Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...
Performance Tier
Balanced
Z.ai GLM 4.6 is a balanced model from Z.ai : strong performance at a reasonable price.
Strong cost-performance ratio. Reliable for most professional use cases without premium pricing.
Pricing
This model is included in Elosia plans
Type
per 1M tokens
Input (prompt)
$0.390
Output (completion)
$1.90
Capabilities
Context Length205K
Max Output Tokens205K
TokenizerOther
Inputtext
Outputtext
Release DateSeptember 30, 2025
Benchmarks
General Intelligence
MMLU
80%
Mathematics
MATH-500
72%
Programming
HumanEval
76.5%
Recommended Use Cases
General ChatCodingTranslation
Strengths
Solid general-purpose model with good Chinese/English support
Good value for bilingual applications
Reliable for everyday reasoning and conversation
Limitations
Superseded by GLM 4.7 on most benchmarks
Limited multilingual support beyond Chinese and English