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

Mistral Small 4 vs Codestral (Current Generation)

Side-by-side technical and economic comparison between Mistral AI's Mistral Small 4 and Mistral AI's Codestral (Current Generation).

Core Technical & Pricing Comparison
MetricMistral Small 4Codestral (Current Generation)Advantage
Provider OrganizationMistral AIMistral AI
Standard Input / 1M$0.15$0.30Mistral Small 4 (50% lower)
Cached Input / 1M$0.015$0.03Mistral Small 4 lower
Output / 1M$0.60$0.90Mistral Small 4 lower
Context Window256k256kMistral Small 4 (256k)
Max Generation Tokens8.2k8.2kMistral Small 4
Tokenizer FamilyMistral Tekken Tokenizer (131k vocabulary)Mistral Tekken BPE (~131k vocabulary)

Interactive Side-by-Side Cost Simulator

Live Delta
Input Tokens / Req2,500
Output Tokens / Req800
Daily Requests10,000
Mistral Small 4LOWER COST
$205.88 / month
$0.00069 / request
Codestral (Current Generation)
$339.75 / month
$0.00113 / request
Selecting Mistral Small 4 saves $133.88 / month (39.4% savings) over Codestral (Current Generation).

When to Choose Mistral Small 4

Opt for Mistral Small 4 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 $0.15/M input rate.

When to Choose Codestral (Current Generation)

Opt for Codestral (Current Generation) when looking for Mistral AI's tooling integration, specific context window depth (256k tokens), or when output generation volume favors its $0.9/M rate.