gpt-oss-safeguard-20b
OpenAI · Released Oct 2025
gpt-oss-safeguard-20b is OpenAI's open-source focused safety model with a 131k token context window, designed to provide content filtering and safety guardrails for applications.
- Strengths
- Delivers straightforward safety classification and content moderation without the overhead of larger reasoning models.
- Best for
- Content filtering, policy enforcement, and safety validation in systems that need reliable guardrails without full reasoning capabilities.
- Limitations
- Smaller context window than current-generation OpenAI models and older release date position it as a specialized safety component rather than a general-purpose reasoning model.
Input / 1M
$0.075
Output / 1M
$0.3
Cached input / 1M
$0.0375
Context window
131K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in — out —
- 90d
- in — out —
- 1y
- in decreased 0.0% out decreased 0.0%
- Since launch
- in decreased 0.0% out decreased 0.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 19 Jun 2026 | $0.075 | $0.3 | $0.0375 | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.075 | $0.3 | $0.037 | Imported from OpenRouter | openrouter.ai |