Head to head

Inkling vs o3-mini

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

Inklingo3-mini
Provider Together AI OpenAI
Input / MTok $1 $1.1
Output / MTok $4.05 $4.4
Cache read / MTok $0.55
Context window 524,288 200,000
Blended 1M in + 3M out $13.15 $14.30
Status ga ga

Inkling detail   o3-mini detail