UTC

GLM-5.3

Zhipu AI (Z.ai) · open weights · served by 169 providers · tool calling, reasoning

zhipuai/glm-5.3

Weights
Open
Released
2026-08-14
Knowledge cutoff
Not stated
Context window
1M
Hugging Face repository

zai-org/GLM-5.3 at commit ba32f8c19c, last changed 2026-10-14

Licence
glm-5.3
Access
Open download
Library
transformers
Formats
.safetensors
  • No model signature file is published with the weights.

What the Hub's scanners report

37 weight files, 37 with a scan result. No scanner reports an issue with them.

The model at this commit, its 37 weight files with their SHA-256.

Facts from the Hugging Face Hub and its file scanners (Protect AI, Cisco, Hugging Face picklescan, VirusTotal, JFrog), as of 2026-11-18. ShieldMap does not copy model cards.

Who serves it
  • 302.AIglm-5.3
  • AbliteratedLLMglm-5.3
  • AbliteratedLLMglm-5.3-fast
  • Adzuki AIglm-5.3
  • AgentRouterglm-5.3
  • ai&zai-org/glm-5.3
  • AIHubMixcoding-glm-5.3-free
  • AIHubMixglm-5.3
  • AI/ML APIzhipu/glm-5.3
  • AKI.IOglm5.3-754b
  • Alibaba (China)glm-5.3
  • Alibaba Token Planglm-5.3
  • Alibaba Token Plan (China)glm-5.3
  • Amazon Bedrockglobal.zai.glm-5.3
  • Amazon Bedrockus.zai.glm-5.3
  • Arceezai-org/glm-5.3beta
  • Augureopen-glm-5-3beta
  • Basetenzai-org/GLM-5.3
  • Basetenzai-org/GLM-5.3-Fast
  • Bothubglm-5.3
  • Boundlessglm-5.3
  • cheapaimodelglm-5.3
  • CheapestTokenglm-5.3
  • ClinePasscline-pass/glm-5.3
145 more providers

