// NVIDIA
Nemotron 3.5 Super VL
A NVIDIA model. 5 prices across 5 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.
- Official in/out per 1M
- —
- Lowest (Crusoe)
- $0.1 / $0.4
- Context
- 262K
- AA index
- 26.5
Prices checked 2026-10-22Official sources linked on every rowNo estimates
01Specs at a glance
Official values first; gaps filled from OpenRouter’s API where the vendor page is silent.
| Vendor | NVIDIA |
|---|---|
| Context window | 262K (262,144 tokens) |
| Max output | 236K |
| Input | Text · Image · Video |
| Output | Text |
| Tool calling / JSON | Yes / Yes |
| Weights & licence | Open weights · Open weights – licence not checked · Hugging Face |
| Released | Oct 15, 2026 (OpenRouter listing date) |
| Model IDs | nvidia/nemotron-3.5-super-vl |
02Prices on 5 channels
Per 1M tokens, in the currency each source publishes (1 USD = 6.7 CNY for the blended column). Sorted: official first, then cheapest.
| Channel | Source | Input | Output | Cache hit | Blended $ | Context | Notes |
|---|---|---|---|---|---|---|---|
| Crusoe · bf16 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.1 | $0.4 | $0.08 | 0.175 | 262K | Crusoe price as listed on OpenRouter (pass-through; quantization=bf16); not checked against Crusoe's own page |
| DeepInfra · fp4 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.15 | $0.5 | $0.02 | 0.237 | 262K | DeepInfra price as listed on OpenRouter (pass-through; quantization=fp4); not checked against DeepInfra's own page |
| Together · unknown Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.15 | $0.5 | $0.02 | 0.237 | 262K | Together price as listed on OpenRouter (pass-through; quantization=unknown); not checked against Together's own page |
| coreweave · nvfp4 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.15 | $0.5 | $0.02 | 0.237 | 1.05M | CoreWeave price as listed on OpenRouter (pass-through; quantization=nvfp4); not checked against CoreWeave's own page |
| venice · fp4 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.25 | $1.25 | $0.125 | 0.5 | 262K | Venice price as listed on OpenRouter (pass-through; quantization=fp4); not checked against Venice's own page |
“Official” = vendor pricing page; “Platform” = the platform’s own pricing page; “OpenRouter” = price listed on OpenRouter, not checked on the platform’s site. Click a source tag to open the original page.
03Where you can use it
Derived only from the price sources above. Country restrictions are set by each vendor – check their terms before you sign up.
- Via OpenRouter / provider listed there
Crusoe · DeepInfra · Together · coreweave · venice - Self-host the open weights
GPU / VRAM sizing and build plans→ - Free option
Nemotron 3.5 Super VL (OpenRouter)→
04Performance
Speed and AA index from Artificial Analysis public leaderboards (not our own tests); benchmark scores from our benchmark library, best result per benchmark.
- AA indexNemotron 3.5 Super VL
- 26.5
- Output speed (median)
- 429 tok/s
- Time to first token
- 0.78s
- AA index per $ (blended)
- 151.38
05Price changes we recorded
All price changes →From our daily re-checks of the sources above.
- 2026-10-20 · DeepInfra · cache read0.08 → 0.02 USD (-75%)
- 2026-10-20 · DeepInfra · output0.4 → 0.5 USD (+25%)
- 2026-10-20 · DeepInfra · input0.1 → 0.15 USD (+50%)
- 2026-10-19 · venice · new listing
- 2026-10-19 · coreweave · new listing
- 2026-10-19 · Together · new listing
- 2026-10-19 · DeepInfra · new listing
- 2026-10-19 · Crusoe · new listing
06More from NVIDIA
FAQ
How much does the Nemotron 3.5 Super VL API cost?
There is no official pay-as-you-go price in our data. The lowest listed price is $0.1 / $0.4 on Crusoe.
What is the context window of Nemotron 3.5 Super VL?
262K tokens of context, up to 236K output tokens. Platforms may cap it lower – see the table.
Is Nemotron 3.5 Super VL open source?
Yes, the weights are published on Hugging Face (nvidia/NVIDIA-Nemotron-3.5-Super-VL). Licence: Open weights – licence not checked.