stringenum: think, no_think	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.
enable_safety_checker	boolean	Whether to enable the safety checker.