gpt-oss-safeguard-20b

OpenAI · Mid

Compare →

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...

Input / 1M

$0.075

Output / 1M

$0.3

Cached input / 1M

$0.037

Context window

131K

Where it sits

40th-cheapest mid model

by blended $/Mtok among 262 listed mid models

77% below the mid median

blended $/Mtok across 262 mid models

Output costs 4× input

$0.075 in / $0.3 out per 1M

Cached input saves 51%

$0.037 vs $0.075 per 1M fresh

Held flat since launch (Jun 2026)

no blended price change recorded

Computed live from current prices and this model's history — not hand-written, so it stays accurate as prices move.

Price history

Only one price on record so far — the history chart appears once a price changes.

Snapshots

Effective Input Output Cached in Note Source
11 Jun 2026 $0.075 $0.3 $0.037 Imported from OpenRouter openrouter.ai

More from OpenAI