Nemotron 3.5 Super VL pricing & benchmarks
Nemotron 3.5 Super VL is available from NVIDIA at $0.150 per million input tokens and $0.500 per million output tokens ($0.237 blended at 3:1). It accepts up to 1,048,576 tokens of context. NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...
Pricing
Per million tokens · OpenRouter
Input$0.150
Output$0.500
Blended (3:1)$0.237
Specification
nvidia/nemotron-3.5-super-vl
Context window1.0M
Max output236K
ReleasedOct 2026
LicenceOpen weights
Modalitiesin:text, in:image, in:video, out:text
No independently-run benchmark scores are published for Nemotron 3.5 Super VL yet. We show nothing rather than reprinting an unverified figure.
Where to run Nemotron 3.5 Super VL
7 hosts · 2.9× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| Crusoe ⚠ 262K context, not 1.0M |
$0.175 | $0.100 / $0.400 | 262K | bf16 | 97.0% |
| Io Net ⚠ 262K context, not 1.0M |
$0.237 | $0.150 / $0.500 | 262K | nvfp4 | 95.1% |
| Together ⚠ 262K context, not 1.0M |
$0.237 | $0.150 / $0.500 | 262K | — | 99.9% |
| DeepInfra ⚠ 262K context, not 1.0M |
$0.237 | $0.150 / $0.500 | 262K | fp4 | 99.2% |
| CoreWeave | $0.237 | $0.150 / $0.500 | 1.0M | nvfp4 | 90.5% |
| BaseTen | $0.275 | $0.200 / $0.500 | 1.0M | fp4 | 100.0% |
| Venice ⚠ 262K context, not 1.0M |
$0.500 | $0.250 / $1.25 | 262K | fp4 | 96.4% |
Host prices and uptime from OpenRouter, synced 2026-10-22. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare Nemotron 3.5 Super VL
Nemotron 3.5 Super VL vs Gemini 3.7 Flash
Nemotron 3.5 Super VL vs Grok 4.6
Nemotron 3.5 Super VL vs DeepSeek V4 Flash 0731
Nemotron 3.5 Super VL vs Inkling Small
Nemotron 3.5 Super VL vs Qwen3.7 Flash
Nemotron 3.5 Super VL vs Claude Opus 5
Nemotron 3.5 Super VL vs Gemini 3.6 Flash
Nemotron 3.5 Super VL vs Gemini 3.5 Flash Lite
FAQ
How much does Nemotron 3.5 Super VL cost?
Nemotron 3.5 Super VL costs $0.150 per million input tokens and $0.500 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.237 per million tokens.
What is Nemotron 3.5 Super VL's context window?
Nemotron 3.5 Super VL accepts up to 1,048,576 tokens of context, and can generate up to 235,929 output tokens.