modelgrep
Z

Z.ai: GLM 4.7

z-ai/glm-4.7

34th smartest of 180ReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
42.1
34th of 180
Design Elo
1274
3D
Speed
474
4th fastest
Latency
564ms
first token
Input price
$0.400
145th cheapest
Context
203K
131K max out

How it compares

Smarter than81%
of all ranked models
Faster than99%
of all ranked models
Cheaper than51%
of all ranked models

Overview

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...

Benchmarks

independent · via OpenRouter
Artificial Analysis78th percentile
Intelligence Index
42.1
Coding Index
36.3
Agentic Index
55.0
GPQA Diamond
86%
Humanity's Last Exam
25%
SciCode
45%
Tau²-Bench (agentic)
96%
Design Arena · Elo27,169 tournaments
3D
1274
Website
1272
codecategories
1269
Game Dev
1259
UI Component
1252
Data Viz
1242
asciiart
1212
svg
1201
mobileapps
1198
androidnative
1132
godotgamedev
1131
fullstack
1129

Providers & pricing (9)

ProviderIn $/MOut $/MUptime
DeepInfrafp4$0.400$1.7599.8%
StreamLake$0.480$1.7697.5%
AtlasCloudfp8$0.520$1.8599.4%
Novitafp8$0.540$1.9894.3%
Venicefp4$0.550$2.6598.9%
Z.AIfp4$0.600$2.2095.8%
Google$0.600$2.2099.5%
Phala$0.850$3.3094.7%
Cerebrasfp16$2.25$2.75100%

Specifications

Context window203K
Max output131K
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price$0.080/M
ModeratedNo

GLM 4.7 FAQ

How much does GLM 4.7 cost?

GLM 4.7 costs $0.400 per million input tokens and $1.75 per million output tokens via OpenRouter, making it 145th cheapest of 298 paid models.

How smart is GLM 4.7?

GLM 4.7 scores 42.1 on the Artificial Analysis Intelligence Index, ranking 34th of 180 benchmarked models, with a GPQA Diamond score of 86%.

How fast is GLM 4.7?

GLM 4.7 generates around 474 tokens per second with 564ms time-to-first-token (p50), the 4th fastest tracked model.

What is GLM 4.7's context window?

GLM 4.7 supports a 203K-token context window and can output up to 131K tokens. It accepts text input.

Compare head-to-head