Compare AI models

Specifications
Parameters
16B480B
Context window
8k256k
API pricing
Cheapest input
—$0.35Venice
Cheapest output
—$1.50Venice
—$145Venice · fp8
These models have no shared benchmark scores.
Overview
CompanyMoonshot AIQwen
Release dateFeb 22 2025Jul 22 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Moonlight and Qwen3-Coder don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Moonlight shipped 150 days before Qwen3-Coder, so benchmark comparisons should account for the intervening progress.

Moonlight has 16B parameters, while Qwen3-Coder has 480B. Context windows are 8k (Moonlight) vs 256k (Qwen3-Coder).

Direct benchmark comparisons are unavailable — Moonlight and Qwen3-Coder don't publish scores on any of the same benchmarks.