Modeldex
Drag to turnCard front showing

Z.aiTextUncommon

GLM-5

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

glm-5
Type
Text
Quality
70 · Top 30% on the Epoch Capabilities Index
Context window
204,800 tokens
Max output
131,072 tokens
Input price
$1.00 / 1M tokens
Output price
$3.20 / 1M tokens
Cache read
$0.20 / 1M tokens
Cache write
Free
Parameters
754B (753,864,139,008)
Downloads
900K in the last 30 days
Likes
2.1K
Access to weights
Open download
Released
Feb 12, 2026
Knowledge cutoff
—
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
777/1040
Open Z.ai docsWeights on Hugging FaceQuality 70Where to run it 50Evolution 4/7Race it 71 tok/sMeet its creatureBattle Qwen3.5 122B-A10B

License read from the model’s Hugging Face card. Specs from models.dev, downloads from Hugging Face, last changed Oct 18, 2026. Official source: docs.z.ai.

How good is it?

Public leaderboard scores for GLM-5, refreshed daily from Epoch AI and LMArena.

Top 30% of the 277 models on the Epoch Capabilities Index: #84.

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

Benchmarks Epoch AI runs

Scores from Epoch AI and 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

46 providers sell GLM-5 through an API, and 4 Hugging Face hosts serve it. Prices are per million tokens, cheapest first.

API providers

ProviderInputOutputContext
Alibaba Coding PlanFreeglm-5FreeFree203K
Alibaba Coding Plan (China)Freeglm-5FreeFree203K
Alibaba Token PlanFreeglm-5FreeFree203K
Alibaba Token Plan (China)Freeglm-5FreeFree203K
SCNet Token PlanFreeGLM-5FreeFree205K
Tencent Coding Plan (China)Freeglm-5FreeFree203K
VultrCheapest paidglm-5.x-menthol$0.40$1.75203K
NanoGPTz-ai/glm-5$0.60$1.90200K
GMI Cloudzai-org/GLM-5-FP8$0.60$1.92203K
Deep Infrazai-org/GLM-5$0.60$2.08203K
Show 36 more providers
ProviderInputOutputContext
DevPass (LLM Gateway)glm-5$0.72$2.30203K
LLM Gatewayembercloud/glm-5$0.72$2.30203K
DInferenceglm-5$0.75$2.40200K
SiliconFlowzai-org/GLM-5$0.95$2.55205K
Meganovazai-org/GLM-5$0.80$2.56203K
Alibaba (China)glm-5$0.57$2.58203K
ZenMuxz-ai/glm-5$0.58$2.60200K
302.AIglm-5$0.60$2.60205K
CrossModelz-ai/glm-5$0.60$3.00200K
Basetenzai-org/GLM-5$0.95$3.15203K
FastRouterz-ai/glm-5$0.95$3.15205K
Abacuszai-org/GLM-5$1.00$3.20205K
Amazon Bedrockzai.glm-5$1.00$3.20203K
DigitalOceanglm-5$1.00$3.2064K
Eden AIzai/glm-5$1.00$3.20203K
Impossiblzai/glm-5$1.00$3.20205K
Kilo Gatewayz-ai/glm-5$1.00$3.20203K
Merge Gatewayzai/glm-5$1.00$3.20200K
Novita AIzai-org/glm-5$1.00$3.20203K
Ofoxz-ai/glm-5$1.00$3.20205K
OpenCodeglm-5$1.00$3.20205K
OpenRouterz-ai/glm-5$1.00$3.20205K
OrcaRouterz-ai/glm-5$1.00$3.20205K
Poenovita/glm-5$1.00$3.20205K
SiliconFlow (China)Pro/zai-org/GLM-5$1.00$3.20205K
Tempr Gatewayzai/glm-5$1.00$3.20205K
TensorXz-ai/glm-5$1.00$3.20203K
Together AIzai-org/GLM-5$1.00$3.20203K
Venice AIzai-org-glm-5$1.00$3.20198K
Vercel AI Gatewayzai/glm-5$1.00$3.20203K
Vertexzai-org/glm-5-maas$1.00$3.20200K
Z.AIOfficialglm-5$1.00$3.20205K
Zhipu AIglm-5$1.00$3.20205K
TokenGoz-ai/glm-5$0.89$3.26205K
Meliousglm-5$1.10$3.36203K
Qiniuz-ai/glm-5——200K

Hugging Face Inference Providers

HostInputOutputContextSpeedFirst token
DeepInfraFastestTools$0.60$2.08203K71 tok/s0.9s
NovitaTools$1.00$3.20203K42 tok/s1.3s
Featherless—————
Z.aiTools———63 tok/s3.3s

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 weightsMIT1010/1040
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 weightsMIT988/1040
Z.ai

GLM-5.3-Flash-BF16

SIZE321B
Vision
TextImageDownloads160K/mo
TextLikes74

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

Open weightsMIT987/1040
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 license981/1040
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 weightsMIT924/1040
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 weightsMIT859/1040
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

PaidProprietary846/1040
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

PaidProprietary828/1040
Deck0/4
  1. Empty slot
  2. Empty slot
  3. Empty slot
  4. Empty slot