nvidia
NVIDIA: Nemotron 3.5 Super VL (free)
nvidia/nemotron-3.5-super-vl:free
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
NVIDIA's Nemotron 3.5 Super VL, listed on OpenRouter as nvidia/nemotron-3.5-super-vl:free, is an open vision-language mixture-of-experts model with 120B total and 12B active parameters, per the vendor card. It accepts text, images, document pages, GUI screenshots, and video, and returns text. The card reports context up to 1M tokens, configurable reasoning modes, tool calling, and native speculative decoding. OpenRouter lists it as free to use. Vendor benchmarks cover reasoning, coding, and multimodal tasks; independent evaluation remains limited to OpenRouter's arena data.[1][2]
Strengths
- The card describes a hybrid Mamba-2 and attention mixture-of-experts backbone with a C-RADIO vision encoder, activating 12B of 120B parameters per token, with reported support for contexts up to 1M tokens.[2]
- The catalog lists tool calling, structured outputs, and a reasoning toggle among supported parameters, while the card describes configurable reasoning levels and native multi-token speculative decoding.[1][2]
- OpenRouter lists the model as free, and the card states the BF16 weights are released under OpenMDW-1.1 for commercial and non-commercial use.[1][2]
Limitations
- Evidence is mostly vendor-published plus the OpenRouter catalog; independent verification is limited to OpenRouter's design-arena results, which show mid-to-lower placements and low win rates across its listed categories.[1][2]
- The free OpenRouter listing does not document which card-described capabilities, such as the full 1M-token context, reasoning levels, or video limits, are actually enabled on that endpoint; validate against your workload.[1][2]
- Self-hosting guidance targets multi-GPU NVIDIA hardware (four H100 or two GB200), and the card itself calls for use-case-specific testing before deployment.[2]
Where to use it
- Prototyping multimodal assistants that read screenshots, document pages, or short video, a reasonable fit given the reported inputs, provided behavior is confirmed on the free endpoint.[1][2]
- Evaluating coding and tool-calling agents, since the card reports training on software-engineering data and tool use.[2]
- Fine-tuning or domain adaptation using the full-precision BF16 weights, which the card positions for customization and evaluation.[2]
Sources
- [1] OpenRouter catalog · NVIDIA: Nemotron 3.5 Super VL (free)Sources checked: Nov 13, 2026
- [2] Model documentation · NVIDIA: Nemotron 3.5 Super VL (free)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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:free
- Canonical ID
- nvidia/nemotron-3.5-super-vl-20261015
- Creator
- nvidia
- Added to OpenRouter
- 15.10.2026
- Context length
- 1,000,000
- Modality
- text+image+video->text
- Input modalities
- text, image, video
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0 / out $0
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | CC — below the B band | reasoning: optional · parameters: include_reasoning, reasoning |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | input: video |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 13.6 | CC — below the B band | 13.11.2026 |
| Design Arena | models · 3dwin rate 30.2% · rank 84 | 1,116Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 32.4% · rank 93 | 1,140Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 26.1% · rank 106 | 1,085Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · gamedevwin rate 27.1% · rank 106 | 1,078Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 33% · rank 82 | 1,154Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · websitewin rate 34.8% · rank 88 | 1,160Elo | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Nvidia | 1,000,000 | $0 | $0 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.