Head to head

Nemotron 3 Ultra 550B-A55B vs Inkling

On a blended workload of one million input tokens and three million output tokens, Nemotron 3 Ultra 550B-A55B is 1.2× cheaper than Inkling.

Nemotron 3 Ultra 550B-A55BInkling
Provider Together AI Together AI
Input / MTok $0.6 $1
Output / MTok $3.6 $4.05
Cache read / MTok
Context window 512,300 524,288
Blended 1M in + 3M out $11.40 $13.15
Status ga ga

Nemotron 3 Ultra 550B-A55B detail   Inkling detail