Compare AI models

Specifications
Parameters
—16B
Context window
1M8k
API pricing
Input price
$0.30—
Output price
$2.50—
Cached input price
$0.03—
Cheapest input
$0.15Google AI Studio—
Cheapest output
$1.25Google AI Studio—
$185Google list price—
Benchmarks
LiveCodeBench
63.5%14.3%
GPQA Diamond
78.3%35.2%
SimpleQA
29.7%5.6%
Overview
CompanyGoogleMoonshot AI
Release dateApr 17 2025Feb 22 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 2.5 Flash leads Moonlight on 3 of the 3 benchmarks they both report (LiveCodeBench, GPQA Diamond, SimpleQA). Only Gemini 2.5 Flash has a verified first-party price for an available API: $0.30 per million input tokens and $2.50 per million output tokens. No currently available pay-as-you-go API rate is tracked for Moonlight. Moonlight shipped 54 days before Gemini 2.5 Flash, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 2.5 Flash) vs 8k (Moonlight). Gemini 2.5 Flash is closed, while Moonlight is open weight.

On LiveCodeBench, Gemini 2.5 Flash leads at 63.5% vs Moonlight at 14.3%. On GPQA Diamond, Gemini 2.5 Flash leads at 78.3% vs Moonlight at 35.2%. On SimpleQA, Gemini 2.5 Flash leads at 29.7% vs Moonlight at 5.6%.