Pricingby IbisWays to buy 6
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
bf16 · cached $0.08 | $0.1 | $0.4 | $0.1 / $0.4Cheapest | $0.08 | Cheapest |
nvfp4 · cached $0.02 | $0.15 | $0.5 | $0.15 / $0.5+36% vs cheapest | $0.02 | +36% vs cheapest |
Default region · cached $0.02 | $0.15 | $0.5 | $0.15 / $0.5+36% vs cheapest | $0.02 | +36% vs cheapest |
fp4 · cached $0.04 | $0.2 | $0.5 | $0.2 / $0.5+57% vs cheapest | $0.04 | +57% vs cheapest |
fp4 · cached $0.1 | $0.2 | $1 | $0.2 / $1+129% vs cheapest | $0.1 | +129% vs cheapest |
fp4 · cached $0.125 | $0.25 | $1.25 | $0.25 / $1.25+186% vs cheapest | $0.125 | +186% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $18.00 direct.
Vercel AI Gateway$18.00+0%
Eden AI$18.99+5.5%
OpenRouter$18.99+5.5%
Cloudflare AI GatewayNot offeredNot offered
HeliconeNot offeredNot offered
Kong AI GatewayNot offeredNot offered
LiteLLMNot offeredNot offered
Martian GatewayNot offeredNot offered
Neon AI GatewayNot offeredNot offered
PortkeyNot offeredNot offered
RequestyNot offeredNot offered
TrueFoundry AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
NVIDIA · 262K | $0.025 | $0.12 | $0.025 / $0.12 | $0.049 | 262K | on Darkbloom (int4) | · |
NVIDIA · 262K | $0.4 | $1.76 | $0.4 / $1.76 | $0.74 | 262K | on DeepInfra (fp4-flex) | · |
NVIDIA · 131K | $0.2 | $0.2 | $0.2 / $0.2 | $0.2 | 131K | on DeepInfra (bf16) | · |
NVIDIA · 262K | $0.085 | $0.4 | $0.085 / $0.4 | $0.164 | 262K | on DeepInfra (bf16) | · |
Anthropic · 1M | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1M | Lab list price | · |
DeepSeek · 1MCheapest: $0.113 on Decart (fp4) | $0.15 | $0.6 | $0.15 / $0.6 | $0.262 | 1M | $0.113 on Decart (fp4) | · |
DeepSeek · 1M | $0.045 | $0.3 | $0.045 / $0.3 | $0.109 | 1M | on InferenceNet (fp8) | · |
OpenAI · 1.05MCheapest: $0.1 on OpenAI (flex) | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1.05M | $0.1 on OpenAI (flex) | · |
About Nemotron 3.5 Super VL
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.
Takes text, image, video in and returns text. First listed Oct 16, 2026. Up to 236K output tokens. Blended price $0.175 per 1M tokens at 3 input to 1 output. Model id nemotron-3-5-super-vl.
Price history
No list-price history: this model is sold by hosts rather than its lab.
Across fru.devCompany profile
Questions
How much does Nemotron 3.5 Super VL cost?
$0.1 per million input tokens and $0.4 per million output tokens, with cached input at $0.08.
What is the context window of Nemotron 3.5 Super VL?
1M tokens, with up to 236K tokens of output.
Where is Nemotron 3.5 Super VL cheapest?
Of 6 routes tracked, Crusoe is cheapest at $0.1 input and $0.4 output per million tokens.
Has Nemotron 3.5 Super VL's price changed?
Yes. The output price went from $0.75 to $0.5, first seen Oct 17, 2026.