Skip to content
  • Status
  • Announcements
  • Docs
  • Support
  • About
  • Partners
  • Enterprise
  • Careers
  • Pricing
  • Privacy
  • Terms
  •  
    • © 2025 OpenRouter, Inc

    OpenAI: gpt-oss-safeguard-20b

    openai/gpt-oss-safeguard-20b

    Created Oct 29, 2025131,072 context
    $0.075/M input tokens$0.30/M output tokens

    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 & safety labeling.

    Learn more about this model in OpenAI's gpt-oss-safeguard user guide.

    Recent activity on gpt-oss-safeguard-20b

    Total usage per day on OpenRouter

    Prompt
    340M
    Reasoning
    64.5M
    Completion
    22.7M

    Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.