Head to head

Ternary Bonsai 27B vs GPT-OSS 20B

On a blended workload of one million input tokens and three million output tokens, Ternary Bonsai 27B is 650000.0× cheaper than GPT-OSS 20B.

Ternary Bonsai 27BGPT-OSS 20B
Provider Together AI Together AI
Input / MTok $0 $0.05
Output / MTok $0 $0.2
Cache read / MTok
Context window 262,144 128,000
Blended 1M in + 3M out $0.00 $0.65
Status ga ga

Ternary Bonsai 27B detail   GPT-OSS 20B detail