Model Serving now supports GLM 5.3 Flash as a Databricks hosted model.
Model Serving now supports GLM 5.3 Flash as a Databricks hosted model. This natively multimodal mixture of experts (MoE) model has 320 billion total parameters and 18 billion active parameters. It supports text and image input, a 1 million token context window, reasoning, coding, and agentic tool use.
Customers are responsible for ensuring their compliance with applicable terms.
Model Serving now supports GLM 5.3 Flash as a Databricks hosted model. This natively multimodal mixture of experts (MoE) model has 320 billion total parameters and 18 billion active parameters.
Read the full documentation ↗