Compare AI models

Specifications
Parameters
2.4T744B
Context window
262k1M
API pricing
Input price
—$1.40
Output price
—$4.40
Cached input price
—$0.26
Cheapest input
—$0.0699Wafer
Cheapest output
—$1.32Featherless
—$83.98Wafer · fp4
Benchmarks
Terminal-Bench 2.1
76.03%88.2%
Overview
CompanyQwenZ.ai
Release dateAug 12 2026Aug 14 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

GLM-5.3 leads Qwen3.8-2.4T-A95B on 1 of the 1 benchmark they both report (Terminal-Bench 2.1). Only GLM-5.3 has a verified first-party price for an available API: $1.40 per million input tokens and $4.40 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen3.8-2.4T-A95B. Qwen3.8-2.4T-A95B shipped 2 days before GLM-5.3, so benchmark comparisons should account for the intervening progress.

Qwen3.8-2.4T-A95B has 2.4T parameters, while GLM-5.3 has 744B. Context windows are 262k (Qwen3.8-2.4T-A95B) vs 1M (GLM-5.3).

On Terminal-Bench 2.1, GLM-5.3 leads at 88.2% vs Qwen3.8-2.4T-A95B at 76.03%.