Compare AI models

Specifications
Parameters
119B16B
Context window
256k8k
API pricing
Input price
$0.15—
Output price
$0.60—
Cached input price
$0.015—
Cheapest input
$0.15Mistral—
Cheapest output
$0.60Mistral—
$60.00Mistral list price—
Benchmarks
LiveCodeBench
63.6%14.3%
GPQA Diamond
71.2%35.2%
MMLU-Pro
78%42.4%
Overview
CompanyMistralMoonshot AI
Release dateMar 16 2026Feb 22 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Small 4 leads Moonlight on 3 of the 3 benchmarks they both report (LiveCodeBench, GPQA Diamond, MMLU-Pro). Only Mistral Small 4 has a verified first-party price for an available API: $0.15 per million input tokens and $0.60 per million output tokens. No currently available pay-as-you-go API rate is tracked for Moonlight. Moonlight shipped 387 days before Mistral Small 4, so benchmark comparisons should account for the intervening progress.

Mistral Small 4 has 119B parameters, while Moonlight has 16B. Context windows are 256k (Mistral Small 4) vs 8k (Moonlight).

On LiveCodeBench, Mistral Small 4 leads at 63.6% vs Moonlight at 14.3%. On GPQA Diamond, Mistral Small 4 leads at 71.2% vs Moonlight at 35.2%. On MMLU-Pro, Mistral Small 4 leads at 78% vs Moonlight at 42.4%.