Mistral Models
Mistral logo

Small 4 (Non-reasoning)

byMistral

Input Price$0.15/1M tokens
Output Price$0.60/1M tokens
Intelligence18.6
Coding16.4

Specifications

Technical details and pricing.

ProviderMistral
Context WindowN/A
Release DateMar 16, 2026
ModalitiesText

Benchmarks

7 benchmark scores from Artificial Analysis.

GPQA57.1%
HLE3.7%
SciCode28.1%
LCR21.3%
IFBench32.8%
Tau218.4%
TerminalBench Hard10.6%

Composite Indices

Higher is better; speed and price are normalized

Standard Benchmarks

Only benchmarks with data are shown

Frequently Asked Questions

What is Small 4 (Non-reasoning) good for?

Small 4 (Non-reasoning) currently has benchmark and pricing data on this page. Runtime metadata will appear later when the model catalog entry becomes available.

How much does Small 4 (Non-reasoning) cost?

Pricing is based on usage. Current rates are $0.15/1M tokens for input and $0.60/1M tokens for output.

Is Small 4 (Non-reasoning) available in LLMBase Chat yet?

Not yet on this page. We will add chat and inference actions automatically once an exact catalog entry exists for Small 4 (Non-reasoning).

Does Small 4 (Non-reasoning) support images or audio?

Small 4 (Non-reasoning) focuses on text-based tasks.

Benchmarks and pricing use Artificial Analysis where available. Catalog specs are used as a fallback.