Head to head

o3-mini vs Inkling

On a blended workload of one million input tokens and three million output tokens, Inkling is 1.1× cheaper than o3-mini.

o3-miniInkling
Provider OpenAI Together AI
Input / MTok $1.1 $1
Output / MTok $4.4 $4.05
Cache read / MTok $0.55
Context window 200,000 524,288
Blended 1M in + 3M out $14.30 $13.15
Status ga ga

o3-mini detail   Inkling detail