Open Nemotron omni model combining reasoning with text, vision, and audio
Details
| Field | Value |
|---|---|
| id | nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free |
| family | nemotron |
| modality | text+image+video+audio->text |
| context_length | 256000 |
| max_output_tokens | 65536 |
| release_date | 2026-04-28 |
| is_open_weights | yes |
| supports_tool_call | yes |
| supports_reasoning | yes |
| supports_structured_output | no |
| supports_attachment | yes |
| input_modalities | text, image, video, audio |
| output_modalities | text |