Z.ai's flagship model. Use glm-5.3 in AdaL for long-horizon coding with 1M context, flexible effort, and open-source weights.
Get StartedRun /model and pick GLM-5.3 · $1.40/M input · $4.40/M output
Key capabilities and pricing
Recommended in AdaL for extended engineering sessions with 1M context.
Seven effort levels from none to max — fine-grained speed/quality control.
1M token context for large codebases and long sessions.
Reliable code generation and tool use.
Open-weight model available for inspection.
Competitive pricing for a 1M-context flagship.
Available in AdaL CLI and Desktop through the model selector
Use the coding environment where AdaL already understands your repo, tools, and task context.
Open the model selector and choose your model from the list.
Ask AdaL to inspect, plan, edit, test, and review with your chosen model powering the agent loop.
Key details about GLM-5.3
"GLM-5.3 is our flagship model for long-horizon coding with open-source weights."
Z.ai
"Use GLM-5.3 for extended coding sessions where 1M context and fine-grained effort control matter."
AdaL
"MIT-licensed weights — inspect, fine-tune, or self-host."
Open source
"Available now in AdaL CLI and Desktop."
Availability
Open AdaL CLI or Desktop, run /model, and choose GLM-5.3.
Get Started with AdaL