Zhipu AI launches ZCode to challenge Claude Code and OpenAI Codex at a fraction of the cost
Quick Answer
Z.ai has launched ZCode, a software development tool based on GLM-5.2, designed to compete with Claude Code and OpenAI Codex at a lower cost.
Quick Take
Z.ai has launched ZCode, a software development tool based on GLM-5.2, designed to compete with Claude Code and OpenAI Codex at a lower cost. It offers a 1M-token context window for multi-step programming and a free five-day trial for new users, with remote control capabilities via popular messaging apps.
Key Points
- ZCode integrates tasks, file access, and Git changes in a single workflow.
- New users receive a free five-day trial with up to 5 million tokens daily.
- GLM-5.2 competes closely with Claude Opus, showing similar performance in benchmarks.
- Remote control of the ZCode agent is possible via Feishu, WeChat, or smartphones.
- Z.ai's pricing strategy targets developers seeking cost-effective alternatives.
📖 Reader Mode
~1 min readZ.ai is already competing with Western models on price with GLM-5.2, and now it's pushing into software development. ZCode is built around GLM-5.2 and works much like Claude Code or OpenAI's Codex. A dedicated agent handles tasks, file access, terminal output, browser context, and Git changes in a single workflow. Users can write, debug, test, and review code using natural language. According to Z.ai, the 1M-token context window allows even multi-step programming tasks without losing context.
Z.ai gives new customers a free five-day trial with up to 5 million tokens per day. Subscribers get about 1.5 times more quota through July 2026. The ZCode agent can also be controlled remotely via Feishu, WeChat, or a smartphone.
GLM-5.2 shipped in June 2026 under an MIT license. It has quickly built a following among developers who see it as competitive with pricier Western models like Claude Opus at a fraction of the cost. A hands-on comparison by Snowflake across 103 tasks shows GLM-5.2 and Opus 4.7 nearly tied after three attempts.
— Originally published at the-decoder.com
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from The Decoder
See more →
An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to run
Epoch AI's MirrorCode benchmark reveals Claude Opus 4.7 as the leader with a 56% solve rate, reconstructing a 16,000-line toolkit in 14 hours. Despite this, all models tested struggle with the most complex tasks, highlighting limitations in current AI capabilities. The single task consumed $2,600 over 19 days, raising questions about cost-effectiveness in AI development.
