wafer
GLM5.2-Fast
GLM-5.2 by Z.AI served through the high-throughput Wafer endpoint with a 1M-token context window.
Provider:
wafer
Model type:
chat
Location:
rest
Context Window
1048576
Intelligence Rating
Speed Rating
Cost Efficiency Rating
Pricing
$
3
Input tokens per million
$
10.25
Output tokens per million
Features
Tool Calling
Supported
JSON Mode
Supported
Reasoning
Supported
