Model details
GLM-5 is designed for agentic engineering, where coding, planning, and tool use must remain productive across complex, long-running tasks. Its architecture builds on the GLM family’s mixture-of-experts and long-context direction, while the model’s multiple thinking modes let users balance deeper reasoning against response time. This makes it particularly relevant to repository-scale programming and workflows that require an agent to sustain context, make plans, and call external tools.
Z.AI positions GLM-5 as a new-generation foundation model with leading open-source coding and agent performance, while emphasizing practical engineering reliability over isolated benchmark gains. Its open-weight availability supports local experimentation and adaptation, and its reasoning and tool-oriented design suits developers building coding assistants, systems-engineering agents, and other multi-step automation. The model is less suited to lightweight interactions where maximum reasoning depth would add unnecessary delay.
Transparent token rates
Rates are shown per one million tokens. Combined means one million input plus one million output tokens.
OpenRouter
Z.ai's **GLM-5.2** launched in mid June with a **1M-token** context window and two reasoning effort levels, according to DataCamp and the Ollama README. Tech Stackups ran a head-to-head test building a 3D platformer in raw WebGL and reports that **Claude Opus** completed the task in **33m 30s** while **GLM-5.2** took *
OpenRouter
The news blog specialized in Japanese culture, odd news, gadgets and all other funny stuffs. Updated everyday.
OpenRouter
Discover more about what's new at AWS with Minimax M2.5 and GLM 5 models now available on Amazon Bedrock
OpenRouter
One of the most impressive open source models ever released.
OpenRouter
SINGAPORE, February 16, 2026--GLM-5, newly released as open source, signals a broader shift in artificial intelligence. Large language models are moving beyond generating code snippets or interface prototypes toward building complete systems and carrying out complex, end-to-end tasks. The change marks a transition from
OpenRouter
Compare GLM 5.1 from Z.ai to other AI models on key metrics including benchmarks, price, context length, and other model features.
OpenRouter
GLM 5.2 is a large-scale reasoning model from Z.ai. $0.98 per million input tokens, $3.08 per million output tokens. 1,048,576 token context window. Higher uptime with 20 providers. Includes independent benchmarks from Artificial Analysis.
OpenRouter
GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. $1.20 per million input tokens, $4 per million output tokens. 202,752 token context window, maximum output of 131,072 tokens. Includes independent benchmarks from Artificial Analysis.
