Modeldex
Drag to turnCard front showing

Z.aiTextUncommon

GLM-4.6

Late GLM-4 workhorse for coding agents, reasoning, and structured tasks

glm-4.6
Type
Text
Quality
82 · Top 18% on the LMArena Text
Context window
204,800 tokens
Max output
131,072 tokens
Input price
$0.60 / 1M tokens
Output price
$2.20 / 1M tokens
Cache read
$0.11 / 1M tokens
Cache write
Free
Parameters
357B (356,785,898,816)
Downloads
19K in the last 30 days
Likes
1.2K
Access to weights
Open download
Released
Sep 30, 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
666/1044
Open Z.ai docsWeights on Hugging FaceQuality 82Where to run it 33Evolution 2/7Race it 38 tok/sMeet its creatureBattle 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-4.6, refreshed daily from Epoch AI and LMArena.

Top 18% of the 416 models on the LMArena Text: #76.

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

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

29 providers sell GLM-4.6 through an API, and 4 Hugging Face hosts serve it. Prices are per million tokens, cheapest first.

API providers

ProviderInputOutputContext
iFlowFreeglm-4.6FreeFree200K
ModelScopeFreeZhipuAI/GLM-4.6FreeFree203K
AIHubMixCheapest paidglm-4.6$0.27$1.10205K
302.AIglm-4.6$0.29$1.14205K
ZenMuxz-ai/glm-4.6$0.29$1.16200K
Heliconeglm-4.6$0.45$1.50205K
IO.NETzai-org/GLM-4.6$0.40$1.75200K
Venice AIzai-org-glm-4.6$0.43$1.75198K
Meganovazai-org/GLM-4.6$0.45$1.90203K
Deep Infrazai-org/GLM-4.6$0.50$2.00203K
Show 19 more providers
ProviderInputOutputContext
NanoGPTz-ai/glm-4.6$0.50$2.00200K
DevPass (LLM Gateway)glm-4.6$0.55$2.20205K
Kilo Gatewayz-ai/glm-4.6$0.55$2.20205K
LLM Gatewaynovita/glm-4.6$0.55$2.20205K
Novita AIzai-org/glm-4.6$0.55$2.20205K
OpenRouterz-ai/glm-4.6$0.55$2.20205K
Abacuszai-org/GLM-4.6$0.60$2.20203K
Eden AIzai/glm-4.6$0.60$2.20203K
Impossiblzai/glm-4.6$0.60$2.20205K
Merge Gatewayzai/glm-4.6$0.60$2.20200K
Ofoxz-ai/glm-4.6$0.60$2.20205K
OpenCodeglm-4.6$0.60$2.20205K
OrcaRouterz-ai/glm-4.6$0.60$2.20205K
Tempr Gatewayzai/glm-4.6$0.60$2.20205K
Vercel AI Gatewayzai/glm-4.6$0.60$2.20200K
Z.AIOfficialglm-4.6$0.60$2.20205K
Zhipu AIglm-4.6$0.60$2.20205K
Poenovita/glm-4.6———
Qiniuz-ai/glm-4.6——200K

Hugging Face Inference Providers

HostInputOutputContextSpeedFirst token
DeepInfraTools$0.50$2.00203K20 tok/s0.7s
NovitaTools$0.55$2.20205K25 tok/s3.6s
Featherless—————
Z.aiFastestTools———38 tok/s2.6s

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.

More from Z.ai

Z.ai

GLM-5.3-FlashX

CTX1M
Reasoning · Vision · Tools
TextImageVideoPDFInput$0.37/M
TextOutput$1.25/M

High-speed GLM-5.3-Flash serving option for coding and agent workflows

Open weightsMIT1011/1044
Z.ai

GLM-5.3-Flash

CTX1M
84Quality
Reasoning · Vision · Tools
TextImageVideoPDFInput$0.15/M
TextOutput$0.50/M

Native multimodal GLM model for efficient coding and long-horizon agent tasks

Open weightsMIT989/1044
Z.ai

GLM-5.3-Flash-BF16

SIZE321B
Vision
TextImageDownloads160K/mo
TextLikes74

Vision-language model from Z.ai, 321B parameters.

Open weightsMIT988/1044
Z.ai

GLM-5.3

CTX1M
89Quality
Reasoning · Tools
TextInput$1.40/M
TextOutput$4.40/M

Flagship GLM model for long-horizon coding, agents, and complex project delivery

Open weightsGLM 5.3 license982/1044
Z.ai

GLM-5.2

CTX1M
82Quality
Reasoning · Tools
TextInput$1.40/M
TextOutput$4.40/M

Open flagship GLM for long-horizon coding agents and million-token context work

Open weightsMIT925/1044
Z.ai

GLM-5.1

CTX200K
79Quality
Reasoning · Tools
TextInput$1.40/M
TextOutput$4.40/M

Strong GLM coding model for agentic engineering, terminals, and repository generation

Open weightsMIT860/1044
Z.ai

GLM-5V-Turbo

CTX200K
80Quality
Reasoning · Vision · Tools
TextImageVideoPDFInput$1.20/M
TextOutput$4/M

Fast GLM vision model for screenshots, documents, and multimodal agent tasks

PaidProprietary847/1044
Z.ai

GLM-5-Turbo

CTX200K
Reasoning · Tools
TextInput$1.20/M
TextOutput$4/M

Faster GLM-5 lane for coding agents that need lower latency

PaidProprietary829/1044
Deck0/4
  1. Empty slot
  2. Empty slot
  3. Empty slot
  4. Empty slot