`gpt-oss-safeguard-120b` and `gpt-oss-safeguard-20b` are safety reasoning models built-upon gpt-oss. With these models, you can classify text content based on safety policies that you provide and perform a suite of foundational safety tasks. These models are intended for safety use cases. For other applications, we recommend using gpt-oss models.
function_calling| Model | Context | Max out |
|---|---|---|
| gpt-oss-120b | 131K | 131K |
| gpt-oss-20b | 131K | 131K |
| gpt-oss-safeguard-20b | 131K | — |
/v1/models/huggingface/openai/gpt-oss-safeguard-20b