GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.
Modalities
In / Out Price
$0.60 / $1.92per 1M
Context
205K
Released
Feb 11, 2026
GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models.
GLM 5 costs $0.60/M input tokens and $1.92/M output tokens, with separate rates for Cache Read at $0.12/M tokens.
GLM 5 has a 204,800 token context window. It supports up to 128,000 completion tokens.
Yes. GLM 5 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
GLM 5 is served by 11 providers on OpenRouter: StreamLake, GMICloud, DeepInfra, Baidu Qianfan, DigitalOcean, SiliconFlow, AtlasCloud, Amazon Bedrock and 3 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.
GLM 5 was released on February 11, 2026.