Model tracker / NVIDIA
NVIDIA Nemotron 3.5 Super VL
NVIDIA Nemotron 3.5 Super VL is a fast open-weight model from NVIDIA, released 15 October 2026. At Together AI it costs $0.15 per million input tokens and $0.50 per million output tokens, with a 1M-token context window. 5 providers serve it, and Together AI is the cheapest.
- Made by
- NVIDIA Corporation
- Released
- 2026-10-15
- Status
- Generally available, new
- Tier
- Fast
- Weights
- Open
- Context window
- 1,048,576 tokens
- Input
- text, image, video
- API id
nvidia/NVIDIA-Nemotron-3.5-Super-VL
NVIDIA Nemotron 3.5 Super VL price at 5 providers
US dollars per million tokens. Blended is 3 input tokens for every output token, one number to compare on. The cheapest blended price is highlighted.
| Provider | Input | Output | Cached input | Blended | Batch | Checked |
|---|---|---|---|---|---|---|
| Together AI | $0.15 | $0.50 | $0.02 | $0.237 | – | 2026-10-16 |
| Baseten · nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B | $0.20 | $0.50 | $0.04 | $0.275 | – | 2026-10-16 |
| DigitalOcean Holdings · nemotron-3.5-super-vl | $0.30 | $0.65 | $0.06 | $0.387 | – | 2026-10-16 |
| DeepInfra | $0.20 | $1.00 | $0.10 | $0.40 | – | 2026-10-16 |
| Nebius Group N.V. · nvidia/Nemotron-3.5-Super-VL | $0.30 | $0.90 | – | $0.45 | – | 2026-10-16 |
- Together AI: Open weights (120B total, 12B active), OpenMDW-1.1 licence. Together publishes no serving context; 1M is from the model card.
- DigitalOcean Holdings: DigitalOcean serverless inference (prepaid). No audio input.
- DeepInfra: Served with a 256K context.
- Nebius Group N.V.: BF16, us-north1. No cached-input or batch price published.
NVIDIA Nemotron 3.5 Super VL benchmarks
| Benchmark | Score | What it measures | Reported by |
|---|---|---|---|
| SWE-bench Verified | 71.1% | real GitHub issues fixed | NVIDIA |
| GPQA Diamond | 89.52% | graduate-level science questions answered correctly | NVIDIA |
Scores reported by a model's maker aren't independently checked.
Models like NVIDIA Nemotron 3.5 Super VL
Other fast models closest in price, at each maker's own price or the cheapest provider.
| Model | Input | Output | Context | Weights |
|---|---|---|---|---|
| NVIDIA Nemotron 3.5 Super VL | $0.15 | $0.50 | 1M | Open |
| GLM-5.3 Flash Z.ai | $0.15 | $0.50 | 1M | Open |
| Qwen3.8 Flash Alibaba | $0.15 | $0.47 | 1M | Closed |
| Gemma 4 26B A4B Google | $0.15 | $0.60 | 262K | Open |
| Mistral Small 4 Mistral AI | $0.15 | $0.60 | 256K | Open |
| Gemma 4 31B Google | $0.14 | $0.40 | 256K | Open |
Compare them all in the model tracker →
NVIDIA Nemotron 3.5 Super VL FAQ
How much does NVIDIA Nemotron 3.5 Super VL cost?
NVIDIA Nemotron 3.5 Super VL costs $0.15 per million input tokens and $0.50 per million output tokens at Together AI, and $0.02 per million cached input tokens. Prices are list prices in US dollars, last checked 16 October 2026.
What is NVIDIA Nemotron 3.5 Super VL's context window?
NVIDIA Nemotron 3.5 Super VL takes up to 1,048,576 tokens in one request.
Is NVIDIA Nemotron 3.5 Super VL open weight?
Yes. NVIDIA publishes the weights, so you can run NVIDIA Nemotron 3.5 Super VL yourself or at any host that serves it.
Where can I use NVIDIA Nemotron 3.5 Super VL?
NVIDIA Nemotron 3.5 Super VL is available from Together AI, Baseten, DigitalOcean Holdings, DeepInfra and Nebius Group N.V.. At Together AI, call it as nvidia/NVIDIA-Nemotron-3.5-Super-VL.