Compare AI models

Specifications
Parameters
—355B
Context window
1M200k
API pricing
Input price
—$0.60
Output price
—$2.20
Cached input price
—$0.11
Cheapest input
—$0.40DeepInfra
Cheapest output
—$1.60DeepInfra
—$174Venice · fp4
Benchmarks
LiveCodeBench
37.8%82.8%
MMLU-Pro
64.5%83.2%
Overview
CompanyQwenZ.ai
Release dateNov 15 2024Sep 30 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GLM-4.6 leads Qwen2.5-Turbo (1M) on 2 of the 2 benchmarks they both report (LiveCodeBench, MMLU-Pro). Only GLM-4.6 has a verified first-party price for an available API: $0.60 per million input tokens and $2.20 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen2.5-Turbo (1M). Qwen2.5-Turbo (1M) shipped 319 days before GLM-4.6, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Qwen2.5-Turbo (1M)) vs 200k (GLM-4.6). Qwen2.5-Turbo (1M) is closed, while GLM-4.6 is open weight.

On LiveCodeBench, GLM-4.6 leads at 82.8% vs Qwen2.5-Turbo (1M) at 37.8%. On MMLU-Pro, GLM-4.6 leads at 83.2% vs Qwen2.5-Turbo (1M) at 64.5%.