Head to head

Magistral Medium vs GLM 5.1

On a blended workload of one million input tokens and three million output tokens, GLM 5.1 is 1.2× cheaper than Magistral Medium.

Magistral MediumGLM 5.1
Provider Mistral Fireworks AI
Input / MTok $2 $1.4
Output / MTok $5 $4.4
Cache read / MTok $0.26
Context window
Blended 1M in + 3M out $17.00 $14.60
Status retired ga

Magistral Medium detail   GLM 5.1 detail