Z.ai

GLM-4.6V

CTX128K

57Quality

Reasoning · Vision · Tools

Input$0.30/M

Output$0.90/M

GLM vision model for visual reasoning, documents, and multimodal agents

Open weightsMIT720/1044

Drag to turn

Z.aiTextCommon

GLM-4.6V

GLM vision model for visual reasoning, documents, and multimodal agents

glm-4.6v

Type: Text
Quality: 57 · Top 43% on the LMArena Text
Context window: 128,000 tokens
Max output: 32,768 tokens
Input price: $0.30 / 1M tokens
Output price: $0.90 / 1M tokens
Cache read: $0.05 / 1M tokens
Cache write: —
Parameters: 108B (107,710,933,120)
Downloads: 3.5K in the last 30 days
Likes: 400
Access to weights: Open download
Released: Dec 8, 2025
Knowledge cutoff: Apr 2025
Takes in: Text, Image, Video
Puts out: Text
Reasoning: Yes
Tool calling: Yes
Structured output: No
File attachments: Yes
Access: Open weights
License: MIT
Rarity: Common
Set number: 720/1044

Open Z.ai docs Weights on Hugging Face Quality 57 Where to run it 17 Evolution 3/4 Race it 46 tok/s Meet its creature Battle Codestral 25.08

License read from the model’s Hugging Face card. Specs from models.dev, downloads from Hugging Face, last changed Oct 19, 2026. Official source: docs.z.ai.

How good is it?

Public leaderboard scores for GLM-4.6V, refreshed daily from Epoch AI and LMArena.

Top 43% of the 416 models on the LMArena Text: #178.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

LMArena Text#178 of 416
People compare two anonymous answers and vote for the better one.1,376 rating
LMArena Text · Coding#183 of 411
The text arena’s coding prompts only.1,389 rating
LMArena Text · Creative writing#170 of 414
The text arena’s creative writing prompts only.1,347 rating
LMArena Vision#111 of 165
Questions about images, voted by people.1,164 rating

Scores from LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

16 providers sell GLM-4.6V through an API, and 1 Hugging Face host serves it. Prices are per million tokens, cheapest first.

CheapestAIHubMix$0.14 in · $0.41 out
From the labZ.AI$0.30 in · $0.90 out
Fastest on Hugging FaceZ.ai46 tokens/s

API providers

Provider	Input	Output	Context
AIHubMixCheapest paid`glm-4.6v`	$0.14	$0.41	128K
302.AI`glm-4.6v`	$0.14	$0.43	128K
ZenMux`z-ai/glm-4.6v`	$0.15	$0.44	200K
DevPass (LLM Gateway)`glm-4.6v`	$0.30	$0.90	131K
Eden AI`zai/glm-4.6v`	$0.30	$0.90	131K
Kilo Gateway`z-ai/glm-4.6v`	$0.30	$0.90	131K
LLM Gateway`zai/glm-4.6v`	$0.30	$0.90	128K
NanoGPT`z-ai/glm-4.6v`	$0.30	$0.90	128K
Novita AI`zai-org/glm-4.6v`	$0.30	$0.90	131K
OpenRouter`z-ai/glm-4.6v`	$0.30	$0.90	131K

Show 6 more providers

Provider	Input	Output	Context
Tempr Gateway`zai/glm-4.6v`	$0.30	$0.90	128K
Z.AIOfficial`glm-4.6v`	$0.30	$0.90	128K
Zhipu AI`glm-4.6v`	$0.30	$0.90	128K
Zhipu AI Coding Plan`glm-4.6v`	$0.30	$0.90	128K
AI/ML API`z-ai/glm-4.6v`	$0.41	$1.24	131K
Poe`novita/glm-4.6v`	—	—	131K

Hugging Face Inference Providers

Host	Input	Output	Context	Speed	First token
Z.aiTools	—	—	—	46 tok/s	2.8s

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.

GLM-4.6V

GLM-4.6V

How good is it?

Leaderboards

Where to run it

API providers

Hugging Face Inference Providers

Face off

More from Z.ai

GLM-5.3-FlashX

GLM-5.3-Flash

GLM-5.3-Flash-BF16

GLM-5.3

GLM-5.2

GLM-5.1

GLM-5V-Turbo

GLM-5-Turbo