NVIDIA Nemotron 3.5 Super VL
NVIDIA Nemotron 3.5 Super VL is a vision-language model for reasoning, coding, tool use, and document understanding.
text + image + video → text · made by NVIDIA
Free
Offered at no charge, which is not the same as cheap: a free lane carries a rate limit and can be withdrawn. The prices above are what you pay when it is not available to you.
- OpenRouter
Sold by 21 ways
| Seller | Lane | Rate |
|---|---|---|
| OpenRouter 12 ways | $0.15per Mtok in$0.5per Mtok out$0.02per Mtok cached | |
| OpenRouter aggregator | free | $0per Mtok in$0per Mtok outopenrouter.ai · read 2026-10-31 |
| OpenRouter aggregator | darkbloom/nvfp4 | $0.06per Mtok in$0.35per Mtok out$0.01per Mtok cachedopenrouter.ai · read 2026-10-24 |
| OpenRouter aggregator | crusoe/bf16 | $0.1per Mtok in$0.4per Mtok out$0.08per Mtok cachedopenrouter.ai · read 2026-10-17 |
| OpenRouter aggregator | standard | $0.15per Mtok in$0.5per Mtok out$0.02per Mtok cachedopenrouter.ai · read 2026-10-20 |
| OpenRouter aggregator | coreweave/nvfp4 | $0.15per Mtok in$0.5per Mtok out$0.02per Mtok cachedopenrouter.ai · read 2026-10-17 |
| OpenRouter aggregator | deepinfra/fp4 | $0.15per Mtok in$0.5per Mtok out$0.02per Mtok cachedopenrouter.ai · read 2026-10-20 |
| OpenRouter aggregator | io-net/nvfp4 | $0.15per Mtok in$0.5per Mtok out$0.02per Mtok cachedopenrouter.ai · read 2026-10-22 |
| OpenRouter aggregator | primeintellect/nvfp4 | $0.15per Mtok in$0.5per Mtok out$0.02per Mtok cachedopenrouter.ai · read 2026-10-31 |
| OpenRouter aggregator | together | $0.15per Mtok in$0.5per Mtok out$0.02per Mtok cachedopenrouter.ai · read 2026-10-17 |
| OpenRouter aggregator | baseten/fp4 | $0.2per Mtok in$0.5per Mtok out$0.04per Mtok cachedopenrouter.ai · read 2026-10-21 |
| OpenRouter aggregator | venice/fp4 | $0.2per Mtok in$0.5per Mtok out$0.04per Mtok cachedopenrouter.ai · read 2026-10-28 |
| OpenRouter aggregator | nebius/bf16 | $0.3per Mtok in$0.9per Mtok out$0.06per Mtok cachedopenrouter.ai · read 2026-10-29 |
| kilo 0 ways | $0.1per Mtok in$0.4per Mtok out$0.08per Mtok cached | |
| kilo aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.4per Mtok out$0.08per Mtok cachedmodels.dev · read 2026-10-16 |
| DeepInfra aggregator | standard | $0.15per Mtok in$0.5per Mtok outapi.deepinfra.com · read 2026-10-20 |
| Nous Research aggregator | standard | $0.15per Mtok in$0.5per Mtok out$0.02per Mtok cachedinference-api.nousresearch.com · read 2026-10-29 |
| Together AI aggregator | standard | $0.15per Mtok in$0.5per Mtok out$0.02per Mtok cachedraw.githubusercontent.com · read 2026-10-31 |
| nano-gpt 0 ways | $0.15per Mtok in$0.5per Mtok out$0.02per Mtok cached | |
| nano-gpt aggregatornot on the seller's list today | standard | $0.15per Mtok in$0.5per Mtok out$0.02per Mtok cachedmodels.dev · read 2026-10-16 |
| wandb aggregator | standard | $0.15per Mtok in$0.75per Mtok out$0.02per Mtok cachedmodels.dev · read 2026-10-16 |
| Vercel AI Gateway aggregator | standard | $0.2per Mtok in$0.5per Mtok out$0.04per Mtok cachedai-gateway.vercel.sh · read 2026-10-17 |
| DigitalOcean aggregator | standard | $0.3per Mtok in$0.65per Mtok out$0.06per Mtok cachedmodels.dev · read 2026-10-31 |
| Nebius Token Factory aggregator | standard | $0.3per Mtok in$0.9per Mtok outtokenfactory.nebius.com · read 2026-10-17 |
Measured 6 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 73rdof 86 | Artificial Analysis · Intelligence Index | Artificial Analysis Intelligence Index | 14 |
| 101stof 150 | Design Arena · 3d (models) | Elo | 1119 |
| 110thof 169 | Design Arena · website (models) | Elo | 1168 |
| 111thof 163 | Design Arena · codecategories (models) | Elo | 1151 |
| 113thof 157 | Design Arena · uicomponent (models) | Elo | 1133 |
| 120thof 162 | Design Arena · gamedev (models) | Elo | 1106 |
About
NVIDIA Nemotron 3.5 Super VL — a text model from NVIDIA, sold by 8 companies from $0.15 in and $0.5 out per million tokens, placed 110th of 169 on Design Arena · website (models).
It takes text, images and video and returns text, with a context window of 1,048,576 tokens. It was published in October 2026. Its sellers say it can reason step by step and call a tool. The catalogue files it under ocr. Eight companies sell it. The cheapest is $0.15 in and $0.5 out per million tokens at DeepInfra. Beside the standard rate there are regional and separately routed lanes. It has been measured on 6 boards, and stands best at 110th of 169 on Design Arena · website (models).
Every current figure
- Maker
- NVIDIA
- Register
- model
- Takes
- text + image + video
- Returns
- text
- Context
- 1,048,576 tokens
- Published
- October 2026
- Sellers
- 8
- Maker's own price
- not read
- Price
- $0.15 in and $0.5 out per million tokens — DeepInfra
- Boards
- 6
- Best place
- 110th of 169 — Design Arena · website (models)
Known as 2 names
nvidia/NVIDIA-Nemotron-3.5-Super-VLnvidia/Nemotron-3.5-Super-VL