Modeldex
Drag to turnCard front showing

Z.aiTextCommon

GLM-5.3-Flash

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

glm-5.3-flash
Type
Text
Quality
84 · Top 16% on the Epoch Capabilities Index
Context window
1,000,000 tokens
Max output
131,072 tokens
Input price
$0.15 / 1M tokens
Output price
$0.50 / 1M tokens
Cache read
$0.03 / 1M tokens
Cache write
Free
Parameters
321B (321,323,031,390)
Downloads
6.5M in the last 30 days
Likes
2.9K
Access to weights
Open download
Released
Aug 26, 2026
Knowledge cutoff
—
Takes in
Text, Image, Video, PDF
Puts out
Text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
File attachments
Yes
Access
Open weights
License
MIT
Rarity
Common
Set number
988/1040
Open Z.ai docsWeights on Hugging FaceQuality 84Where to run it 83Evolution 3/3Race it 150 tok/sMeet its creatureBattle Claude Haiku 5.5

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-5.3-Flash, refreshed daily from Epoch AI and LMArena.

Top 16% of the 277 models on the Epoch Capabilities Index: #45.

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

76 providers sell GLM-5.3-Flash through an API, and 7 Hugging Face hosts serve it. Prices are per million tokens, cheapest first.

API providers

ProviderInputOutputContext
AIHubMixFreecoding-glm-5.3-flash-freeFreeFree1M
KenariFreeglm-5-3-flashFreeFree1M
NaNFreeglm5.3-flashFreeFree1M
NvidiaFreez-ai/glm-5.3-flashFreeFree1M
OrcaRouterFreez-ai/glm-5.3-flash-freeFreeFree1M
SCNet Token PlanFreeGLM-5.3-FlashFreeFree1M
Umans AI Coding PlanFreeumans-glm-5.3-flashFreeFree1.05M
Volcengine Ark Coding PlanFreeglm-5.3-flashFreeFree1M
Z.AI Coding PlanFreeglm-5.3-flashFreeFree1M
Zhipu AI Coding PlanFreeglm-5.3-flashFreeFree1M
Show 66 more providers
ProviderInputOutputContext
TokenGoCheapest paidz-ai/glm-5.3-flash$0.075$0.0251M
Pareto Inferencez-ai/glm-5.3-flash$0.03$0.101M
OpenRouterz-ai/glm-5.3-flash$0.048$0.201.05M
CrofAIglm-5.3-flash$0.07$0.221M
302.AIglm-5.3-flash$0.075$0.251M
EmpirioLabs AIglm-5-3-flash$0.075$0.251M
DevPass (LLM Gateway)glm-5.3-flash$0.088$0.251.05M
LLM Gatewayscx-ai-gp/glm-5.3-flash$0.088$0.251.05M
NanoGPTz-ai/glm-5.3-flash$0.10$0.301.05M
IteraComputez-ai/glm-5.3-flash$0.099$0.351.05M
Cortecsglm-5.3-flash$0.10$0.351.05M
Vultrglm-5.3-flash$0.10$0.351.05M
RunInfrazai-org/GLM-5.3-Flash$0.10$0.401.05M
Boundlessglm-5.3-flash$0.12$0.401.05M
Vancineglm-5.3-flash$0.12$0.401M
Volcengine Arkglm-5-3-flash-260828$0.12$0.421M
Bothubglm-5.3-flash$0.12$0.441M
engyglm-5.3-flash$0.14$0.45328K
Meliousglm-5.3-flash$0.12$0.461M
NEAR AI Cloudz-ai/glm-5.3-flash$0.08$0.501M
Standard Computez-ai/glm-5.3-flash$0.08$0.501M
