GLM 4.5
GLM 4.5 is a series of foundation models built by Z.ai for intelligent agents, unifying reasoning, coding, and agent capabilities. It is a hybrid reasoning model offering both thinking and non-thinking modes.
Input
Output
Context
131K
Max Output
96K
Parameters
358.3B
Technical Specifications
Model TypeChat
Context Window131,072 tokens
Max Output Tokens96,000 tokens
Parameters358.3B
Release DateJul 20, 2025
Training CutoffNot available
Licensemit
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
12.2%
HLE
87.3%
AIME
78.2%
GPQA
34.8%
SciCode
97.9%
MATH 500
83.5%
MMLU Pro
73.7
Math
26.3
Coding
73.8%
LiveCodeBench
19.5
Intelligence
52.5
Speed (tok/s)
39.4
TTFA (s)
1.3
TTFT (s)
Estimated GPU Requirements for GLM 4.5
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.