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

Mar 16, 2026 · Updated Apr 25, 2026

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