{T}
TokenMath.net
Updated 2026-09-22 11:16 UTC
Head-to-Head Specification Battle

Mistral Large 3 vs Mistral Small 4

Side-by-side technical and economic comparison between Mistral AI's Mistral Large 3 and Mistral AI's Mistral Small 4.

Core Technical & Pricing Comparison
MetricMistral Large 3Mistral Small 4Advantage
Provider OrganizationMistral AIMistral AI
Standard Input / 1M$0.50$0.15Mistral Small 4 (70% lower)
Cached Input / 1M$0.05$0.015Mistral Small 4 lower
Output / 1M$1.50$0.60Mistral Small 4 lower
Context Window256k256kEqual
Max Generation Tokens16.4k8.2kMistral Large 3
Tokenizer FamilyMistral Tekken Tokenizer (131k vocabulary)Mistral Tekken Tokenizer (131k vocabulary)

Interactive Side-by-Side Cost Simulator

Live Delta
Input Tokens / Req2,500
Output Tokens / Req800
Daily Requests10,000
Mistral Large 3
$566.25 / month
$0.00189 / request
Mistral Small 4LOWER COST
$205.88 / month
$0.00069 / request
Selecting Mistral Small 4 saves $360.38 / month (63.6% savings) over Mistral Large 3.

When to Choose Mistral Large 3

Opt for Mistral Large 3 when your engineering requirements prioritize Mistral AI's ecosystem, specific tokenizer efficiencies (Calibrated Mistral Tokenizer (±3%)), or when your expected prompt-to-completion ratios favor its $0.5/M input rate.

When to Choose Mistral Small 4

Opt for Mistral Small 4 when looking for Mistral AI's tooling integration, specific context window depth (256k tokens), or when output generation volume favors its $0.6/M rate.