Compare AI models

Specifications
Parameters
16B—
Context window
8k1M
API pricing
Input price
—$0.40
Output price
—$1.60
Cached input price
—$0.10
Cheapest input
—$0.40Azure
Cheapest output
—$1.60Azure
—$160OpenAI list price
Benchmarks
HumanEval
48.1%93.8%
GPQA Diamond
35.2%65%
SimpleQA
5.6%16.8%
MMLU
70%87.5%
Overview
CompanyMoonshot AIOpenAI
Release dateFeb 22 2025Apr 14 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GPT-4.1 mini leads Moonlight on 4 of the 4 benchmarks they both report (HumanEval, GPQA Diamond, SimpleQA, MMLU). Only GPT-4.1 mini has a verified first-party price for an available API: $0.40 per million input tokens and $1.60 per million output tokens. No currently available pay-as-you-go API rate is tracked for Moonlight. Moonlight shipped 51 days before GPT-4.1 mini, so benchmark comparisons should account for the intervening progress.

Context windows are 8k (Moonlight) vs 1M (GPT-4.1 mini). Moonlight is open weight, while GPT-4.1 mini is closed.

On HumanEval, GPT-4.1 mini leads at 93.8% vs Moonlight at 48.1%. On GPQA Diamond, GPT-4.1 mini leads at 65% vs Moonlight at 35.2%. On SimpleQA, GPT-4.1 mini leads at 16.8% vs Moonlight at 5.6%. On MMLU, GPT-4.1 mini leads at 87.5% vs Moonlight at 70%.