gpt-oss-120b vs gpt-oss-20b
gpt-oss-20b is cheaper on output tokens. Choose gpt-oss-120b or gpt-oss-20b based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | gpt-oss-120b | gpt-oss-20b |
|---|---|---|
| Provider | Amazon Bedrock | Amazon Bedrock |
| Input / 1M tokens | $0.15 | $0.07 |
| Output / 1M tokens | $0.60 | $0.30 |
| Context window | 128K | 128K |
| Parameters | 117B | 21B |
| Open weights | No | No |
| Released | Aug 2025 | Aug 2025 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.