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...
The figures
- Made by
- OpenAI
- Model ID
- openai/gpt-oss-safeguard-20b
- Input
- $0.075 per million tokens
- Output
- $0.3 per million tokens
- Context window
- 131K tokens
- Longest answer
- 66K tokens
- Takes in
- text
- Gives back
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Reads images
- No
- Open weights
- Yes
- Released
- 29 Oct 2025
Read on 3 Oct 2026.