Nemotron 3 Ultra vs NVIDIA Nemotron 3.5 Super VL
Lower and Larger mark one number at a time; they don’t rank the models. How well a model does depends on your task; see Benchmarks for measured results.
| Detail | Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b | NVIDIA Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl |
|---|---|---|
| Maker | nvidia | nvidia |
| Kind | Chat | Chat |
| Input per 1M tokens | $0.63 | $0.21 Lower |
| Cached input per 1M tokens | $0.126 | $0.042 |
| Cache write per 1M tokens | Same as input | Same as input |
| Output per 1M tokens | $2.52 | $0.525 Lower |
| Context window | 1,000,000 tokens | 1,048,576 tokens Larger |
| Max output | 65,000 tokens | 1,048,576 tokens Larger |
| Capabilities | Reasoning, tool use | Reasoning, tool use, vision |
| Takes | Text | Text, image, video |
| Returns | Text | Text |
| Zero data retention | Yes, on every provider | Not on every provider |
| No training on requests | Yes, on every provider | Not on every provider |
| Released | 2026-06-04 | 2026-10-15 |
Example costs
Example requests, priced at today’s rates with no cached input.
| Example request | Nemotron 3 Ultra | NVIDIA Nemotron 3.5 Super VL |
|---|---|---|
| 1,000 tokens in, 200 out | $0.001134 | $0.000315 |
| 10,000 tokens in, 1,000 out | $0.00882 | $0.002625 |
| 100,000 tokens in, 4,000 out | $0.07308 | $0.0231 |