Nemotron 3.5 Super VL vs Voxtral Small 24B 2507

Price, context window & benchmark comparison

NVIDIA

Nemotron 3.5 Super VL

NVIDIA
$0.15 / $0.47
Input / Output · per 1M tokens
VS
Mistral AI

Voxtral Small 24B 2507

Mistral AI
$0.10 / $0.30
Input / Output · per 1M tokens
Compare different models
NVIDIA
Mistral AI
Verdict: Voxtral Small 24B 2507 is 35% 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 33K).
Nemotron 3.5 Super VLVoxtral Small 24B 2507
Input price / 1M$0.15$0.10
Output price / 1M$0.47$0.30
Blended price (3:1)$0.23$0.15
Cached input / 1M$0.02$0.01
Context window1M33K
Max output944K26K
Intelligence index13.6—
Coding index——
Providers10—
Best provider uptime (30m)100.0%—
Vision inputYesNo
ReasoningYesNo
Tool callingYesYes
Released2026-10-152025-10-30
Retirement——

Cost calculator

FAQ

Which is cheaper, Nemotron 3.5 Super VL or Voxtral Small 24B 2507?

Voxtral Small 24B 2507 is 35% cheaper than Nemotron 3.5 Super VL on a typical 3:1 input/output mix.

Nemotron 3.5 Super VL vs Voxtral Small 24B 2507: which has a bigger context window?

Nemotron 3.5 Super VL: 1,048,576 tokens. Voxtral Small 24B 2507: 32,768 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Nemotron 3.5 Super VL ≈ $535.00, Voxtral Small 24B 2507 ≈ $350.00.

More comparisons