Nemotron 3.5 Lightning vs Summarize

Price, context window & benchmark comparison

NVIDIA

Nemotron 3.5 Lightning

NVIDIA
$0.07 / $0.20
Input / Output · per 1M tokens
VS
Scaledown

Summarize

Scaledown
$0.04 / Free
Input / Output · per 1M tokens
Compare different models
NVIDIA
Scaledown
Verdict: Summarize is 3.4× cheaper than Nemotron 3.5 Lightning on a typical 3:1 input/output mix. Summarize has the larger context window (1M vs 262K).
Nemotron 3.5 LightningSummarize
Input price / 1M$0.07$0.04
Output price / 1M$0.20Free
Blended price (3:1)$0.10$0.03
Cached input / 1M$0.04—
Context window262K1M
Max output236K4K
Intelligence index5.5—
Coding index26.8—
Providers5—
Best provider uptime (30m)100.0%—
Vision inputNoYes
ReasoningYesNo
Tool callingYesNo
Released2026-08-112026-10-13
Retirement——

Cost calculator

FAQ

Which is cheaper, Nemotron 3.5 Lightning or Summarize?

Summarize is 3.4× cheaper than Nemotron 3.5 Lightning on a typical 3:1 input/output mix.

Nemotron 3.5 Lightning vs Summarize: which has a bigger context window?

Nemotron 3.5 Lightning: 262,144 tokens. Summarize: 1,000,000 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Nemotron 3.5 Lightning ≈ $240.00, Summarize ≈ $80.00.

More comparisons