openai

GPT OSS Safeguard 20B

gpt-oss-safeguard

Safety model for policy screening, moderation, and risk-aware routing workflows

ReasoningTool CallingOpen Weights

Context Window

131K

Max Output

131K

Temperature

Yes

Open Weights

Yes

Knowledge Cutoff

N/A

Released

2025-10-29

Last Updated

2025-10-29

Modalities

Input:Text
→
Output:Text

Available Providers (7)

ProviderInput /1MOutput /1MCache Read /1MCache Write /1MReasoningStatus
Merge GatewayMerge GatewayRp 1.272Rp 3.633GratisGratis✓—
Vercel AI GatewayVercel AI GatewayRp 1.272Rp 3.633——effort—
OpenRouterOpenRouterRp 1.363Rp 5.449Rp 682—effort—
Kilo GatewayKilo GatewayRp 1.272Rp 3.633——effort—
AI/ML APIAI/ML APIRp 1.442Rp 5.765Rp 721—effort—
GroqGroqRp 1.363Rp 5.449Rp 682—effort—
NanoGPTNanoGPTRp 1.363Rp 5.449——effort—