Head to head
Claude Opus 4 vs Claude Opus 4.5
Claude Opus 4: retiredClaude Opus 4.5: legacyheavy tier
No verdict
One cost is measured by its benchmark and the other is modelled by Solvency. The two bases are never ranked against each other, so no verdict is given here.
Source: Aider polyglot benchmark · verified 2026-08-21 · prices from each provider's pricing page
Input $/M tokens
lower is better
Output $/M tokens
lower is better
Cost per solved task
different bases — not comparable
| Claude Opus 4 | Claude Opus 4.5 | |
|---|---|---|
| Input $/Mtok | $15 | $5 |
| Output $/Mtok | $75 | $25 |
| Cached input $/Mtok | $1.5 | $0.5 |
| Pass rate | 72% | 46% |
| Pass rate source | Aider | SEAL |
| Cost basis | modelled | modelled |
| Cost per solved task | $18.75 | $9.81 |
verified 2026-08-21 · heavy task tier; measured rows ignore the tier· Methodology· Claude Opus 4· Claude Opus 4.5