OPOpenAI/ GPT
gpt-oss-safeguard-20b
openai/gpt-oss-safeguard-20b
gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...
Model information
Released
2025-10-29
Context window
131K
Max output
66K
Model parameters
22B
Weights
Open
Modalities
Input
Text
Output
Text
Identity
- Version
- gpt-oss-safeguard-20b
- License
- Apache-2.0
Resources
Capabilities
Open weightReasoningStructuredTemperatureTool call
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | openai/gpt-oss-safeguard-20b | openai_chat | 131K | 66K | ReasoningTool callStructuredTemperature | Reasoning required, Hugging Face: openai/gpt-oss-safeguard-20b | input $0.075/M · output $0.3/M cache read $0.038/M | Yes | ||
| NanoGPT | openai/gpt-oss-safeguard-20b | openai_chat | 131K | 66K | Reasoning | - | input $0.075/M · output $0.3/M | Yes | ||
| Groq | openai/gpt-oss-safeguard-20b | openai_chat | 131K | 66K | ReasoningTool callStructuredTemperature | - | input $0.075/M · output $0.3/M | Yes | ||
| Kilo Gateway | openai/gpt-oss-safeguard-20b | openai_chat | 131K | 66K | ReasoningTool callStructuredTemperature | - | input $0.075/M · output $0.3/M cache read $0.038/M | Yes | ||
| Vercel AI Gateway | openai/gpt-oss-safeguard-20b | openai_chat | 131K | 66K | ReasoningTool callTemperature | - | input $0.075/M · output $0.3/M cache read $0.037/M | Yes | ||
| OpenAI | gpt-oss-safeguard-20b | custom | 131K | 66K | - | - | - | Yes |