gpt-oss-20b vs Nemotron 3.5 Lightning

Price, context window & benchmark comparison

O

gpt-oss-20b

OpenAI
$0.018 / $0.09
Input / Output · per 1M tokens
VS
N

Nemotron 3.5 Lightning

NVIDIA
$0.08 / $0.20
Input / Output · per 1M tokens
Compare different models
O
N
Verdict: gpt-oss-20b is 3.1× cheaper than Nemotron 3.5 Lightning on a typical 3:1 input/output mix. Nemotron 3.5 Lightning scores higher on the Artificial Analysis Intelligence Index (12.9 vs 9). Nemotron 3.5 Lightning has the larger context window (262K vs 131K).
gpt-oss-20bNemotron 3.5 Lightning
Input price / 1M$0.018$0.08
Output price / 1M$0.09$0.20
Blended price (3:1)$0.036$0.11
Cached input / 1M$0.04
Context window131K262K
Max output33K131K
Intelligence index912.9
Coding index20.726.8
Providers4
Best provider uptime (30m)100.0%
Vision inputNoNo
ReasoningYesYes
Tool callingYesYes
Released2025-08-052026-08-11
Retirement

Cost calculator

FAQ

Which is cheaper, gpt-oss-20b or Nemotron 3.5 Lightning?

gpt-oss-20b is 3.1× cheaper than Nemotron 3.5 Lightning on a typical 3:1 input/output mix.

gpt-oss-20b vs Nemotron 3.5 Lightning: which has a bigger context window?

gpt-oss-20b: 131,072 tokens. Nemotron 3.5 Lightning: 262,144 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: gpt-oss-20b ≈ $81.00, Nemotron 3.5 Lightning ≈ $260.00.

More comparisons