Model family
gpt-oss Models
OpenAI gpt-oss models are open-weight reasoning models for local, self-hosted, and developer-controlled AI workflows.
Best for
Open weights
Use this family hub to compare gpt-oss variants for open weights workflows, then open the detail page for deeper deployment notes.
Local AI
Use this family hub to compare gpt-oss variants for local ai workflows, then open the detail page for deeper deployment notes.
Reasoning
Use this family hub to compare gpt-oss variants for reasoning workflows, then open the detail page for deeper deployment notes.
Source box
gpt-oss pages should cite the OpenAI model card paper and distinguish 120B/20B hardware requirements, active parameters, and runtime context limits.
Verified through: June 2026
Model licenses, context windows, release names, and provider terms can vary by checkpoint. Verify the exact model card before production or commercial use.
Variants
gpt-oss models grouped by workflow
Latest / flagship
Local-friendly
Compare
All gpt-oss models in the directory
| Model | Type | Best for | Local runner notes | License | Detail |
|---|---|---|---|---|---|
| gpt-oss-120b | Chat | Teams evaluating high-capacity local, self-hosted, or developer-controlled model deployments. | Best evaluated with the exact release, runtime support, and hardware profile available to your team. | Apache 2.0 | Open |
| gpt-oss-20b | Chat | Builders evaluating more accessible open-weight deployments for local apps, prototypes, and controlled workflows. | A smaller gpt-oss entry is worth evaluating for local workflows when compatible runtimes and quantized builds are available. | Apache 2.0 | Open |