Z.aiZ.ai·💬 Text Generation

GLM 5.1

ReasoningWeb SearchE2EEfp8private
🧠 Try in Intelligence →Try on Venice.ai ↗
Quick reference
GLM 5.1 — TLDR
  • 🔒 Runs in a Trusted Execution Environment with hardware attestation.
  • 🧠 Flagship agentic-engineering model in the GLM 5 line.
  • 📏 200K-token context window for long inputs.
  • 🔧 Built for coding, tool use, and agentic workflows.
  • ⚡ FP8 quantization; supports reasoning and web search.
  • 📚 Open-weight under the MIT license from Z.ai.
  • 🆕 Successor refresh following the GLM 5 release.
  • 🎯 Vendor reports long-horizon autonomous task execution.
💰 Pricing
$1.10 / $4.15
per 1M · input / output
📏 Context
200K tokens
📅 On Venice since
Apr 24, 2026
40 days ago
Provider

Z.ai, formally Knowledge Atlas Technology Joint Stock Co., Ltd., is a Chinese technology company specializing in artificial intelligence. Previously known internationally as Zhipu AI, the company rebranded to Z.ai in 2025. Its core focus is the GLM family of…

Read full profile →
11 models on Venice
10 text · 1 image
Since Apr 1, 2024

About this model

GLM 5.1 is the flagship agentic-engineering model from Z.ai (formerly Zhipu AI), here deployed inside a Trusted Execution Environment so that hardware attestation evidence can independently verify enclave identity and configuration. This privacy-oriented packaging is the distinguishing feature of this build; the underlying weights are the same ones Z.ai also ships as the standard GLM 5.1 release.

As a text model, GLM 5.1 carries a 200,000-token context window and is distributed under the permissive MIT license, with FP8 weights suitable for self-hosting. It supports reasoning, web search, and the tool-driven workflows the GLM line targets, positioning it for coding and agentic engineering tasks rather than general chat alone.

GLM 5.1 follows the GLM 5 foundation model in the same family. On its developer documentation, Z.ai describes stronger coding capabilities and longer-horizon autonomy than GLM 5, including sustained autonomous work on a single task. These are vendor-reported characterizations; independent verification of the refreshed claims was not established from the primary sources available here, so specific benchmark figures are omitted.

For lighter or faster deployments, Z.ai also offers related models in the broader catalog, including GLM 4.7 and its Flash variant GLM 4.7 Flash, giving users a range of sizes around this flagship build.

This About section is AI-generated from public sources (Claude Opus 4.8), with no human editing. It may contain inaccuracies — verify critical details against the sources listed above.

Research & Papers

Primary reference paper for this model family, sourced from the HuggingFace model card.

Data sources: Venice API · HuggingFace · Wikipedia · arXiv — enrichment updated 4d ago