Head to head

GPT-5.4 mini vs Inkling

On a blended workload of one million input tokens and three million output tokens, Inkling is 1.1× cheaper than GPT-5.4 mini.

GPT-5.4 miniInkling
Provider OpenAI Together AI
Input / MTok $0.75 $1
Output / MTok $4.5 $4.05
Cache read / MTok $0.075
Context window 524,288
Blended 1M in + 3M out $14.25 $13.15
Status ga ga

GPT-5.4 mini detail   Inkling detail