{T}
TokenMath.net
Updated 2026-09-23 04:43 UTC
Head-to-Head Specification Battle

Mistral Small 4 vs Command R (08-2024)

Side-by-side technical and economic comparison between Mistral AI's Mistral Small 4 and Cohere's Command R (08-2024).

Endpoint Availability & Transition Notice

Command R (08-2024): Classified as a Legacy Reference model (Tracked Production / Legacy Family).

Core Technical & Pricing Comparison
MetricMistral Small 4Command R (08-2024)Advantage
Provider OrganizationMistral AICohere
Standard Input / 1M$0.15$0.15Identical
Cached Input / 1M$0.015$0.015Command R (08-2024) lower
Output / 1M$0.60$0.60Identical
Context Window256k128kMistral Small 4 (256k)
Max Generation Tokens8.2k4.1kMistral Small 4
Tokenizer FamilyMistral Tekken Tokenizer (131k vocabulary)Cohere BPE (~256k vocabulary)

Interactive Side-by-Side Cost Simulator

Live Delta
Input Tokens / Req2,500
Output Tokens / Req800
Daily Requests10,000
Mistral Small 4
$205.88 / month
$0.00069 / request
Command R (08-2024)
$205.88 / month
$0.00069 / request

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 Command R (08-2024)

Opt for Command R (08-2024) when looking for Cohere's tooling integration, specific context window depth (128k tokens), or when output generation volume favors its $0.6/M rate.