gpt-oss-120b vs gpt-oss-20b

Price, context window & benchmark comparison

O

gpt-oss-120b

OpenAI
$0.15 / $0.60
Input / Output · per 1M tokens
VS
O

gpt-oss-20b

OpenAI
$0.018 / $0.09
Input / Output · per 1M tokens
Compare different models
O
O
Verdict: gpt-oss-20b is 7.3× cheaper than gpt-oss-120b on a typical 3:1 input/output mix. gpt-oss-120b scores higher on the Artificial Analysis Intelligence Index (11.6 vs 9).
gpt-oss-120bgpt-oss-20b
Input price / 1M$0.15$0.018
Output price / 1M$0.60$0.09
Blended price (3:1)$0.26$0.036
Cached input / 1M$0.075
Context window131K131K
Max output66K33K
Intelligence index11.69
Coding index30.420.7
Providers
Best provider uptime (30m)
Vision inputNoNo
ReasoningYesYes
Tool callingYesYes
Released2025-08-052025-08-05
Retirement

Cost calculator

FAQ

Which is cheaper, gpt-oss-120b or gpt-oss-20b?

gpt-oss-20b is 7.3× cheaper than gpt-oss-120b on a typical 3:1 input/output mix.

gpt-oss-120b vs gpt-oss-20b: which has a bigger context window?

gpt-oss-120b: 131,072 tokens. gpt-oss-20b: 131,072 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: gpt-oss-120b ≈ $600.00, gpt-oss-20b ≈ $81.00.

More comparisons