gpt-oss-safeguard-20b pricing & benchmarks
gpt-oss-safeguard-20b is available from OpenAI at $0.075 per million input tokens and $0.300 per million output tokens ($0.131 blended at 3:1). It accepts up to 131,072 tokens of context. 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…
Pricing
Per million tokens · OpenRouter
Input$0.075
Output$0.300
Blended (3:1)$0.131
Specification
openai/gpt-oss-safeguard-20b
Context window131K
Max output66K
ReleasedOct 2025
LicenceOpen weights
Modalitiesin:text, out:text
No independently-run benchmark scores are published for gpt-oss-safeguard-20b yet. We show nothing rather than reprinting an unverified figure.
Compare gpt-oss-safeguard-20b
gpt-oss-safeguard-20b vs Qwen3.8 Max
gpt-oss-safeguard-20b vs DeepSeek V4 Flash 0731
gpt-oss-safeguard-20b vs Claude Opus 5
gpt-oss-safeguard-20b vs Gemini 3.6 Flash
gpt-oss-safeguard-20b vs Kimi K3
gpt-oss-safeguard-20b vs Grok 4.5
gpt-oss-safeguard-20b vs Claude Sonnet 5
gpt-oss-safeguard-20b vs GLM 5.2
FAQ
How much does gpt-oss-safeguard-20b cost?
gpt-oss-safeguard-20b costs $0.075 per million input tokens and $0.300 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.131 per million tokens.
What is gpt-oss-safeguard-20b's context window?
gpt-oss-safeguard-20b accepts up to 131,072 tokens of context, and can generate up to 65,536 output tokens.