Hugging Face model card
Fields: tags, gated, license, summary, base model, library name, pipeline tag, base model relation
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.
- Context
- 131K
- Max output
- 66K
- Input
- $0.075
- Output
- $0.30
Recommended use cases
Strengths in this dataset
- 131,072-token context window
- text input
- 11 supported API parameters listed
Limits and caveats
- Provider behavior and pricing can change; verify the linked sources before production use.
Capability
Model-native facts
Model- Reasoning
- Supported
- Open weights
- Supported
Provider endpoint facts
Provider endpoint- Tool calling
- Supported
- Structured output
- Supported
- Streaming
- Unknown
- Prompt cache
- Supported
- Batch
- Unknown
- Fine-tuning
- Unknown
gpt-oss-safeguard-20b Provider pricing
Provider endpoint: openai/gpt-oss-safeguard-20b
- Input
- $0.075 per 1M tokens
- Output
- $0.30 per 1M tokens
- Cached input
- $0.0375 per 1M tokens
- Image output
- Unknown per 1M tokens
Sources and verification
Official model documentation
Fields: model identity
OpenRouter Models API
Fields: identity, description, modalities, context window, maximum output, pricing, supported parameters
Frequently asked questions
Answers are generated from the same sourced model and provider facts shown above.
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.
Model specifications and prices may vary by provider and change over time. AIToolly displays sources and verification dates so users can confirm critical details before production use.