Z.ai

GLM-4.5

CTX131K

77Quality

Reasoning · Tools

Input$0.60/M

Output$2.20/M

Hybrid-reasoning GLM release that made the 4.5 line broadly useful

Open weightsMIT610/1044

Drag to turn

Z.aiTextUncommon

GLM-4.5

Hybrid-reasoning GLM release that made the 4.5 line broadly useful

glm-4.5

Type: Text
Quality: 77 · Top 23% on the LMArena Text
Context window: 131,072 tokens
Max output: 98,304 tokens
Input price: $0.60 / 1M tokens
Output price: $2.20 / 1M tokens
Cache read: $0.11 / 1M tokens
Cache write: Free
Parameters: 358B (358,337,791,296)
Downloads: 120K in the last 30 days
Likes: 1.4K
Access to weights: Open download
Released: Jul 28, 2025
Knowledge cutoff: Apr 2025
Takes in: Text
Puts out: Text
Reasoning: Yes
Tool calling: Yes
Structured output: No
File attachments: No
Access: Open weights
License: MIT
Rarity: Uncommon
Set number: 610/1044

Open Z.ai docs Weights on Hugging Face Quality 77 Where to run it 19 Evolution 1/7 Race it 41 tok/s Meet its creature Battle Seed 2.1 Turbo

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-4.5, refreshed daily from Epoch AI and LMArena.

Top 23% of the 416 models on the LMArena Text: #95.

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#95 of 416
People compare two anonymous answers and vote for the better one.1,430 rating
LMArena Text · Coding#129 of 411
The text arena’s coding prompts only.1,434 rating
LMArena Text · Math#106 of 400
The text arena’s math prompts only.1,427 rating
LMArena Text · Creative writing#108 of 414
The text arena’s creative writing prompts only.1,395 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

18 providers sell GLM-4.5 through an API, and 1 Hugging Face host serves it. Prices are per million tokens, cheapest first.

Cheapest302.AI$0.29 in · $1.14 out
Free to try1 providerModelScope
From the labZ.AI$0.60 in · $2.20 out
Fastest on Hugging FaceZ.ai41 tokens/s

API providers

Provider	Input	Output	Context
ModelScopeFree`ZhipuAI/GLM-4.5`	Free	Free	131K
302.AICheapest paid`glm-4.5`	$0.29	$1.14	131K
ZenMux`z-ai/glm-4.5`	$0.29	$1.16	128K
NanoGPT`z-ai/glm-4.5`	$0.30	$1.30	128K
Abacus`zai-org/GLM-4.5`	$0.60	$2.20	131K
DevPass (LLM Gateway)`glm-4.5`	$0.60	$2.20	131K
Impossibl`zai/glm-4.5`	$0.60	$2.20	131K
Jiekou.AI`zai-org/glm-4.5`	$0.60	$2.20	131K
Kilo Gateway`z-ai/glm-4.5`	$0.60	$2.20	131K
LLM Gateway`zai/glm-4.5`	$0.60	$2.20	128K

Show 8 more providers

Provider	Input	Output	Context
Merge Gateway`zai/glm-4.5`	$0.60	$2.20	128K
OpenRouter`z-ai/glm-4.5`	$0.60	$2.20	131K
OrcaRouter`z-ai/glm-4.5`	$0.60	$2.20	131K
Tempr Gateway`zai/glm-4.5`	$0.60	$2.20	131K
Vercel AI Gateway`zai/glm-4.5`	$0.60	$2.20	128K
Z.AIOfficial`glm-4.5`	$0.60	$2.20	131K
Zhipu AI`glm-4.5`	$0.60	$2.20	131K
Qiniu`glm-4.5`	—	—	131K

Hugging Face Inference Providers

Host	Input	Output	Context	Speed	First token
Z.aiTools	—	—	—	41 tok/s	1.7s

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-4.5

GLM-4.5

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