modelgrep
Z

Z.ai: GLM 4.5 Air

z-ai/glm-4.5-air

107th smartest of 178Cheaper than 77% of paidReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
23.2
107th of 178
Design Elo
1237
Data Viz
Speed
48
176th fastest
Latency
760ms
first token
Input price
$0.125
68th cheapest
Context
131K
131K max out

How it compares

Smarter than40%
of all ranked models
Faster than40%
of all ranked models
Cheaper than77%
of all ranked models

Overview

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...

Benchmarks

independent · via OpenRouter
Artificial Analysis39th percentile
Intelligence Index
23.2
Coding Index
23.8
Agentic Index
21.0
GPQA Diamond
73%
Humanity's Last Exam
7%
SciCode
31%
Tau²-Bench (agentic)
47%
Design Arena · Elo8,103 tournaments
Data Viz
1237
3D
1204
Website
1191
codecategories
1189
UI Component
1181
Game Dev
1163
svg
1128

Providers & pricing (4)

ProviderIn $/MOut $/MUptime
Io Netfp8$0.125$0.850100%
Novitabf16$0.130$0.850100%
SiliconFlowfp8$0.140$0.860100%
Z.AIfp8$0.200$1.1098.9%

Specifications

Context window131K
Max output131K
Knowledge cutoffDec 2024
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price$0.060/M
ModeratedNo

GLM 4.5 Air FAQ

How much does GLM 4.5 Air cost?

GLM 4.5 Air costs $0.125 per million input tokens and $0.850 per million output tokens via OpenRouter, making it 68th cheapest of 298 paid models.

How smart is GLM 4.5 Air?

GLM 4.5 Air scores 23.2 on the Artificial Analysis Intelligence Index, ranking 107th of 178 benchmarked models, with a GPQA Diamond score of 73%.

How fast is GLM 4.5 Air?

GLM 4.5 Air generates around 48 tokens per second with 760ms time-to-first-token (p50), the 176th fastest tracked model.

What is GLM 4.5 Air's context window?

GLM 4.5 Air supports a 131K-token context window and can output up to 131K tokens. It accepts text input.

Compare head-to-head