Head to head
GPT-4.1 vs Claude Opus 4
GPT-4.1 is legacy; Claude Opus 4 is retired.
For tasks, about a month.
Verdict · stale basis
GPT-4.1 costs $1.37 per solved task against
Claude Opus 4 at $8.33 — ▼ 6.1x cheaper.
Over 200 tasks that is $1.4k a month.
On output token price alone GPT-4.1 looks 9.4x cheaper. The ranking holds, but the margin changes.
Verified pricing, pass rate and cost per solved task for GPT-4.1 and Claude Opus 4| Figure | GPT-4.1 | Claude Opus 4 |
|---|
| Input $/Mtok | $2 | $15 |
|---|
| Output $/Mtok | $8 | $75 |
|---|
| Cached input $/Mtok | $0.5 | $1.5 |
|---|
| Pass rate | 52% | 72% |
|---|
| Cost per solved task | $1.37stale | $8.33stale |
|---|
| Cost per month | $275 | $1.7k |
|---|
Cost per month against tasks per month · drag the marker
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