GPT OSS Safeguard 20BOpen weights
OpenAI · released 2025-10-29
No price from the maker itself is on record for GPT OSS Safeguard 20B. The lowest of 10 providers is Amazon Bedrock: $0.07 per 1M input tokens and $0.2 per 1M output tokens (as of 2026-11-12). Context window: 131K tokens, up to 65.5K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 Amazon BedrockLowestopenai. | $0.07 | $0.2 | — | Lowest | Official docs |
EEden AIamazon/ | $0.07 | $0.2 | — | Official docs | |
EEden AIamazon/ | $0.07 | $0.2 | — | Official docs | |
MMerge Gatewayopenai/ | $0.07 | $0.2 | $0 | Official docs | |
 Vercel AI Gatewayopenai/ | $0.07 | $0.2 | — | Official docs | |
LLowRouterauto/ | $0.08 | $0.24 | — | Official docs | |
EEden AIgroq/ | $0.075 | $0.3 | $0.0375 | Official docs | |
 GroqBetaopenai/ | $0.075 | $0.3 | $0.0375 | Beta | Official docs |
KKilo Gatewayopenai/ | $0.075 | $0.3 | $0.0375 | Official docs | |
NNanoGPTopenai/ | $0.075 | $0.3 | — | Official docs | |
 OpenRouteropenai/ | $0.075 | $0.3 | $0.0375 | Official docs | |
 AI/ML APIopenai/ | $0.07935 | $0.3174 | $0.039675 | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Safety model for policy screening, moderation, and risk-aware routing workflows
Description from models.dev.
Specs
- Type
- Text
- Context
- 131K
- Max output
- 65.5K
- Input
- Text
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- —
- Open weights
- Yes
- Released
- 2025-10-29
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.