Head to head
vs For light moderate heavy
Verdict · measured basis
gpt-oss-safeguard-20b costs $0.0002 per solved task against
gpt-oss-20b at $0.0003 — ▼ 1.4x cheaper .
Over 200 tasks that is $0.02 a month.
On output token price alone gpt-oss-20b looks 2.3x cheaper. The ranking reverses once you divide by pass rate — the cheaper tokens do not win the task.
Copy link Save scenario Export compare table Planned
Verified pricing, pass rate and cost per solved task for gpt-oss-safeguard-20b and gpt-oss-20b Figure gpt-oss-safeguard-20b gpt-oss-20b Input $/Mtok $0.075 $0.03 Output $/Mtok $0.3 $0.13 Cached input $/Mtok $0.037 $0.03 Pass rate 97% 94% Cost per solved task $0.0002 measured $0.0003 measured Cost per month $0.04 $0.05
Cost per month against tasks per month · drag the marker
Monthly cost against tasks per month Log-log lines for gpt-oss-safeguard-20b (measured, $0.0002 per solved task), gpt-oss-20b (measured, $0.0003 per solved task) from 10 to 100,000 tasks a month. Marker at 200 tasks. 10 100 1k 10k 100k $0.01 $0.1 $1 $10 TASKS / MONTH (log) → 200 tasks gpt-oss-safeguard-20b · MEASURED · $0.0002 per solved task $0.04 gpt-oss-safeguard-20b MEASURED gpt-oss-20b · MEASURED · $0.0003 per solved task $0.05 gpt-oss-20b MEASURED Monthly cost against tasks per month Log-log lines for gpt-oss-safeguard-20b (measured, $0.0002 per solved task), gpt-oss-20b (measured, $0.0003 per solved task) from 10 to 100,000 tasks a month. Marker at 200 tasks. 10 100 1k 10k 100k $0.01 $0.1 $1 $10 TASKS / MONTH (log) → 200 tasks gpt-oss-safeguard-20b · MEASURED · $0.0002 per solved task $0.04 gpt-oss-20b · MEASURED · $0.0003 per solved task $0.05 — gpt-oss-safeguard-20b · MEASURED — gpt-oss-20b · MEASURED Solid measured · dashed modeled · dotted stale. The gap is the verdict.
Solvency Bench (solvency.dev) — first-party measurement · verified 2026-08-26 · prices from each provider's pricing page; measured rows ignore the tier · Methodology · All models at these settings