GPT-OSS Safeguard 120B served through Amazon Bedrock with support for AWS zero-data-retention mode.
AWS reported status=available and allowed_modes containing none on 2026-07-31. The serving account must set data_retention_mode=none.
Modalities
In / out price
$0.15 / $0.60
per 1M
Context
128K
Max output
16K
Released
Oct 29, 2025
Updated
Jul 31, 2026
Providers
1 routeThe same model can have different pricing and privacy guarantees depending on who serves it. The model's headline privacy uses the strongest available route below.
| Provider | Privacy | Input / 1M | Output / 1M | Cache read / 1M | Context | Max output | Uptime | Latency | Throughput |
|---|---|---|---|---|---|---|---|---|---|
| Private | $0.15 | $0.60 | — | 128K | 16K | — | — | — |
Privacy
2 / 3Private routing
Private tier
- Anonymous
- Private
- E2EE
Prompt and response content is not retained after the request. Request content is visible to the inference runtime while it is being processed.
Features
No feature flags reported for this route.