gpt-oss-120b vs gpt-oss-20b
Benchmarks, API pricing and specs, head to head. Data updated 2026-06-10.
gpt-oss-120b
OpenAI · Aug 2025
OpenAI's open-weights MoE reasoning model under Apache 2.0 — near o4-mini quality, runnable on a single 80GB GPU.
gpt-oss-20b
OpenAI · Aug 2025
The small gpt-oss variant that runs on a 16GB consumer GPU or laptop — local reasoning for everyone, Apache 2.0 licensed.
The verdict
These two models don't yet share verified results on the benchmarks we track, so judge them on specs, pricing and intended use. gpt-oss-20b is about 2.3x cheaper per blended million tokens (3:1 input:output mix).
Specs & pricing
| gpt-oss-120b | gpt-oss-20b | |
|---|---|---|
| modhub Index | — | — |
| Input price / 1M | $0.1 | $0.05 |
| Output price / 1M | $0.5 | $0.2 |
| Context window | 131K | 131K |
| Max output | 131K | 131K |
| Open weights | yes (Apache 2.0) | yes (Apache 2.0) |
| Reasoning model | yes | yes |
| Multimodal input | text | text |
| Knowledge cutoff | Jun 2024 | Jun 2024 |
| Released | Aug 2025 | Aug 2025 |
| Example monthly cost* | $1.75 | $0.8 |
* 10M input + 1.5M output tokens per month at list prices, no caching. Green = better value on that row.
Frequently asked questions
- Which is better, gpt-oss-120b or gpt-oss-20b?
- These two models don't yet share verified results on the benchmarks we track, so judge them on specs, pricing and intended use. gpt-oss-20b is about 2.3x cheaper per blended million tokens (3:1 input:output mix).
- Which is cheaper, gpt-oss-120b or gpt-oss-20b?
- gpt-oss-120b costs $0.1/$0.5 per million input/output tokens, while gpt-oss-20b costs $0.05/$0.2. For a typical workload of 10M input and 1.5M output tokens per month, that's $1.75 versus $0.8.
- Which model is better for coding, gpt-oss-120b or gpt-oss-20b?
- We don't yet track SWE-bench Verified results for both models; check their individual pages for coding-related scores.