Migration assistant

Replacing Claude Opus 4.1 (deprecated)?

Deprecated — migration recommended. 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 Opus 4.1 (deprecated)

Anthropic · Claude Opus 4 · Deprecated
Input: $15/M Output: $75/M Context: 200K
View detail →
#1 RECOMMENDED

Claude Opus 4

Anthropic · Claude Opus 4
same provider; same family; same context window
View full detail →
What changes if you switch
Field Claude Opus 4.1 (deprecated) Claude Opus 4 Impact
Input price $15/M $15/M Same price
Output price $75/M $75/M Same price
Context window 200K tokens 200K tokens Same capacity
Vision input ✓ supported ✓ supported Preserved
Function calling ✓ supported ✓ supported Preserved
Prompt caching ✓ supported ✓ supported Preserved
Lifecycle Deprecated Active Generally available
Other candidates
#2

Claude Sonnet 4

Anthropic
same provider; 80% cheaper input; same context window
Details →
Input price: Save 80%Output price: Save 80%Lifecycle: Generally available
#3

Gemini 2.5 Flash

Google Gemini
98% cheaper input; 1M context (larger)
Details →
Input price: Save 98%Output price: Save 97%Context window: +424% largerLifecycle: Generally available
#4

Gemini 2.5 Flash-Lite

Google Gemini
99% cheaper input; 1M context (larger)
Details →
Input price: Save 99%Output price: Save 99%Context window: +424% largerLifecycle: Generally available
#5

Gemini 2.5 Pro

Google Gemini
92% cheaper input; 1M context (larger)
Details →
Input price: Save 92%Output price: Save 87%Context window: +424% largerLifecycle: Generally available
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.