Model Serving now supports DeepSeek V4 Pro (0813) as a Databricks hosted model in the us west 2 region.
Model Serving now supports DeepSeek V4 Pro (0813) as a Databricks hosted model in the us west 2 region. This large mixture of experts language model supports reasoning and function calling for complex coding and agentic workflows. You can access this model using Foundation Model APIs.
For production workloads, Databricks recommends priority pay per token, also referred to as priority mode, for latency sensitive workloads that need more consistent performance under load.
Model Serving now supports DeepSeek V4 Pro (0813) as a Databricks hosted model in the us west 2 region. This large mixture of experts language model supports reasoning and function calling for complex coding and agentic workflows.
Read the full documentation ↗