Skip to content
SOLVENCY

Head to head

o3 vs GPT-4.1

o3 is legacy; GPT-4.1 is legacy.

For tasks, about a month.

Verdict · stale basis

o3 costs $0.89 per solved task against GPT-4.1 at $1.37 — ▼ 1.6x cheaper. Over 200 tasks that is $98 a month.

On output token price alone o3 looks 1.0x cheaper. The ranking holds, but the margin changes.

Verified pricing, pass rate and cost per solved task for o3 and GPT-4.1
Figureo3GPT-4.1
Input $/Mtok$2$2
Output $/Mtok$8$8
Cached input $/Mtok$0.5$0.5
Pass rate81%52%
Cost per solved task$0.89stale$1.37stale
Cost per month$177$275

Cost per month against tasks per month · drag the marker

Monthly cost against tasks per monthLog-log lines for o3 (stale, $0.89 per solved task), GPT-4.1 (stale, $1.37 per solved task) from 10 to 100,000 tasks a month. Marker at 200 tasks.101001k10k100k$10$100$1k$10k$100kTASKS / MONTH (log) →200 taskso3 · STALE · $0.89 per solved task$177GPT-4.1 · STALE · $1.37 per solved task$275— o3 · STALE— GPT-4.1 · STALE

Solid measured · dashed modelled · dotted stale. The gap is the verdict.

Source: Aider polyglot benchmark · verified 2026-08-21 · prices from each provider's pricing page; measured rows ignore the tier · Methodology · All models at these settings