Dieser Bereich ist noch nicht übersetzt. Der folgende Inhalt wird auf Englisch angezeigt, wie veröffentlicht. Englische Fassung lesen.
NVIDIA · Text model · GA
Compare with similar models Open the Model Finder
Figures checked 1 Nov 2026. A dash means not published on the sources we checked, so it stays blank rather than estimated. AA index and speed are from Artificial Analysis at the default setting.
| Lab | NVIDIA |
|---|---|
| Type | Text |
| Status | GA models.dev (opens in a new tab) |
| Released | 15 Oct 2026 models.dev (opens in a new tab) |
| API access | Open weights only models.dev (opens in a new tab) |
| API model ID | – |
| API rate limits | – |
| Consumer app plans | – |
| Price at each level | – |
| Input per 1M tokens | – |
| Output per 1M tokens | – |
| Cached input | – |
| Batch in / out | – |
| Other pricing | Free trial endpoints on build.nvidia.com. Otherwise self-host or third-party host |
| Context window | 1.05M tokens models.dev (opens in a new tab)As listed for NVIDIA NIM |
| Max output | – |
| Input types | text, image, video models.dev (opens in a new tab) |
| Output types | text |
| Weights | Open huggingface.co (opens in a new tab) |
| Reasoning | Yes models.dev (opens in a new tab) |
| Tool use | Yes models.dev (opens in a new tab) |
| Artificial Analysis index | 14 (default) artificialanalysis.ai (opens in a new tab) |
| Output speed | 474 tokens/s artificialanalysis.ai (opens in a new tab) |
| Time to first token | 0.71 s artificialanalysis.ai (opens in a new tab) |
| Reasoning levels | – |
| Lab benchmark claims | – |
| Limitations |
|
NVIDIA does not document calling MCP servers from its own API. You can still connect tools through an agent or framework. Browse AI tools
Same type, closest on quality index and blended price. A similarity, not a ranking.
Compare Nemotron 3.5 Super VL with Nemotron 3 Ultra and Qwen3.8 27B
All 109 AI models · AI agents · How we check sources
NVIDIA 
DSX POD ships Vera Rubin racks in containers with liquid cooling and rack power fitted and tested at the factory. NVIDIA says deployment at a prepared site drops from six months to as little as 14 days, so the site's power and cooling must be ready first.
