Head to head
GPT-5.6 LunavsMistral Small 3.2 24B
For tasks, about a month.
Verdict · measured basis
Mistral Small 3.2 24B costs $0.0001 per solved task against
GPT-5.6 Luna at $2.65 — ▼ 52562x cheaper.
Over 200 tasks that is $530 a month.
On output token price alone Mistral Small 3.2 24B looks 6.0x cheaper. The ranking holds, but the margin changes.
Verified pricing, pass rate and cost per solved task for GPT-5.6 Luna and Mistral Small 3.2 24B| Figure | GPT-5.6 Luna | Mistral Small 3.2 24B |
|---|
| Input $/Mtok | $0.2 | $0.075 |
|---|
| Output $/Mtok | $1.2 | $0.2 |
|---|
| Cached input $/Mtok | $0.02 | $0.075 |
|---|
| Pass rate | 57% | 69% |
|---|
| Cost per solved task | $2.65measured | $0.0001measured |
|---|
| Cost per month | $530 | $0.01 |
|---|
Cost per month against tasks per month · drag the marker
Solid measured · dashed modeled · dotted stale. The gap is the verdict.
Source: Artificial Analysis (artificialanalysis.ai) · verified 2026-08-21 · prices from each provider's pricing page; measured rows ignore the tier · Methodology · All models at these settings