Compare AI models

Specifications
Parameters
1T14.3B
Context window
256k32k
API pricing
Cheapest input
$0.49AtlasCloud—
Cheapest output
$2.50AtlasCloud—
$223AtlasCloud · int4—
These models have no shared benchmark scores.
Overview
CompanyMoonshot AIQwen
Release dateJan 27 2026Mar 28 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2.5 and Qwen1.5-MoE don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen1.5-MoE shipped 670 days before Kimi K2.5, so benchmark comparisons should account for the intervening progress.

Kimi K2.5 has 1T parameters, while Qwen1.5-MoE has 14.3B. Context windows are 256k (Kimi K2.5) vs 32k (Qwen1.5-MoE).

Direct benchmark comparisons are unavailable — Kimi K2.5 and Qwen1.5-MoE don't publish scores on any of the same benchmarks.