模型目录

GLM-5.3-Flash 是 z.ai 国际站 (api.z.ai) 轻量高速模型, 原生多模态输入 (图片/视频), 面向高效编码与长程 agent 任务. 1M context, 常驻 thinking (不可关闭, 支持 low/high/max 三档 reasoning effort), 支持 prompt caching / tool calling / web search. 通过 OpenAI-compatible + Anthropic 双协议接入 (无 responses 端点).

GLM-5.3 是 z.ai 国际站 (api.z.ai) 旗舰推理模型, 在 GLM-5.2 基础上提升编码能力与性能/token 效率平衡, 面向复杂软件工程与长程 agent 任务. 1M context, 常驻 thinking (不可关闭, 支持 low/high/max 三档 reasoning effort), 支持 prompt caching / tool calling / web search. 通过 OpenAI-compatible + Anthropic 双协议接入 (无 responses 端点).

GLM-5.2 是 z.ai 国际站 (api.z.ai) 旗舰推理模型, MoE 架构 open-weights, 1M context, 内嵌 thinking (reasoning_content), 支持 prompt caching / tool calling / web search. 强编码与长程自治执行. 通过 OpenAI-compatible + Anthropic 双协议接入 (无 responses 端点).

GLM-5V-Turbo is Z.AI’s first multimodal coding foundation model, built for vision-based coding tasks. It can natively process multimodal inputs such as images, video, and text, while also excelling at long-horizon planning, complex coding, and action execution.

GLM-5-Turbo is a foundation model deeply optimized for the OpenClaw scenario. It has been specifically optimized for the core requirements of OpenClaw tasks since the training phase, enhancing key capabilities such as tool invocation, command following, timed and persistent tasks, and long-chain execution.

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.

As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning, and tool collaboration, and has achieved leading performance among open-source models of the same size on several current public benchmark leaderboards.

Zhipu GLM-4.7 - latest flagship model with advanced reasoning, 128K context, and web search capabilities. Best-in-class Chinese language understanding.

Zhipu GLM-4.6 with 128K context and strong instruction following. Excellent balance of performance and cost for Chinese language tasks.