Gemma 4 31B vs Nemotron 3.5 Super VL

Price, context window & benchmark comparison

Google

Gemma 4 31B

Google
$0.20 / $0.40
Input / Output · per 1M tokens
VS
NVIDIA

Nemotron 3.5 Super VL

NVIDIA
$0.15 / $0.47
Input / Output · per 1M tokens
Compare different models
Google
NVIDIA
Verdict: Nemotron 3.5 Super VL is 8% cheaper than Gemma 4 31B on a typical 3:1 input/output mix. Nemotron 3.5 Super VL scores higher on the Artificial Analysis Intelligence Index (13.6 vs 4.4). Nemotron 3.5 Super VL has the larger context window (1M vs 262K).
Gemma 4 31BNemotron 3.5 Super VL
Input price / 1M$0.20$0.15
Output price / 1M$0.40$0.47
Blended price (3:1)$0.25$0.23
Cached input / 1M—$0.02
Context window262K1M
Max output16K944K
Intelligence index4.413.6
Coding index43.4—
Providers—10
Best provider uptime (30m)—100.0%
Vision inputYesYes
ReasoningYesYes
Tool callingYesYes
Released2026-04-022026-10-15
Retirement——

Cost calculator

FAQ

Which is cheaper, Gemma 4 31B or Nemotron 3.5 Super VL?

Nemotron 3.5 Super VL is 8% cheaper than Gemma 4 31B on a typical 3:1 input/output mix.

Gemma 4 31B vs Nemotron 3.5 Super VL: which has a bigger context window?

Gemma 4 31B: 262,144 tokens. Nemotron 3.5 Super VL: 1,048,576 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Gemma 4 31B ≈ $600.00, Nemotron 3.5 Super VL ≈ $535.00.

More comparisons