ai&zai-org/glm-5.3-flash$0.15$0.501.05M
Basetenzai-org/GLM-5.3-Flash$0.15$0.501.05M
ClinePasscline-pass/glm-5.3-flash$0.15$0.501M
Cloudflare Workers AI@cf/zai-org/glm-5.3-flash$0.15$0.501.05M
CommandCodez-ai/glm-5.3-flash$0.15$0.501M
CoreWeavezai-org/GLM-5.3-Flash$0.15$0.501.05M
CrossModelz-ai/glm-5.3-flash$0.15$0.501M
Deep Infrazai-org/GLM-5.3-Flash$0.15$0.501.05M
DigitalOceanglm-5.3-flash$0.15$0.501.05M
Eden AIzai/glm-5.3-flash$0.15$0.501.05M
Fireworks AIaccounts/fireworks/models/glm-5p3-flash$0.15$0.501.05M
Friendlizai-org/GLM-5.3-Flash$0.15$0.501.05M
Incoglm-5.3-flash:fast$0.15$0.501M
Kilo Gatewayz-ai/glm-5.3-flash$0.15$0.501.05M
Merge Gatewayzai/glm-5.3-flash$0.15$0.501M
Nebius Token Factoryzai-org/GLM-5.3-Flash$0.15$0.501.02M
Neonglm-5-3-flash$0.15$0.501.05M
Neuralwattglm-5.3-flash$0.15$0.501.05M
Novita AIzai-org/glm-5.3-flash$0.15$0.501.05M
Ofoxz-ai/glm-5.3-flash$0.15$0.501M
Ollama Cloudglm-5.3-flash$0.15$0.501M
OpenCodeglm-5.3-flash$0.15$0.501M
OpenCode Goglm-5.3-flash$0.15$0.501M
Prime Inferencez-ai/glm-5.3-flash$0.15$0.501.05M
SiliconFlowzai-org/GLM-5.3-Flash$0.15$0.501.05M
Synthetichf:zai-org/GLM-5.3-Flash$0.15$0.50524K
Tempr Gatewayzai/glm-5.3-flash$0.15$0.501M
Together AIzai-org/GLM-5.3-Flash$0.15$0.501.05M
Umans AIumans-glm-5.3-flash$0.15$0.501.05M
Venice AIz-ai-glm-5-3-flash$0.15$0.501.05M
Vercel AI Gatewayzai/glm-5.3-flash$0.15$0.501M
Vivgridglm-5.3-flash$0.15$0.501M
Z.AIOfficialglm-5.3-flash$0.15$0.501M
ZenMuxz-ai/glm-5.3-flash$0.15$0.501M
Zhipu AIglm-5.3-flash$0.15$0.501M
Opperglm-5.3-flash$0.20$0.501M
TensorXz-ai/glm-5.3-flash$0.20$0.501.05M
GreenPTglm-5.3-flash$0.13$0.511M
Charm Hyperglm-5.3-flash$0.16$0.541.05M
above.devglm-5.3-flash$0.17$0.551M
Berget.AIzai-org/GLM-5.3-Flash$0.29$0.581.05M
Requestyglm-5.3-flash$0.20$0.601M
AI/ML APIz-ai/glm-5.3-flash$0.20$0.651.05M
Privatemode AIglm-5.3-flash$0.23$0.751M
Modalzai-org/GLM-5.3-Flash$0.45$1.501M

Hugging Face Inference Providers

HostInputOutputContextSpeedFirst token
BasetenFastestTools$0.15$0.501.05M150 tok/s0.2s
DeepInfraTools$0.15$0.501.05M61 tok/s0.5s
NovitaTools$0.15$0.501.05M63 tok/s1.8s
Together AITools$0.15$0.501.05M140 tok/s0.2s
Featherless—————
FireworksTools——1.05M136 tok/s0.4s
Z.aiTools———57 tok/s2.1s

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-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
Z.ai

GLM-5

CTX205K
70Quality
Reasoning · Tools
TextInput$1/M
TextOutput$3.20/M

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

Open weightsMIT777/1040
Deck0/4
  1. Empty slot
  2. Empty slot
  3. Empty slot
  4. Empty slot