Nemotron 3 Ultra vs Nemotron 3.5 Super VL

Price, context window & benchmark comparison

Nemotron 3 Ultra

NVIDIA

$0.60 / $2.40

Input / Output · per 1M tokens

Nemotron 3.5 Super VL

NVIDIA

$0.15 / $0.47

Input / Output · per 1M tokens

Compare different models

Verdict: Nemotron 3.5 Super VL is 4.6× cheaper than Nemotron 3 Ultra on a typical 3:1 input/output mix. Nemotron 3.5 Super VL scores higher on the Artificial Analysis Intelligence Index (13.6 vs 11.8). Nemotron 3.5 Super VL has the larger context window (1M vs 262K).

	Nemotron 3 Ultra	Nemotron 3.5 Super VL
Input price / 1M	$0.60	$0.15
Output price / 1M	$2.40	$0.47
Blended price (3:1)	$1.05	$0.23
Cached input / 1M	$0.12	$0.02
Context window	262K	1M
Max output	183K	944K
Intelligence index	11.8	13.6
Coding index	49.3	—
Providers	—	10
Best provider uptime (30m)	—	100.0%
Vision input	No	Yes
Reasoning	Yes	Yes
Tool calling	Yes	Yes
Released	2026-06-04	2026-10-15
Retirement	—	—

Cost calculator

Input tokens / requestOutput tokens / requestRequests / day

FAQ

Which is cheaper, Nemotron 3 Ultra or Nemotron 3.5 Super VL?

Nemotron 3.5 Super VL is 4.6× cheaper than Nemotron 3 Ultra on a typical 3:1 input/output mix.

Nemotron 3 Ultra vs Nemotron 3.5 Super VL: which has a bigger context window?

Nemotron 3 Ultra: 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: Nemotron 3 Ultra ≈ $2,400, Nemotron 3.5 Super VL ≈ $535.00.

More comparisons