Skip to content
SOLVENCY

Head to head

o3-pro vs GPT-4.1

o3-pro is legacy; GPT-4.1 is legacy.

For tasks, about a month.

Verdict · stale basis

GPT-4.1 costs $1.37 per solved task against o3-pro at $8.48 — ▼ 6.2x cheaper. Over 200 tasks that is $1.4k a month.

On output token price alone GPT-4.1 looks 10x cheaper. The ranking holds, but the margin changes.

Verified pricing, pass rate and cost per solved task for o3-pro and GPT-4.1
Figureo3-proGPT-4.1
Input $/Mtok$20$2
Output $/Mtok$80$8
Cached input $/Mtokmissing$0.5
Pass rate85%52%
Cost per solved task$8.48stale$1.37stale
Cost per month$1.7k$275

Cost per month against tasks per month · drag the marker

Monthly cost against tasks per monthLog-log lines for GPT-4.1 (stale, $1.37 per solved task), o3-pro (stale, $8.48 per solved task) from 10 to 100,000 tasks a month. Marker at 200 tasks.101001k10k100k$10$100$1k$10k$100k$1MTASKS / MONTH (log) →200 tasksGPT-4.1 · STALE · $1.37 per solved task$275o3-pro · STALE · $8.48 per solved task$1.7k— GPT-4.1 · STALE— o3-pro · 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