UTC

GLM-4.6

Zhipu AI (Z.ai) · open weights · served by 31 providers · tool calling, reasoning

zhipuai/glm-4.6

Weights
Open
Released
2025-09-30
Knowledge cutoff
2025-04
Context window
205K
Deprecation dates

When each platform deprecates GLM-4.6, 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 2026-07-29together_ai/zai-org/GLM-4.6successor: together_ai/zai-org/GLM-5.3
  • Basetendeprecated 2026-10-16baseten/zai-org/GLM-4.6successor: baseten/zai-org/GLM-5.3
Every upcoming deprecation →
Hugging Face repository

zai-org/GLM-4.6 at commit be72194883, last changed 2025-09-30

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

What the Hub's scanners report

45 weight files, 0 with a scan result. No scanner reports an issue with them.

The model at this commit, its 45 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-4.6
  • Abacuszai-org/GLM-4.6
  • AIHubMixglm-4.6
  • Deep Infrazai-org/GLM-4.6
  • Eden AIzai/glm-4.6
  • Heliconeglm-4.6
  • Hugging Facezai-org/GLM-4.6
  • Impossiblzai/glm-4.6
  • IO.NETzai-org/GLM-4.6
  • Kilo Gatewayz-ai/glm-4.6
  • DevPass (LLM Gateway)glm-4.6
  • LLM Gatewaynovita/glm-4.6
  • LLM Gatewayzai/glm-4.6
  • Meganovazai-org/GLM-4.6
  • Merge Gatewayzai/glm-4.6
  • ModelScopeZhipuAI/GLM-4.6
  • NanoGPTz-ai/glm-4.6
  • NanoGPTz-ai/glm-4.6-original
  • NanoGPTz-ai/glm-4.6:thinking
  • Novita AIzai-org/glm-4.6
  • Ofoxz-ai/glm-4.6
  • OpenCodeglm-4.6deprecated
  • OpenRouterz-ai/glm-4.6
  • OrcaRouterz-ai/glm-4.6
7 more providers

Poe (novita/glm-4.6), Qiniu (z-ai/glm-4.6), Venice AI (zai-org-glm-4.6), Vercel AI Gateway (zai/glm-4.6), Z.AI (glm-4.6), ZenMux (z-ai/glm-4.6), Zhipu AI (glm-4.6)

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.