NVIDIA: Nemotron 3.5 Super VL
by NVIDIANVIDIA: Nemotron 3.5 Super VL is a large language model from NVIDIA. It costs $0.150 per million input tokens and $0.500 per million output tokens. Its context window is 1.0M tokens.
- Input / 1M tokens
- $0.150
- Output / 1M tokens
- $0.500
- Cached input / 1M
- $0.020
- Context window
- 1.0M
On repeated prefixes
tokens
Who serves it cheapest
9 hosts serve Nemotron 3.5 Super VL. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| DarkbloomCheapestnvfp4 | $0.060 | $0.350 | 262K | - | 91.6% |
| Crusoebf16 | $0.100 | $0.400 | 1.0M | - | 99.2% |
| Io Netnvfp4 | $0.150 | $0.500 | 262K | - | 94.8% |
| Together | $0.150 | $0.500 | 262K | - | 99.9% |
| DeepInfrafp4 | $0.150 | $0.500 | 262K | - | 99.8% |
| CoreWeavenvfp4 | $0.150 | $0.500 | 1.0M | - | 99.7% |
| Venicefp4 | $0.200 | $0.500 | 262K | - | 99.6% |
| BaseTenfp4 | $0.200 | $0.500 | 1.0M | - | 100.0% |
| Nebiusbf16 | $0.300 | $0.900 | 1.0M | - | 94.9% |
The spread between Darkbloom and Nebius is 3.4× for identical weights. Quantization and context limits differ, so check both columns before switching.
Benchmarks
Independent scores published alongside the catalogue.
- Intelligence index
- 13.6
About 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...
Specifications
| Model ID | nvidia/nemotron-3.5-super-vl |
|---|---|
| Provider | NVIDIA |
| Context window | 1.0M tokens |
| Max output | 236K tokens |
| Input modalities | text, image, video |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | Yes - nvidia/NVIDIA-Nemotron-3.5-Super-VL |
| Released | October 15, 2026 |
Cheaper alternatives
Models that cost less than Nemotron 3.5 Super VL while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does NVIDIA: Nemotron 3.5 Super VL cost?
$0.150 per million input tokens and $0.500 per million output tokens. Cached input reads cost $0.020 per million tokens.
What is the context window of NVIDIA: Nemotron 3.5 Super VL?
1.0M tokens, with up to 236K tokens of output per request.
Which provider serves NVIDIA: Nemotron 3.5 Super VL cheapest?
Darkbloom at $0.060 per million input tokens - 3.4× cheaper than Nebius, the most expensive of the 9 hosts serving it.
Confirm against the source: NVIDIA official pricing.