NNVIDIA · Released Oct 15, 2026
Nemotron 3.5 Super VL
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...
- Released
- Oct 15 2026
- Context window
- 1M 236K out
- Input / 1M tokens
- $0.15 from $0.10
- Output / 1M tokens
- $0.50 from $0.40
Where to run it
6 providers compared
Cheapest: Crusoe at $0.10 / $0.40 per 1M input / output tokens — 65% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| CrusoeBF16 | $0.10 | $0.40 | $0.08 | 262K | 236K | 82.5%24h | Cheapest |
| Together | $0.15 | $0.50 | $0.02 | 262K | 236K | 100%24h | +36% |
| CoreWeavenvfp4 · NVFP4 | $0.15 | $0.50 | $0.02 | 1M | 944K | 98.6%24h | +36% |
| DeepInfraFP4 | $0.15 | $0.50 | $0.02 | 262K | 236K | 96.5%24h | +36% |
| BaseTenFP4 | $0.20 | $0.50 | $0.04 | 1M | 944K | 36%24h | +57% |
| VeniceFP4 | $0.25 | $1.25 | $0.13 | 262K | 33K | 99.3%24h | +186% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Nemotron 3.5 Super VL. Scores appear here automatically once it does.
Specs
Details
- Model ID
nvidia/nemotron-3.5-super-vl- Developer
- NVIDIA
- Release date
- Oct 15, 2026 ·
- Context window
- 1,048,576 tokens
- Max output
- 235,929 tokens
- API price
- $0.15 / $0.50 per 1M input / output tokens
- Providers
- 6
- Input types
- text, image, video
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- Yes
Release date, prices and providers from OpenRouter's catalog; buying directly from a provider can cost a little differently. Uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.