DataLearner logo
GL

GLM-4.5-Air

Reasoning modelGLM AirGLM-4.5

GLM-4.5-MoE-106B-A12B-0715

Release date: 2025-07-28Updated: 2026-06-15 07:18:18.9391,699
Parameters
106B
Context length
128K
Chinese support
Supported
Reasoning ability

GLM-4.5-MoE-106B-A12B-0715 is an AI model published by Zhipu AI, released on 2025-07-28, for Reasoning model, with 106B parameters, and 128K context length, requiring about 212 GB storage, with a 98.10 score on MATH-500.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

GLM-4.5-Air

Model basics

Reasoning traces
Supported
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
95K tokens
Model type
Reasoning model
Modality (in / out)
Text → Text
Release date
2025-07-28
Model file size
212 GB
MoE architecture
Yes
Total params / Active params
106B / 12B
Knowledge cutoff
No data
GLM-4.5-Air

Open source & experience

Code license
Weights license
Apache 2.0- Commercial use permitted
GLM-4.5-Air

Official resources

Paper
DataLearnerAI blog
GLM-4.5-Air

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-¥0.800/ 1M¥2.00/ 1M
Cache PricingPrompt Cache
TypeTTLWriteRead
Text-¥0.0000/ 1M¥0.400/ 1M
GLM-4.5-Air

Benchmark Results

GLM-4.5-Air currently shows benchmark results led by MATH-500 (5 / 44, score 98.10), AIME 2024 (15 / 62, score 89.40), Pinch Bench (13 / 37, score 85.70). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
Tool usage

General Knowledge

3 evaluations
Benchmark / mode
Score
Rank/total
81.40
54 / 132
75
100 / 187
10.60
143 / 170

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
70.70
50 / 123
57.60
83 / 111

Math and Reasoning

2 evaluations
Benchmark / mode
Score
Rank/total
98.10
5 / 44
89.40
15 / 62

AI Agent - Tool Usage

1 evaluations
Benchmark / mode
Score
Rank/total

Claw-style Agent Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
Pinch Bench
Thinking ModeTools
85.70
13 / 37

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

GLM-4.5-Air

Publisher

GLM-4.5-MoE-106B-A12B-0715

Model Overview

GLM-4.5-MoE-106B-A12B-0715 is an AI model published by Zhipu AI, released on 2025-07-28, for Reasoning model, with 106B parameters, and 128K context length, requiring about 212 GB storage, with a 98.10 score on MATH-500.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code