Head to head
MiniMax M3vsgpt-oss-20b
For tasks, about a month.
Verdict · measured basis
gpt-oss-20b costs $0.0003 per solved task against
MiniMax M3 at $0.02 — ▼ 78x cheaper.
Over 200 tasks that is $4 a month.
On output token price alone gpt-oss-20b looks 9.2x cheaper. The ranking holds, but the margin changes.
Verified pricing, pass rate and cost per solved task for MiniMax M3 and gpt-oss-20b| Figure | MiniMax M3 | gpt-oss-20b |
|---|
| Input $/Mtok | $0.3 | $0.03 |
|---|
| Output $/Mtok | $1.2 | $0.13 |
|---|
| Cached input $/Mtok | $0.06 | $0.03 |
|---|
| Pass rate | 47% | 94% |
|---|
| Cost per solved task | $0.02measured | $0.0003measured |
|---|
| Cost per month | $4 | $0.05 |
|---|
Cost per month against tasks per month · drag the marker
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