GLM-5.3-Flash

Name: GLM-5.3-Flash
Brand: Z.ai

Model

Vendor:Z.ai

│

Model Size:320B total / 18B active

│

Context Window:1,000,000 tokens

│

Max Output:131,072 tokens

Find on AI Platforms

View model card and weights

AI model leaderboard and benchmarks

Compare and use multiple AI models

320B total / 18B active

1.0M

131.1K

GlobalUS DollarHistorical pricingEnded 9/9/2026

Input $0.075 / 1M tokens

Output $0.25 / 1M tokens

Cache read $0.015 / 1M tokens

Cache write $0.00 / 1M tokens

GlobalUS Dollar

Input $0.15 / 1M tokens

Output $0.50 / 1M tokens

Cache read $0.03 / 1M tokens