Nemotron 3.5 Super VL pricing

Cheapest host: Darkbloom · checked Oct 26, 2026
Benchmarks and alternatives →
$0.06 / $0.35per 1M tokens in / out
$0.01cache read · −83%
$0.19per task at thinking?
#26on OpenRouter by tokens · 1.3T / week

Price sheetper 1M tokens

Input$0.06Darkbloom
Output$0.35
Cache read$0.01−83% vs input
Context1Mtokens
Free tieryesfree OpenRouter route

Where to buy8 providers · per 1M tokens

ProviderInputOutputContext
Darkbloom$0.06$0.35262K
Crusoe$0.10$0.40262K
DeepInfra$0.10$0.40—
CoreWeave$0.15$0.50—
Io Net$0.15$0.50262K
Together$0.15$0.50—
BaseTen$0.20$0.501M
Venice$0.25$1.25—

In NVIDIA's line-upper 1M in / out

NVIDIA Nemotron Nano 9B V2$0.04 / $0.16−47%
Nemotron 3 Nano 30B A3B$0.06 / $0.24−21%
Nemotron Nano 3 30B$0.06 / $0.24−21%
Nemotron 3.5 Super VL$0.06 / $0.35this model
NVIDIA Nemotron 3.5 Super VL 120B A12B NVFP4$0.08 / $0.45+30%
Nemotron 3.5 Content Safety$0.20 / $0.20+51%
NVIDIA Nemotron Nano 12B v2 VL$0.20 / $0.602.3×
<

Cheaper for the same workvs Nemotron 3.5 Super VL

MiMo v2.6 Pro thinkingOpen-28%score +75%$0.13
GPT-6.1 Terra high-27%score +66%$0.13
GPT-6.1 Sol low-29%score +59%$0.13
Claude Haiku 5.5 xhigh-33%score +56%$0.12
GPT-6 Luna max-63%score +44%$0.068

Pricing questions

How much does Nemotron 3.5 Super VL cost?›

$0.06 per 1M input tokens and $0.35 per 1M output tokens. Cached input is $0.01. One Intelligence Index task costs about $0.19 at the default effort.

Is Nemotron 3.5 Super VL free to use?›

Yes, with limits: free OpenRouter route. Free route; provider availability and account rate limits apply.

How much does prompt caching save?›

Cache reads cost $0.01 per 1M, 83% below the input price.

Is Nemotron 3.5 Super VL cheaper than Nemotron 3 Super?›

Yes: $0.06 / $0.35 against $0.085 / $0.40, 19% less per token.

What is a cheaper alternative to Nemotron 3.5 Super VL?›

MiMo v2.6 Pro at thinking effort costs -28% per task with a score +75% on Humanity's Last Exam.