UTC

GLM-5.1

Zhipu AI (Z.ai) · open weights · served by 58 providers · tool calling, reasoning

zhipuai/glm-5.1

Weights
Open
Released
2026-04-07
Knowledge cutoff
Not stated
Context window
200K
Deprecation dates

When each platform deprecates GLM-5.1, as LiteLLM records it. Plan the move before the date: after it, the platform may stop serving the model or stop updating it.

  • Together AIdeprecated 2026-07-10together_ai/zai-org/GLM-5.1successor: together_ai/zai-org/GLM-5.3
  • friendliaideprecated 2026-11-20friendliai/zai-org/GLM-5.1successor: friendliai/zai-org/GLM-5.3
Every upcoming deprecation →
Hugging Face repository

zai-org/GLM-5.1 at commit 26e1bd6e01, last changed 2026-05-13

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

What the Hub's scanners report

34 weight files, 34 with a scan result. No scanner reports an issue with them.

The model at this commit, its 34 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-5.1
  • Abacuszai-org/GLM-5.1
  • AIHubMixalicloud-glm-5.1deprecated
  • AIHubMixcoding-glm-5.1
  • AIHubMixcoding-glm-5.1-free
  • AIHubMixzai-glm-5.1deprecated
  • Alibaba Token Planglm-5.1
  • Alibaba Token Plan (China)glm-5.1
  • Aurikoglm-5.1
  • Chuteszai-org/GLM-5.1-TEE
  • CrossModelz-ai/glm-5.1
  • Crusoezai/GLM-5.1deprecated
  • Deep Infrazai-org/GLM-5.1deprecated
  • DInferenceglm-5.1deprecated
  • EBCloudGLM-5.1
  • Eden AIzai/glm-5.1
  • EmpirioLabs AIglm-5-1
  • FastRouterz-ai/glm-5.1
  • FrogBotzai-glm-5-1deprecated
  • GMI Cloudzai-org/GLM-5.1-FP8
  • GreenPTglm-5.1deprecated
  • HPC-AIzai-org/glm-5.1
  • Huawei Cloud MAASglm-5.1
  • Hugging Facezai-org/GLM-5.1
34 more providers

Impossibl (zai/glm-5.1), Jalapeno Cloud (GLM-5.1), Kilo Gateway (z-ai/glm-5.1), DevPass (LLM Gateway) (glm-5.1), LLM Gateway (alibaba/glm-5.1), LLM Gateway (baidu/glm-5.1), LLM Gateway (novita/glm-5.1), LLM Gateway (tencent/glm-5.1), LLM Gateway (zai/glm-5.1), Merge Gateway (zai/glm-5.1), NanoGPT (TEE/glm-5.1), NanoGPT (TEE/glm-5.1-thinking), NanoGPT (z-ai/glm-5.1), NanoGPT (z-ai/glm-5.1:thinking), Novita AI (zai-org/glm-5.1), Ofox (z-ai/glm-5.1), OpenCode (glm-5.1), OpenRouter (z-ai/glm-5.1), OrcaRouter (z-ai/glm-5.1), Phala (z-ai/glm-5.1), Requesty (glm-5.1), SCNet Token Plan (GLM-5.1), SiliconFlow (zai-org/GLM-5.1), SiliconFlow (China) (Pro/zai-org/GLM-5.1), TensorX (z-ai/glm-5.1), Together AI (zai-org/GLM-5.1), TokenGo (z-ai/glm-5.1), Venice AI (zai-org-glm-5-1), Vercel AI Gateway (zai/glm-5.1), Watt Cloud (GLM-5.1), Z.AI (glm-5.1), Zenifra (zenifra/glm-5.1), ZenMux (z-ai/glm-5.1), Zhipu AI (glm-5.1)

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.