Head to head

Ministral 3 14B vs GPT-OSS 20B

On a blended workload of one million input tokens and three million output tokens, GPT-OSS 20B is 1.2× cheaper than Ministral 3 14B.

Ministral 3 14BGPT-OSS 20B
Provider Mistral Together AI
Input / MTok $0.2 $0.05
Output / MTok $0.2 $0.2
Cache read / MTok
Context window 128,000
Blended 1M in + 3M out $0.80 $0.65
Status ga ga

Ministral 3 14B detail   GPT-OSS 20B detail