Safety model for policy screening, moderation, and risk-aware routing workflows
Details
| Field | Value |
|---|---|
| id | openai/gpt-oss-safeguard-20b |
| family | gpt-oss |
| modality | text->text |
| context_length | 131072 |
| max_output_tokens | 65536 |
| release_date | 2025-10-29 |
| is_open_weights | no |
| supports_tool_call | yes |
| supports_reasoning | yes |
| supports_structured_output | yes |
| supports_attachment | no |
| input_modalities | text |
| output_modalities | text |