Claude 3 Haiku vs Claude Haiku 5.5

Wins 0 of 3 benchmarks
$0.047 / task
Wins 0 of 3 benchmarks
3 Haiku—
Haiku 5.533.8
3 Haiku—
Haiku 5.515.2
3 Haiku—
Haiku 5.528.6

Specs

Spec3 HaikuHaiku 5.5
Input, per 1M—$0.10
Output, per 1M—$0.50
Cost per task?—$0.047
Speed, tok/s—174
Context—1M
WeightsNot verifiedClosed
ReleasedMar 2024Oct 2026
See images✓✓
Read PDFs?Partial
Hear audio——
Watch video——
Call tools✓✓
Force a tool call?Partial
Return strict JSON✓✓
Search the web?✓
Run code?✓
Use a computer??

What breaks when you switch

3 Haiku → 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 → 3 Haiku
Context: not verified