Migration assistant

Replacing gpt-oss-120b?

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.

OP
Migrating from

gpt-oss-120b

OpenAI · gpt-oss · Active
Input: $0.04/M Output: $0.18/M Context: 131K
View detail →
#1 RECOMMENDED

GPT-4.1 Mini

OpenAI · GPT-4.1
same provider; 926% more expensive input; 1M context (larger)
View full detail →
What changes if you switch
Field gpt-oss-120b → GPT-4.1 Mini Impact
Input price $0.04/M → $0.4/M +926% more expensive
Output price $0.18/M → $1.6/M +789% more expensive
Context window 131K tokens → 1M tokens +699% larger
Function calling ✓ supported → ✓ supported Preserved
Structured output (JSON) ✓ supported → ✓ supported Preserved
Fine-tuning ✓ supported → ✓ supported Preserved
Lifecycle Active → Active Same status
Other candidates
#2

GPT-4o Mini

OpenAI
same provider; 285% more expensive input
Details →
Input price: +285% more expensiveOutput price: +233% more expensiveContext window: 2% smaller
#3

GPT-5 Nano

OpenAI
same provider; 28% more expensive input; 400K context (larger); loses 1 capability
Details →
Input price: +28% more expensiveOutput price: +122% more expensiveContext window: +205% largerFine-tuning: LOST — re-evaluate before switching
#4

GPT-4.1 Nano

OpenAI
same provider; 156% more expensive input; 1M context (larger); loses 1 capability
Details →
Input price: +156% more expensiveOutput price: +122% more expensiveContext window: +699% largerFine-tuning: LOST — re-evaluate before switching
#5

GPT-5 Mini

OpenAI
same provider; 541% more expensive input; 400K context (larger); loses 1 capability
Details →
Input price: +541% more expensiveOutput price: +1011% more expensiveContext window: +205% largerFine-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.