Head to head

Llama 3.3 70B Instruct Turbo vs Inkling Small

On a blended workload of one million input tokens and three million output tokens, Inkling Small is line-ball with Llama 3.3 70B Instruct Turbo.

Llama 3.3 70B Instruct TurboInkling Small
Provider Together AI Together AI
Input / MTok $1.04 $0.5
Output / MTok $1.04 $1.2
Cache read / MTok
Context window 131,072 524,288
Blended 1M in + 3M out $4.16 $4.10
Status ga ga

Llama 3.3 70B Instruct Turbo detail   Inkling Small detail