Start building
SandBase

Appearance

Nemotron 3 Nano Omni

POST/v1/run

Nemotron 3 Nano Omni Video by NVIDIA - advanced AI model for video-to-text. Delivers high-quality results with fast inference, suitable for both creative and production workflows.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to nvidia/nemotron-3-nano-omni/video.

Default: nvidia/nemotron-3-nano-omni/video

stringpromptrequired

Text prompt to send to the model. English only.

Optional<string>video

URL of the video to reason about. mp4, up to 1080p, max 2 minutes.

Optional<integer>max_tokens

Maximum number of tokens to generate.

Range: 1 to 20000

Default: 1024

Optional<number>top_p

Nucleus sampling probability mass.

Range: 0 to 1

Default: 0.95

Optional<number>temperature

Sampling temperature. Lower is more deterministic.

Range: 0 to 2

Default: 0.7

Optional<string>system_prompt

Optional system prompt to steer the model. Reasoning behavior is controlled by the separate `reasoning_mode` field.

Optional<string>reasoning_mode

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.

Allowed values: think, no_think

Default: no_think

Response Schema

The submit endpoint returns a run response. If its status is pending or running, poll GET /v1/run/{id} with the returned opaque ID until it reaches a terminal state.

stringidrequired

Opaque SandBase run identifier. Use it exactly as returned; no prefix is guaranteed.

stringstatusrequired

Current public run status.

Allowed values: pending, running, completed, failed, timeout

Optional<string>model

Public SandBase model name used for this run.

Optional<array<object>>outputs

Present only for completed runs. Each object is capability-specific; inspect the selected model schema for its fields.

Optional<object>error

Present only for failed or timeout runs. Contains a public error type and sanitized message.

Optional<string>error.type

Stable public error category.

Optional<string>error.message

Sanitized error message safe to show to clients.

Optional<object>usage

Usage details when available.

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: video-to-text

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async