Head to head

Ministral 3 8B vs GPT-OSS 20B

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.

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

Ministral 3 8B detail   GPT-OSS 20B detail