Head to head

GPT-OSS 20B vs Ministral 3 8B

On a blended workload of one million input tokens and three million output tokens, Ministral 3 8B is 1.1× cheaper than GPT-OSS 20B.

GPT-OSS 20BMinistral 3 8B
Provider Together AI Mistral
Input / MTok $0.05 $0.15
Output / MTok $0.2 $0.15
Cache read / MTok
Context window 128,000
Blended 1M in + 3M out $0.65 $0.60
Status ga ga

GPT-OSS 20B detail   Ministral 3 8B detail