modelgrep
z-ai logo

Z.ai: GLM 5V Turbo

z-ai/glm-5v-turbo

82nd smartest of 212ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
35.3
82nd of 212
Design Elo
1264
3D
Speed
37
241st fastest
Latency
4.8s
first token
Input price
$1.20
259th cheapest
Context
203K
131K max out

How it compares

Smarter than61%
of all ranked models
Faster than28%
of all ranked models
Cheaper than29%
of all ranked models

Overview

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...

Benchmarks

independent · Artificial Analysis & Design Arena
Artificial Analysis82th percentile
Intelligence Index
35.3
GPQA Diamond
81%
Humanity's Last Exam
17%
SciCode
44%
Tau²-Bench (agentic)
99%
Design Arena · Elo11,001 tournaments
3D
1264
Game Dev
1260
Website
1253
UI Component
1246
Data Viz
1225
svg
1195

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Z.AIfp8$1.20$4.0099%

Specifications

Context window203K
Max output131K
Knowledge cutoff
Input modalitiesimage, text, video
Output modalitiestext
Prompt caching
Cache read price$0.240/M
ModeratedNo

GLM 5V Turbo FAQ

How much does GLM 5V Turbo cost?

GLM 5V Turbo costs $1.20 per million input tokens and $4.00 per million output tokens via OpenRouter, making it 259th cheapest of 367 paid models.

How smart is GLM 5V Turbo?

GLM 5V Turbo scores 35.3 on the Artificial Analysis Intelligence Index, ranking 82nd of 212 benchmarked models, with a GPQA Diamond score of 81%.

How fast is GLM 5V Turbo?

GLM 5V Turbo generates around 37 tokens per second with 4.8s time-to-first-token (p50), the 241st fastest tracked model.

What is GLM 5V Turbo's context window?

GLM 5V Turbo supports a 203K-token context window and can output up to 131K tokens. It accepts image, text, video input.

Compare head-to-head