gpt-oss-20b
OpenAI · Released Aug 2025
An open-weight 20-billion-parameter model from OpenAI using Mixture-of-Experts architecture with roughly 3.6 billion active parameters per forward pass.
- Strengths
- Runs efficiently on consumer hardware while maintaining reasoning capability across its full 131k token context window.
- Best for
- Local deployment, edge inference, and workloads where model weight size is a constraint but reasoning depth is needed.
- Limitations
- Smaller active parameter count makes it less capable than gpt-oss-120b for complex reasoning or multi-step agentic tasks.
Input / 1M
$0.03
Output / 1M
$0.13
Cached input / 1M
$0.03
Context window
131K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in — out —
- 90d
- in increased 3.4% out decreased 7.1%
- 1y
- in increased 3.4% out decreased 7.1%
- Since launch
- in increased 3.4% out decreased 7.1%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 1 Aug 2026 | $0.03 | $0.13 | $0.03 | Imported from OpenRouter | openrouter.ai |
| 31 Jul 2026 | $0.03 | $0.14 | — | Imported from OpenRouter | openrouter.ai |
| 29 Jul 2026 | $0.03 | $0.13 | $0.03 | Imported from OpenRouter | openrouter.ai |
| 26 Jul 2026 | $0.03 | $0.14 | — | Imported from OpenRouter | openrouter.ai |
| 25 Jul 2026 | $0.03 | $0.13 | $0.03 | Imported from OpenRouter | openrouter.ai |
| 24 Jul 2026 | $0.029 | $0.14 | — | Imported from OpenRouter | openrouter.ai |
| 15 Jul 2026 | $0.03 | $0.13 | $0.03 | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.029 | $0.14 | — | Imported from OpenRouter | openrouter.ai |