Gimbix
Home / Compare / Mistral Large 3 2512 vs Mistral Small 4

Mistral Large 3 2512 vs Mistral Small 4

For a typical chat reply (2,000 tokens in, 400 out), Mistral Large 3 2512 costs 3.0× as much as Mistral Small 4: $1.60 against $0.54 per 1,000 requests at list price on 2026-09-28.

Mistral Large 3 2512Mistral Small 4
Input, per 1M tokens$0.50$0.15
Output, per 1M tokens$1.50$0.60
Context window262K262K
Classification or routing (600 tokens in, 10 out), per 1,000$0.315$0.096
Chat reply (2,000 in, 400 out), per 1,000$1.60$0.54
Retrieval-augmented answer (8,000 in, 500 out), per 1,000$4.75$1.50
Confidence signalnono
Tool callingyesyes

Which one should carry your traffic?

If Mistral Small 4 answers your requests as well as Mistral Large 3 2512, moving that traffic saves 66% on chat-shaped requests. Averages cannot tell you whether it does for your requests. Mistral Small 4 does not expose a confidence signal through OpenRouter, so Gimbix would test it as a full replacement rather than a first answer.

Mistral Large 3 2512 profile · Mistral Small 4 profile · Measure it on your traffic