Claude Haiku 4.5 vs Claude Haiku 5.5

Wins 0 of 4 benchmarks
$0.047 / task
Wins 3 of 4 benchmarks
Haiku 4.54.2
Haiku 5.533.8
Haiku 4.50
Haiku 5.515.2
Haiku 4.53.2
Haiku 5.528.6
Haiku 4.555.1
Haiku 5.5—

Specs

SpecHaiku 4.5Haiku 5.5
Input, per 1M$1$0.10
Output, per 1M$5$0.50
Cost per task?—$0.047
Speed, tok/s86174
Context200K1M
WeightsClosedClosed
ReleasedOct 2025Oct 2026
See images✓✓
Read PDFsPartialPartial
Hear audio——
Watch video——
Call tools✓✓
Force a tool callPartialPartial
Return strict JSON✓✓
Search the web?✓
Run code?✓
Use a computer??

What breaks when you switch

Haiku 4.5 → Haiku 5.5
Remove sampling parameters›

Unsupported sampling values, any top_k or combined temperature and top_p return HTTP 400; omit all three and use prompting.

Replace manual thinking budgets›

Manual thinking with budget_tokens returns HTTP 400; replace the old thinking configuration.

No assistant prefill›

A final assistant prefill returns HTTP 400 even with thinking off; end messages with a user turn.

Replace old computer tool · Claude API / Google Cloud›

computer_20250124 returns HTTP 400 on the Claude API and Google Cloud; use computer_toolset_20260801 there.

Keep conversations append-only›

Replaying thinking after earlier history changes returns HTTP 400, with older accounts checked only when the binding field is set; keep history append-only.

Bedrock needs another computer version · Bedrock›

Bedrock does not accept computer_20250124; use computer_20251124 with the computer-use-2025-11-24 beta header.

Haiku 5.5 → Haiku 4.5
Context: 1M → 200K