Databricks releases, every cloud
- Protobuf tensor input for custom model serving endpoints (Public Preview)
Replaces JSON with serialized KServe v2 ModelInferRequest. Requires endpoints deployed after July 9, 2026.
AWS, read it on their docsAzure, read it on their docsGCP, read it on their docsSAP(not on this cloud) - Declarative Automation Bundles will soon default to use the direct deployment engine Coming soon
Replaces Terraform deployment engine, migrating bundles automatically on July 24, 2026.
AWS, read it on their docsAzure, read it on their docsGCP, read it on their docsSAP(not on this cloud) - Serve custom LLMs with Custom Model Serving (Beta)
Supports multimodal models and PEFT recipes, unlike Foundation Model APIs.
- Edits to resources in the UI now automatically update YAML
Applies to jobs and pipeline settings, see Edit bundle resources.
- Alibaba Cloud Qwen3.5 122B A10B now available as a Databricks-hosted model in Public Preview
Accessible via Foundation Model APIs, available in Public Preview.
- Databricks Asset Bundles is now Declarative Automation Bundles
Replaces Databricks Asset Bundles.
AWS, read it on their docsAzure, read it on their docsGCP, read it on their docsSAP(not on this cloud) - Run the change, do not just read it. Hands-on labs in your own Databricks workspace, graded when you submit. Browse labs
- Endpoint telemetry for custom model serving endpoints (Beta)
Stores logs, traces, and metrics in Unity Catalog Delta tables using OpenTelemetry.
- Function calling and structured output now available using the Alibaba Cloud Qwen3-Next Instruct model (Beta)
Supports Qwen3-Next 80B A3B Instruct model.
- OpenAI GPT 5 models are now generally available in Mosaic AI Model Serving
Includes GPT-5 mini and nano models.
- Alibaba Cloud Qwen3-Next Instruct now available in Beta
Supports 80B A3B Instruct in us-west-2 and ap-northeast-1 regions via pay-per-token APIs.
- Declarative Automation Bundles in the workspace is GA
Allows collaborative editing and deployment of bundle updates through the UI.
- Improved autoscaling behavior for Mosaic AI Model Serving
Ignores brief traffic surges, scaling on sustained load increases. Reduces unnecessary concurrency scaling.
- Mosaic AI Model Serving now supports OpenAI GPT 5 models (preview)
Supports GPT-5, GPT-5 mini, and GPT-5 nano models for batch inference with AI Functions.
- Anthropic Claude Opus 4.1 now available as a Databricks-hosted foundation model
Accessible via Foundation Model APIs on a pay-per-token basis.
- Route-optimized endpoints now require route-optimized URL path for querying
Requires route-optimized URL path for querying, standard workspace URL path not supported for new endpoints.
- Spark Declarative Pipelines on Lakeflow template in bundles in the workspace (Public Preview)
Creates ETL pipelines in workspace bundles using Lakeflow template. Requires New ETL pipeline setup.
Headlines, dates and product areas are Databricks' own, from the release notes published for each cloud, and every item links to the note it came from. The one-line summaries are ours. Not a Databricks product and not affiliated with Databricks, Inc.