gpt-oss-safeguard-20b

OpenAI released 2025-10-29

$0.131 per million tokens, balanced

No independent quality score.

No benchmark we track has measured this model. That is not the same as measuring it and finding it wanting — we simply cannot rank it, so we do not.

Every price dimension

Input$0.075/M
Output$0.300/M
Cached input$0.037/M

Independent scores

No independent benchmark has measured this model.

Capability

Context window131K
Max output66K
Input modestext
Tool useyes
Reasoningalways on

Provenance

Price sourceopenrouter.ai
Fetched2026-08-24
Quality dataunrated

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...

Markdown for LLMs