Claude Haiku 4.5 vs Claude Haiku 5.5
Reading a 26.2K-token pull request costs $0.0262 on Claude Haiku 4.5, 10× the $0.0026 it costs on Claude Haiku 5.5. Both are Claude Haiku models, so the difference is one version of the same line against another.
Side by side
| Figure | Claude Haiku 4.5 | Claude Haiku 5.5 |
|---|---|---|
| Price tier | Mid-range | Economy |
| Bugs caughtshare of known bugs | – | 64% |
| False alarmsper clean PR | – | 1.4 |
| Cost per reviewmeasured | – | $0.0038 |
| Cost per bug caught | – | $0.0064 |
| Exact linecatches on the expected lines | – | 82% |
| Review timemean | – | 15s |
| Typical review calllist price | $0.0383 | $0.0038 (better) |
| Input / 1M tokens | $1.00 | $0.10 (better) |
| Output / 1M tokens | $5.00 | $0.50 (better) |
| Context window | 200K | 1M |
Not benchmarked yet
Claude Haiku 4.5 isn't benchmarked yet, so this page compares list prices only. Measured bugs caught, false alarms and a bug-by-bug comparison appear here once both have results.
See measured models