Z.ai GLM 4.5
Z.aiCompact
ThinkingTool Use
About this model
GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...
Performance Tier
Compact
Z.ai GLM 4.5 is a compact model from Z.ai : optimized for speed and affordability.
Small, fast, and affordable. Optimized for speed and low cost, great for high-volume or simple tasks.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.600 |
| Output (completion) | $2.20 |
| Cache read | $0.110 |
Capabilities
Context Length131K
Max Output Tokens98K
TokenizerOther
Inputtext
Outputtext
Release DateJuly 25, 2025
Benchmarks
General Intelligence
MMLU
76.5%
MMLU-Pro
84.6%
Mathematics
MATH-500
62%
Programming
HumanEval
65%
LiveCodeBench
72.9%
Reasoning
Humanity's Last Exam
14.4%
Recommended Use Cases
General ChatTranslationSummarization
Strengths
- Affordable entry point to the GLM family
- Good bilingual Chinese/English performance
- Suitable for everyday conversation and translation
Limitations
- Older model — GLM 4.7 recommended for new projects
- Limited performance on complex tasks
Resources
This model may use your data for training
