UTC

GLM-5

Zhipu AI (Z.ai) · open weights · served by 48 providers · tool calling, reasoning

zhipuai/glm-5

Weights
Open
Released
2026-02-12
Knowledge cutoff
Not stated
Context window
205K
Deprecation dates

When each platform deprecates GLM-5, 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 2026-06-22together_ai/zai-org/GLM-5successor: together_ai/zai-org/GLM-5.3
  • Basetendeprecated 2026-10-16baseten/zai-org/GLM-5successor: baseten/zai-org/GLM-5.3
  • Google Vertex AIdeprecated 2026-10-21vertex_ai/zai-org/glm-5-maassuccessor: vertex_ai/zai-org/glm-5.2-maas
Every upcoming deprecation →
Hugging Face repository

zai-org/GLM-5 at commit c183ef8c61, last changed 2026-08-11

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
  • Abacuszai-org/GLM-5
  • Alibaba Token Planglm-5
  • Alibaba Token Plan (China)glm-5
  • Amazon Bedrockzai.glm-5
  • CommandCodezai-org/GLM-5
  • CrossModelz-ai/glm-5
  • Deep Infrazai-org/GLM-5deprecated
  • DInferenceglm-5
  • Eden AIzai/glm-5
  • FastRouterz-ai/glm-5
  • GMI Cloudzai-org/GLM-5-FP8
  • Vertexzai-org/glm-5-maasdeprecated
  • Hugging Facezai-org/GLM-5
  • Impossiblzai/glm-5
  • Kilo Gatewayz-ai/glm-5
  • DevPass (LLM Gateway)glm-5
  • LLM Gatewayalibaba/glm-5
  • LLM Gatewaynovita/glm-5
  • LLM Gatewaytencent/glm-5
  • LLM Gatewayzai/glm-5
  • Meganovazai-org/GLM-5
  • Merge Gatewayzai/glm-5
  • NanoGPTz-ai/glm-5
24 more providers

NanoGPT (z-ai/glm-5-original), NanoGPT (z-ai/glm-5-original:thinking), NanoGPT (z-ai/glm-5:thinking), Novita AI (zai-org/glm-5), Ofox (z-ai/glm-5), OpenCode (glm-5), OpenCode (glm-5-free), OpenRouter (z-ai/glm-5), OrcaRouter (z-ai/glm-5), Poe (novita/glm-5), Qiniu (z-ai/glm-5), SCNet Token Plan (GLM-5), SiliconFlow (zai-org/GLM-5), SiliconFlow (China) (Pro/zai-org/GLM-5), Tencent Coding Plan (China) (glm-5), TensorX (z-ai/glm-5), Together AI (zai-org/GLM-5), TokenGo (z-ai/glm-5), Venice AI (zai-org-glm-5), Vercel AI Gateway (zai/glm-5), Vultr (glm-5.x-menthol), Z.AI (glm-5), ZenMux (z-ai/glm-5), Zhipu AI (glm-5)

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.