Migration assistant

Replacing Claude Haiku 3.5?

Ranked replacement candidates, each shown with exactly what changes if you switch. Same-provider matches surface first because switching cost is lower; capability regressions are flagged in red.

AN
Migrating from

Claude Haiku 3.5

Anthropic · Claude Haiku 3 · Active
Input: $0.8/M Output: $4/M Context: 200K
View detail →
#1 RECOMMENDED

Claude Haiku 4.5

Anthropic · Claude Haiku 4
same provider; 25% more expensive input; same context window
View full detail →
What changes if you switch
Field Claude Haiku 3.5 → Claude Haiku 4.5 Impact
Input price $0.8/M → $1/M +25% more expensive
Output price $4/M → $5/M +25% more expensive
Context window 200K tokens → 200K tokens Same capacity
Function calling ✓ supported → ✓ supported Preserved
Prompt caching ✓ supported → ✓ supported Preserved
Lifecycle Active → Active Same status
Other candidates
#2

Claude Opus 4

Anthropic
same provider; 1775% more expensive input; same context window
Details →
Input price: +1775% more expensiveOutput price: +1775% more expensive
#3

Claude Opus 4.1

Anthropic
same provider; 1775% more expensive input; same context window
Details →
Input price: +1775% more expensiveOutput price: +1775% more expensive
#4

Claude Opus 4.5

Anthropic
same provider; 525% more expensive input; same context window
Details →
Input price: +525% more expensiveOutput price: +525% more expensive
#5

Claude Opus 4.6

Anthropic
same provider; 525% more expensive input; 1M context (larger)
Details →
Input price: +525% more expensiveOutput price: +525% more expensiveContext window: +400% larger
Methodology

How candidates are ranked

Candidates are ranked by how much of the source model's profile each one preserves — weighing switching cost (same provider or model family surface first), capability parity (what you keep versus what you'd lose), context window, and pricing direction. A candidate that is itself deprecated is pushed down the list; one that's already retired is never recommended.

Ranking is purely algorithmic — no editorial weighting, no paid placement. Every value is pulled from each provider's own documentation; click any model name to see the source-linked detail.