Model Directory
    OpenAI

    gpt-oss-safeguard-20b

    Context 131KIn $0.075/MOut $0.3/M

    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...

    Specifications

    ProviderOpenAI
    Context window131,072 tokens (131K)
    Input price$0.075 / 1M tokens
    Output price$0.3 / 1M tokens
    Input modalitiestext
    Output modalitiestext
    Model IDopenai/gpt-oss-safeguard-20b

    Pricing is per 1M tokens, indicative pricing via OpenRouter (updated 2026-08-22); a provider's own list price may differ.

    Frequently asked questions

    How much does gpt-oss-safeguard-20b cost?

    Indicative pricing (via OpenRouter, updated 2026-08-22) is $0.075 per 1M input tokens and $0.3 per 1M output tokens. A provider's own list price may differ. On Vincony, gpt-oss-safeguard-20b is available on credit-based pricing alongside 800+ other models.

    What is gpt-oss-safeguard-20b's context window?

    gpt-oss-safeguard-20b supports a context window of up to 131,072 tokens (131K), which is how much text it can consider at once.

    Who makes gpt-oss-safeguard-20b?

    gpt-oss-safeguard-20b is built by OpenAI. You can access it — and compare it against other providers' models — through Vincony's multi-model platform.

    How do I use gpt-oss-safeguard-20b?

    You can use gpt-oss-safeguard-20b directly through OpenAI, or via Vincony, which aggregates 800+ models (including gpt-oss-safeguard-20b) into one interface with side-by-side comparison and credit-based pricing.