CloudCode.ONE (glm-5.3), CloudFerro Sherlock (zai-org/GLM-5.3), Cloudflare Workers AI (@cf/zai-org/glm-5.3), CommandCode (zai-org/GLM-5.3), Cortecs (glm-5.3), CrossModel (z-ai/glm-5.3), Deep Infra (zai-org/GLM-5.3), DigitalOcean (glm-5.3), Doubleword (zai-org/GLM-5.3), Eden AI (zai/glm-5.3), EmpirioLabs AI (glm-5-3), engy (glm-5.3), Entrim (zai-org/GLM-5.3), Ezkielyna (glm-5.3), Fireworks AI (accounts/fireworks/models/glm-5p3), Fireworks AI (accounts/fireworks/routers/glm-5p3-fast), Fireworks AI (accounts/fireworks/routers/glm-5p3-spot), Fireworks AI (accounts/fireworks/routers/glm-fast-latest), Fireworks AI (accounts/fireworks/routers/glm-latest), Friendli (zai-org/GLM-5.3), FrogBot (zai-glm-5-3), Gisoo (alibaba/glm-5.3), GraphN (glm-5.3), GreenPT (glm-5.3), Huawei Cloud MAAS (glm-5.3), Hugging Face (zai-org/GLM-5.3), Charm Hyper (glm-5.3), Inceptron (zai-org/GLM-5.3), Inco (glm-5.3), Inco (glm-5.3:fast), InferAll (z-ai/glm-5.3), Inference Cooperative (greenpt/glm-5.3), Inference Cooperative (tinfoil/glm-5.3), Inference APIs (zai-org/GLM-5.3), Inferris (glm-5.3), IteraCompute (z-ai/glm-5.3), JZSTOKEN (glm-5.3), Keln (zai-org/glm-5.3), Kenari (glm-5-3), Kilo Gateway (z-ai/glm-5.3), Kilo Gateway (z-ai/glm-5.3-fast), Kitani (z-ai/glm-5.3), Klavo AI (z-ai/glm-5.3), KoRouter (glm-5.3), Liquid Inference (glm-5.3), DevPass (LLM Gateway) (glm-5.3), DevPass (LLM Gateway) (glm-5.3-fast), LLM Gateway (alibaba/glm-5.3), LLM Gateway (baidu/glm-5.3), LLM Gateway (canopywave/glm-5.3), LLM Gateway (cloudflare/glm-5.3), LLM Gateway (entrim/glm-5.3), LLM Gateway (fireworks/glm-5.3), LLM Gateway (inference.net/glm-5.3), LLM Gateway (mistral/glm-5.3), LLM Gateway (novita/glm-5.3), LLM Gateway (runpod/glm-5.3), LLM Gateway (runware/glm-5.3), LLM Gateway (scx-ai-gp/glm-5.3), LLM Gateway (scx-ai-gp/glm-5.3-fast), LLM Gateway (tencent/glm-5.3), LLM Gateway (together-ai/glm-5.3), LLM Gateway (zai/glm-5.3), Lyceum (z-ai/glm-5.3), Melious (glm-5.3), Merge Gateway (zai/glm-5.3), Mistral (zai-glm-5-3), Moark (GLM-5.3), Modal (zai-org/GLM-5.3), Morph (morph-glm53-744b), NaN (glm5.3), NanoGPT (TEE/glm-5.3), NanoGPT (z-ai/glm-5.3), NanoGPT (z-ai/glm-5.3:thinking), NEAR AI Cloud (z-ai/glm-5.3), Nebius Token Factory (zai-org/GLM-5.3), Neon (glm-5-3), Neuralwatt (glm-5.3), Neuralwatt (glm-5.3-flex), Novita AI (zai-org/glm-5.3), Nvidia (z-ai/glm-5.3), Oathbreaker AI (oathbreaker-glm-5.3), Obscurify.ai (z-ai/glm-5.3), Ofox (z-ai/glm-5.3), Ollama Cloud (glm-5.3), OpenCode (glm-5.3), OpenCode Go (glm-5.3), OpenRouter (z-ai/glm-5.3), Opper (glm-5.3), OrcaRouter (z-ai/glm-5.3), Perplexity Agent (perplexity/glm-5.3), Phala (z-ai/glm-5.3), Privatemode AI (glm-5.3), Privatemode AI (glm-latest), ProxyStacks Relay (glm-5.3), Refuseless (glm-5.3-abliterated), Requesty (glm-5.3), Requesty (glm-5.3@eu), Runcrate (zai-org/GLM-5.3), RunInfra (zai-org/GLM-5.3), SambaNova (GLM-5.3), SandBase (z-ai/glm-5.3), Scaleway (glm-5.3), SCNet Token Plan (GLM-5.3), SCX.ai (GLM-5.3), SiliconFlow (zai-org/GLM-5.3), SiliconFlow (China) (zai-org/GLM-5.3), Standard Compute (z-ai/glm-5.3), Subconscious (subconscious/glm-5.3-marathon), Synthetic (hf:zai-org/GLM-5.3), Synthorai (glm-5.3), TeamoRouter (glm-5.3), Tencent Token Plan (glm-5-3), Tencent Token Plan (glm-5.3), TensorX (z-ai/glm-5.3), Tenstorrent (zai-org/GLM-5.3), Thinking Machines (zai-org/GLM-5.3:peft:262144), Tinfoil (glm-5-3), Together AI (zai-org/GLM-5.3), TokenGo (z-ai/glm-5.3), TokenRouter (z-ai/glm-5.3-free), TrustedTokens (zai-org/GLM-5.3), Umans AI (umans-glm-5.3), Umans AI Coding Plan (umans-glm-5.3), UncensuredAI (glm-5.3-abliterated), UplinkSwitch (glm-5.3), Vancine (glm-5.3), Venice AI (z-ai-glm-5-3), Vercel AI Gateway (zai/glm-5.3), Vercel AI Gateway (zai/glm-5.3-fast), Vivgrid (glm-5.3), Volcengine Ark Coding Plan (glm-5.3), Vultr (glm-5.3), Wafer (GLM-5.3), Wally (glm-5.3-fast), CoreWeave (zai-org/GLM-5.3), Watt Cloud (GLM-5.3), Z.AI (glm-5.3), Z.AI Coding Plan (glm-5.3), Z.AI Coding Plan (glm-5.3-highspeed), ZenMux (z-ai/glm-5.3), Zhipu AI (glm-5.3), Zhipu AI Coding Plan (glm-5.3), Zhipu AI Coding Plan (glm-5.3-highspeed), Zro (glm-5.3)

Running it yourself

Open weights are loaded and served by code that has its own advisories. These inference servers and model loaders are on ShieldMap; load weights only from the publisher's own repository, and prefer safetensors over formats that can run code.

How supply-chain attacks on models work →

Sources: models.dev (MIT) and the LiteLLM model catalogue (MIT). Deprecation dates are as each platform published them and as LiteLLM records them; check the platform before you rely on one. Data as of 2026-11-22.