Nemotron 3.5 Super VL vs Ternary Bonsai 2 27B

Price, context window & benchmark comparison

NVIDIA

Nemotron 3.5 Super VL

NVIDIA
$0.15 / $0.47
Input / Output · per 1M tokens
VS
Prism Ml

Ternary Bonsai 2 27B

Prism Ml
$0.075 / $0.50
Input / Output · per 1M tokens
Compare different models
NVIDIA
Prism Ml
Verdict: Ternary Bonsai 2 27B is 21% cheaper than Nemotron 3.5 Super VL on a typical 3:1 input/output mix. Nemotron 3.5 Super VL has the larger context window (1M vs 262K).
Nemotron 3.5 Super VLTernary Bonsai 2 27B
Input price / 1M$0.15$0.075
Output price / 1M$0.47$0.50
Blended price (3:1)$0.23$0.18
Cached input / 1M$0.02$0.0375
Context window1M262K
Max output944K33K
Intelligence index13.6—
Coding index——
Providers10—
Best provider uptime (30m)100.0%—
Vision inputYesYes
ReasoningYesYes
Tool callingYesYes
Released2026-10-152026-09-18
Retirement——

Cost calculator

FAQ

Which is cheaper, Nemotron 3.5 Super VL or Ternary Bonsai 2 27B?

Ternary Bonsai 2 27B is 21% cheaper than Nemotron 3.5 Super VL on a typical 3:1 input/output mix.

Nemotron 3.5 Super VL vs Ternary Bonsai 2 27B: which has a bigger context window?

Nemotron 3.5 Super VL: 1,048,576 tokens. Ternary Bonsai 2 27B: 262,144 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Nemotron 3.5 Super VL ≈ $535.00, Ternary Bonsai 2 27B ≈ $400.00.

More comparisons