modelgrep
Z

Z.ai: GLM 5

z-ai/glm-5

41st smartest of 178ReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
40.6
41st of 178
Design Elo
1313
3D
Speed
92
75th fastest
Latency
304ms
first token
Input price
$0.600
170th cheapest
Context
203K

How it compares

Smarter than77%
of all ranked models
Faster than75%
of all ranked models
Cheaper than43%
of all ranked models

Overview

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...

Benchmarks

independent · via OpenRouter
Artificial Analysis74th percentile
Intelligence Index
40.6
Coding Index
39.0
Agentic Index
60.3
GPQA Diamond
67%
Humanity's Last Exam
7%
SciCode
38%
Tau²-Bench (agentic)
97%
Design Arena · Elo28,717 tournaments
3D
1313
Game Dev
1302
codecategories
1297
Website
1291
UI Component
1289
Data Viz
1271
godotgamedev
1238
androidnative
1230
mobileapps
1230
svg
1224
fullstack
1202
asciiart
1187

Providers & pricing (16)

ProviderIn $/MOut $/MUptime
GMICloudfp8$0.600$1.9262.1%
DeepInfrafp4$0.600$2.0899.7%
StreamLake$0.650$2.0899.9%
Baidufp8cache$0.700$2.24100%
DigitalOcean$0.850$2.7295.5%
SiliconFlowfp8$0.950$2.5598.9%
Chutesfp8$0.950$2.5588.4%
AtlasCloudfp8$0.950$3.15100%
Amazon Bedrock$1.00$3.2093%
Friendli$1.00$3.20100%
Novitafp8$1.00$3.20100%
Z.AIfp8$1.00$3.2099.7%
Parasailfp8$1.00$3.2097.8%
Together$1.00$3.20100%
Venicefp8$1.00$3.20
Phala$1.20$3.50

Specifications

Context window203K
Max output
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt cachingSupported
Cache read price$0.120/M
ModeratedNo
Open weightszai-org/GLM-5

GLM 5 FAQ

How much does GLM 5 cost?

GLM 5 costs $0.600 per million input tokens and $1.92 per million output tokens via OpenRouter, making it 170th cheapest of 298 paid models.

How smart is GLM 5?

GLM 5 scores 40.6 on the Artificial Analysis Intelligence Index, ranking 41st of 178 benchmarked models, with a GPQA Diamond score of 67%.

How fast is GLM 5?

GLM 5 generates around 92 tokens per second with 304ms time-to-first-token (p50), the 75th fastest tracked model.

What is GLM 5's context window?

GLM 5 supports a 203K-token context window. It accepts text input.

Compare head-to-head