gpt-oss-safeguard-20b
Open safety-reasoning model that applies your own written policy.
gpt-oss-safeguard-20b is an open-weight safety reasoning model from OpenAI built on gpt-oss-20b. Instead of a fixed taxonomy it reasons over a policy you supply at inference time, for content classification, LLM filtering and trust & safety labelling.
- Provider
- OpenAI
- Type
- Safety classifier
- Released
- Oct 29, 2025
- Context window
- 131K tokens
- Max output
- 66K tokens
- Price
- $0.075 input / $0.30 output per 1M tokens
- Input
- text
- Output
- text
- Open weights
- Yes
- License
- Apache 2.0
Best for
- Enterprise
- Extraction & classification
- Reasoning
Strengths
- Bring-your-own policy
- Explains its decisions
- Apache 2.0
More from OpenAI
- GPT-6 Astra — OpenAI. OpenAI’s flagship for deep research, science and end-to-end engineering.
- GPT-6.1 Sol — OpenAI. Mid-tier GPT-6 model with excellent cost per task for agentic coding.
- GPT-6 Luna — OpenAI. Fast, cost-efficient GPT-6 tier for chat, classification and light agents.
- GPT-5.6 Terra — OpenAI. Balanced GPT-5.6 model for everyday coding and reasoning.
- gpt-oss-120b — OpenAI. OpenAI’s Apache-2.0 open-weight reasoning model; runs on a single 80GB GPU.
- gpt-oss-20b — OpenAI. Compact open-weight reasoning model that runs on consumer hardware.
- GPT-5.4 Image 2 — OpenAI. OpenAI’s native image generation and editing model.
- text-embedding-3-large — OpenAI. OpenAI’s most capable embedding; the default in countless RAG stacks.