OpenRouter exposes GLM-5 Turbo through model ID z-ai/glm-5-turbo. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-06-15. Next refresh: weekly.
Quick Start
- 1
- 2Use the OpenRouter SDK or REST API to call
z-ai/glm-5-turbo— see the documentation for request format. - 3
Code Examples
Pricing on OpenRouter
| Type | Price (per 1M) |
|---|---|
| Input tokens | $1.20 |
| Output tokens | $4.00 |
Capabilities
ReasoningJSON / Tool useStructured Outputs
About GLM-5 Turbo
Purpose-built variant of GLM-5 optimized for agent orchestration and complex automated workflows. Features native agent-friendly training emphasizing tool use, command following, and persistent task execution. Designed for OpenClaw (Lobster Agent) workflows with ~0.67% tool-call error rate. Achieves 20% higher inference performance vs base GLM-5.
Model Specs
Released2026-03-01
Parameters744B total, 40B active
Context200k
ArchitectureMixture of Experts
Knowledge cutoff2025-11