baseten
GLM 5.2 Fast
General Language Model 5.2 by Z.AI, served by Wafer with bilingual English/Chinese generation, coding, reasoning, and a 1M-token context window.
Provider:
baseten
Model type:
chat
Location:
rest
Context Window
524288
Intelligence Rating
Speed Rating
Cost Efficiency Rating
Pricing
$
2.1
Input tokens per million
$
6.6
Output tokens per million
Features
Tool Calling
Supported
JSON Mode
Supported
Reasoning
Supported
