GLM 5.3 from Z.ai is now available on AI Gateway. GLM 5.3 has improvements vs. GLM 5.2 at complex software engineering and at agent tasks that run across many steps, and it reaches those results while producing fewer output tokens than GLM 5.2 did at the same effort level.
Z.ai also reports stronger vulnerability discovery, including reasoning across the successive stages of an exploitation chain. DeepsecBench measures that work directly, scoring how reliably a model finds security vulnerabilities in application code and what a run costs, and it covers GLM-5.3 at both high and max effort.
GLM 5.3 takes text input, with a 1M token context window and a maximum output of 128K tokens, both unchanged from GLM 5.2. It supports function calling, structured output, streaming, and context caching.
To use the model, the slug is zai/glm-5.3
:
To use it in a coding agent, run vercel ai-gateway coding-agents setup
to connect agents like Claude Code, Codex, OpenCode, Cursor, Pi, and more, then select zai/glm-5.3
inside the agent.
AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more.
AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests.