Z.ai Launches GLM-5-Turbo, Optimized for Agent Tasks from the Training Phase

Zhipu AI

Mar 16, 2026 · Updated Apr 25, 2026

Z.ai released GLM-5-Turbo, a fast GLM-5 variant optimized for agent scenarios since the training phase. It targets what agent deployments need: reliable tool calls, complex instruction decomposition, and stable execution through persistent tasks. Available via the Z.ai API and OpenRouter.

GLM-5-Turbo is a foundation model from Z.ai, the developer platform of Chinese AI company Zhipu AI, built for agent-driven environments with agent tasks as the primary training objective. It's the native model for OpenClaw, Z.ai's agentic AI platform, supporting 200K context, 128K max output, function calling, MCP integration, and thinking mode.

Most LLMs are adapted for agent use after training — GLM-5-Turbo addresses agent failure modes at the model level. Tool call failures, instruction drift in long chains, and stalled persistent tasks are the pain points agent developers actually face; this model was built around them.

Test it through the Z.ai API (glm-5-turbo) or via OpenRouter at z-ai/glm-5-turbo. The model ships as a closed-source experimental release — Z.ai plans to fold the improvements into their next open-source model.

View the full update on docs.z.ai

Z.ai

@Zai_orgMar 15

Introducing GLM-5-Turbo: A high-speed variant of GLM-5, excellent in agent-driven environments such as OpenClaw. Coding Plan Max: https://t.co/E63z53nXOX OpenRouter: https://t.co/ldgN3uiI2M API: https://t.co/13bVk0Vpup https://t.co/kNKZMDGUbm

220

View on X

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

See all AI news & updates from Zhipu AI →

Keep reading

Z.ai Launches AutoClaw for One Click Local AI Agent Deployment

Z.ai released AutoClaw, a local setup tool for the OpenClaw assistant framework that requires no API keys and keeps all data on-device. By pairing the tool with the new GLM-5-Turbo model, users can run complex multi-step agentic workflows entirely within their own infrastructure.

Fireworks AI Adds GLM 5.1 Training to Build Long Horizon Coding Agents

Fireworks AIApr 28

Fireworks AI Adds GLM 5.1 Training to Build Long Horizon Coding Agents

Fireworks AI added Z.ai's GLM 5.1 to its training platform, supporting supervised fine-tuning and direct preference optimization with a 200K context window. This allows developers to customize the flagship agentic model for multi-hour autonomous tasks without the numerical drift common in fragmented training and inference stacks.

OpenCode Integrates GLM-5.1 Into Go With Zero Data Retention Privacy

OpenCodeApr 8

OpenCode Integrates GLM-5.1 Into Go With Zero Data Retention Privacy

OpenCode added Z.ai's new GLM-5.1 model to its OpenCode Go platform, featuring a zero-retention policy for user data. This allows developers to use a frontier-level model for agentic engineering without their proprietary code being stored or used for future training.