gpt-oss-20b
OpenAI · Released Aug 2025
An open-weight 20-billion-parameter model from OpenAI, released after the larger gpt-oss-120b.
- Strengths
- The smaller parameter count makes it more compute-efficient than its 120B predecessor, reducing latency and resource requirements while maintaining reasonable capability for general tasks.
- Best for
- Deployments where inference speed and lower computational overhead matter more than maximum reasoning capability, or where the model is run locally or on cost-constrained infrastructure.
- Limitations
- The 20B parameter size limits reasoning depth and accuracy on complex problems compared to larger models in OpenAI's lineup; the 131k context window is smaller than the 400k offered by GPT-5-series models.
Input / 1M
$0.03
Output / 1M
$0.14
Cached input / 1M
—
Context window
131K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in increased 3.4% out decreased 0.0%
- 90d
- in increased 3.4% out decreased 0.0%
- 1y
- in increased 3.4% out decreased 0.0%
- Since launch
- in increased 3.4% out decreased 0.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 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 |