← All models
Ask NVIDIA Nemotron 3.5 Super about a video clip: summarize what happens, find moments and reason across frames.
Details
- Accepts
- text
Pricing
- Input
- 1250 cr / 1M tokens
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| top_p | number | Nucleus sampling probability mass. |
| promptrequired | string | Text prompt to send to the model. |
| video_urlrequired | string | URL of the video to reason about. mp4, max 2 minutes, max 3840 pixels per side and 3840x2160 total pixels. |
| max_tokens | integer | Maximum number of tokens to generate. |
| temperature | number | Sampling temperature. NVIDIA recommends 1.0 for all tasks. |
| system_prompt | — | Optional system prompt to steer the model. |
| reasoning_mode | stringenum: think, no_think | `think` emits an explicit reasoning trace before the final answer; `no_think` returns a direct answer. |
| enable_safety_checker | boolean | Whether to enable the safety checker. |
Output
| Field | Type | Description |
|---|---|---|
| usage | — | Token usage for the request. |
| output | string | Generated text response. |
| reasoning | — | Reasoning trace, returned only in `think` mode. |
| finish_reason | string | Reason generation stopped. |