Nemotron 3.5 Super VL
Nemotron 3.5 Super VLAlternatives?
CheaperMiMo v2.6 ProthinkingOpen×2.5-29%$0.13Memory (4-bit): 75 GB → 615 GB+4
BetterGPT-6 Lunahigh+46%-85%$0.029Function calling only with none · Chat Completions+3OpenMiMo v2.6 Flashthinking+14%-67%$0.062Memory (4-bit): 75 GB → 186 GB+4CheaperGPT-6.1 Sollow×2.4-31%$0.13Remove unsupported parameters+5
CheaperClaude Haiku 5.5xhigh×2.1-34%$0.12Remove sampling parameters+5MiMo v2.6 ProthinkingOpen×2.5-29%$0.13Memory (4-bit): 75 GB → 615 GB+4GPT-6.1 Sollow×2.4-31%$0.13Remove unsupported parameters+5Claude Haiku 5.5xhigh×2.1-34%$0.12Remove sampling parameters+5GPT-5.6 Lunaxhigh+95%-55%$0.085GPT-6 Lunamax+84%-64%$0.068Function calling only with none · Chat Completions+3GPT-6 Lunahigh+46%-85%$0.029Function calling only with none · Chat Completions+3GPT-5.6 Lunahigh+57%-77%$0.044Claude Haiku 5.5medium+22%-75%$0.047Remove sampling parameters+5GPT-6.1 Sollow×2.4-31%$0.13Remove unsupported parameters+5GPT-6 Sollow+54%-29%$0.13MiMo v2.6 FlashthinkingOpen+14%-67%$0.062Memory (4-bit): 75 GB → 186 GB+4
Qwen3.8 FlashthinkingOpensame+98%$0.37Context: 1M → 262K+7TInkling SmallthinkingOpen-22%-52%$0.089Context: 1M → 256K+2
Solar Open2 250BOpen-46%——Memory (4-bit): 75 GB → 150 GB+1Qwen3.8 27BxhighOpen-49%+435%$1.01Context: 1M → 262K+5Nemotron 3.5 Bolt 74B-A9BOpen-59%——Context: 1M → 256KNemotron 3 UltrathinkingOpen-70%+207%$0.58Memory (4-bit): 75 GB → 336 GB+1Nemotron 3 Super 120B A12BOpen-70%+771%$1.64No image inputNemotron Cascade 2 30B A3BOpen-95%——No image inputNemotron 3.5 LightningthinkingOpen-100%-58%$0.079No image inputNemotron 3 Nano Omni 30B A3B ReasoningOpen-100%—$0 / $0Context: 1M → 256KNVIDIA Nemotron 3 Nano 4BOpen-100%——Context: 1M → 262K+1Nemotron 3 Nano 30B A3Bnon-thinkingOpen-100%—$0.06 / $0.24Context: 1M → 131K+1All NVIDIA models →Run it yourself
estimateBenchmarks
in Chat & KnowledgeFAQ
How much does Nemotron 3.5 Super VL cost?›
$0.10 per 1M input tokens and $0.40 per 1M output tokens (cheapest host: DeepInfra). A typical benchmark task costs about $0.19 at default effort.
Is Nemotron 3.5 Super VL free to use?›
There is no free API; the cheapest paid price is $0.10 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Nemotron 3.5 Super VL, and what is it best at?›
#76 of 334 in Chat & Knowledge, #75 of 132 in Coding, #68 of 133 in Agents & Tool Use, #69 of 133 in Vision & Documents. Strongest at: Reasoning.
Is Nemotron 3.5 Super VL better than Mistral Large 4?›
On CritPt (physics), Nemotron 3.5 Super VL scores 10.6 vs 10.6 — about the same. It is 83% cheaper per task.
How can I use Nemotron 3.5 Super VL?›
Through the API of BaseTen, CoreWeave, Crusoe, DeepInfra, Together and 1 more.
What is the context window of Nemotron 3.5 Super VL?›
1M tokens.
When was Nemotron 3.5 Super VL released? Is there a newer version?›
Released 2026-10-15. It is the current version in its line.
Is Nemotron 3.5 Super VL open source?›
Yes, the weights are open (openmdw-1.1 licence).
Can I run Nemotron 3.5 Super VL locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Nemotron 3.5 Super VL read images?›
It accepts text and images, video as input.
What is Nemotron 3.5 Super VL?›
Nemotron 3.5 Super VL is an open-weights language model from NVIDIA, released Oct 2026, the successor to Nemotron 3 Super.
What are the best alternatives to Nemotron 3.5 Super VL?›
MiMo v2.6 Pro (cheaper), GPT-6 Luna (better), MiMo v2.6 Flash (open weights).