Head to head

Llama 3.1 8B Instant vs Ternary Bonsai 27B

On a blended workload of one million input tokens and three million output tokens, Ternary Bonsai 27B is 290000.0× cheaper than Llama 3.1 8B Instant.

Llama 3.1 8B InstantTernary Bonsai 27B
Provider Groq Together AI
Input / MTok $0.05 $0
Output / MTok $0.08 $0
Cache read / MTok
Context window 131,072 262,144
Blended 1M in + 3M out $0.29 $0.00
Status ga ga

Llama 3.1 8B Instant detail   Ternary Bonsai 27B detail