modelgrep
Z

Z.ai: GLM 4.5

z-ai/glm-4.5

90th smartest of 179ReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
26.4
90th of 179
Design Elo
1251
3D
Speed
42
207th fastest
Latency
1.4s
first token
Input price
$0.600
176th cheapest
Context
131K
98K max out

How it compares

Smarter than50%
of all ranked models
Faster than33%
of all ranked models
Cheaper than41%
of all ranked models

Overview

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...

Benchmarks

independent · via OpenRouter
Artificial Analysis47th percentile
Intelligence Index
26.4
Coding Index
26.3
Agentic Index
16.2
GPQA Diamond
78%
Humanity's Last Exam
12%
SciCode
35%
Tau²-Bench (agentic)
43%
Design Arena · Elo9,161 tournaments
3D
1251
codecategories
1217
Game Dev
1214
Website
1214
Data Viz
1204
UI Component
1201
svg
1153

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
Novitafp8$0.600$2.20
Z.AIfp8$0.600$2.2098%

Specifications

Context window131K
Max output98K
Knowledge cutoffDec 2024
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price$0.110/M
ModeratedNo

GLM 4.5 FAQ

How much does GLM 4.5 cost?

GLM 4.5 costs $0.600 per million input tokens and $2.20 per million output tokens via OpenRouter, making it 176th cheapest of 298 paid models.

How smart is GLM 4.5?

GLM 4.5 scores 26.4 on the Artificial Analysis Intelligence Index, ranking 90th of 179 benchmarked models, with a GPQA Diamond score of 78%.

How fast is GLM 4.5?

GLM 4.5 generates around 42 tokens per second with 1.4s time-to-first-token (p50), the 207th fastest tracked model.

What is GLM 4.5's context window?

GLM 4.5 supports a 131K-token context window and can output up to 98K tokens. It accepts text input.

Compare head-to-head