Migration assistant

Replacing Amazon Nova Pro?

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.

AB
Migrating from

Amazon Nova Pro

AWS Bedrock · Amazon Nova · Active
Input: $0.8/M Output: $3.2/M Context: 300K
View detail →
#1 RECOMMENDED

Amazon Nova Lite

AWS Bedrock · Amazon Nova
same provider; same family; 92% cheaper input; same context window; loses 1 capability
View full detail →
What changes if you switch
Field Amazon Nova Pro → Amazon Nova Lite Impact
Input price $0.8/M → $0.06/M Save 92%
Output price $3.2/M → $0.24/M Save 92%
Context window 300K tokens → 300K tokens Same capacity
Vision input ✓ supported → ✓ supported Preserved
Video input ✓ supported → ✓ supported Preserved
Function calling ✓ supported → ✓ supported Preserved
Batch API ✓ supported → ✗ not supported LOST — re-evaluate before switching
Fine-tuning ✓ supported → ✓ supported Preserved
Lifecycle Active → Active Same status
Other candidates
#2

Amazon Nova Premier

AWS Bedrock
same provider; same family; 212% more expensive input; 1M context (larger); loses 2 capabilities
Details →
Input price: +212% more expensiveOutput price: +291% more expensiveContext window: +233% largerBatch API: LOST — re-evaluate before switchingFine-tuning: LOST — re-evaluate before switching
#3

Gemini 2.5 Flash

Google Gemini
62% cheaper input; 1M context (larger); loses 1 capability
Details →
Input price: Save 62%Output price: Save 22%Context window: +250% largerFine-tuning: LOST — re-evaluate before switching
#4

Gemini 2.5 Flash-Lite

Google Gemini
88% cheaper input; 1M context (larger); loses 1 capability
Details →
Input price: Save 88%Output price: Save 88%Context window: +250% largerFine-tuning: LOST — re-evaluate before switching
#5

Amazon Nova Reel

AWS Bedrock
same provider; same family; loses 3 capabilities
Details →
Function calling: LOST — re-evaluate before switchingBatch API: LOST — re-evaluate before switchingFine-tuning: LOST — re-evaluate before switching
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.