GLM-5.3

GLM-5.3 is Z.AI's flagship post-trained model for complex coding, long-horizon agentic work, and cybersecurity tasks. It uses the same 753B-parameter base model as GLM-5.2, with its capability gains coming from post-training. The text-only model supports a 1M-token context window, 128K maximum output, function calling, structured output, context caching, and always-on thinking with low, high, and max reasoning-effort levels. Z.AI launched GLM-5.3 through ZCode and the GLM Coding Plan on August 14, 2026, then published first-party API access and per-token pricing on August 18, while announcing that open weights would follow after a two-week safety evaluation and hardening period.