glm-4.5-air by zai - AI Model Details, Pricing, and Performance Metrics

z-ai
glm-4.5-air
z-ai

glm-4.5-air

completions
byzai

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter size. GLM-4.5-Air also supports hybrid inference modes, offering a "thinking mode" for advanced reasoning and tool use, and a "non-thinking mode" for real-time interaction.

Released
Jul 28, 2025
Knowledge
Jan 29, 2025
License
MIT
Context
131072
Input
$0.2 / 1M tokens
Output
$1.1 / 1M tokens
Cached
$0.03 / 1M tokens
Capabilities: tools
Accepts: text
Returns: text

Access glm-4.5-air through LangDB AI Gateway

Recommended

Integrate with z-ai's glm-4.5-air and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API
Cost Optimization
Enterprise Security
Get Started Now

Free tier available • No credit card required

Instant Setup
99.9% Uptime
10,000+Monthly Requests
Request Volume
Daily API requests
155
Performance (TPS)
Tokens per second
38.02 tokens/s

Category Scores

Benchmark Tests

View Other Benchmarks
AIME
67.3
Mathematics
AA Coding Index
49.5
Programming
AAII
48.8
General
AA Math Index
80.7
Mathematics
GPQA
74.2
STEM (Physics, Chemistry, Biology)
HLE
6.8
General Knowledge
LiveCodeBench
68.4
Programming
MATH-500
96.5
Mathematics
MMLU-Pro
81.5
General Knowledge
SciCode
30.6
Scientific

Code Examples

Integration samples and API usage

Related Models

Similar models from zai