Skip to content

Databricks releases, every cloud

All GAPreviewBehavior changeDeprecationUpdate

13 releases of 1321

Last updated

  1. Custom trace views in the MLflow trace explorer are in Beta

    Genie generates views based on plain language descriptions, surfacing relevant trace fields and metrics.

    #Gen AI#MLflow
    AWS, read it on their docsAzure, read it on their docsGCP, read it on their docsSAP(unknown)
  2. Protobuf tensor input for custom model serving endpoints (Public Preview)

    Replaces JSON with serialized KServe v2 ModelInferRequest. Requires endpoints deployed after July 9, 2026.

    #Machine Learning#Model Serving
    AWS, read it on their docsAzure, read it on their docsGCP, read it on their docsSAP(not on this cloud)
  3. Serve custom LLMs with Custom Model Serving (Beta)

    Supports multimodal models and PEFT recipes, unlike Foundation Model APIs.

    #Machine Learning#Model Serving
    AWS, read it on their docsAzure, read it on their docsGCP(not on this cloud)SAP(not on this cloud)
  4. 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 AI#Model Serving
    AWS, read it on their docsAzure, read it on their docsGCP(not on this cloud)SAP(not on this cloud)
  5. Endpoint telemetry for custom model serving endpoints (Beta)

    Stores logs, traces, and metrics in Unity Catalog Delta tables using OpenTelemetry.

    #Machine Learning#Model Serving
    AWS, read it on their docsAzure, read it on their docsGCP(not on this cloud)SAP(not on this cloud)
  6. Store and query MLflow traces in Unity Catalog (Beta)

    Stores MLflow traces in Delta tables for long-term retention and analysis using OpenTelemetry format.

    #Gen AI#MLflow
    AWS, read it on their docsAzure, read it on their docsGCP(not on this cloud)SAP(unknown)
  7. Run the change, do not just read it. Hands-on labs in your own Databricks workspace, graded when you submit. Browse labs
  8. Function calling and structured output now available using the Alibaba Cloud Qwen3-Next Instruct model (Beta)

    Supports Qwen3-Next 80B A3B Instruct model.

    #Databricks AI#Model Serving
    AWS, read it on their docsAzure(not on this cloud)GCP(not on this cloud)SAP(unknown)
  9. OpenAI GPT 5 models are now generally available in Mosaic AI Model Serving

    Includes GPT-5 mini and nano models.

    #Databricks AI#Model Serving
    AWS, read it on their docsAzure(not on this cloud)GCP, read it on their docsSAP(unknown)
  10. 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.

    #Databricks AI#Model Serving
    AWS, read it on their docsAzure, read it on their docsGCP(not on this cloud)SAP(unknown)
  11. Improved autoscaling behavior for Mosaic AI Model Serving

    Ignores brief traffic surges, scaling on sustained load increases. Reduces unnecessary concurrency scaling.

    #Databricks AI#Model Serving
    AWS, read it on their docsAzure, read it on their docsGCP, read it on their docsSAP(unknown)
  12. 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.

    #Databricks AI#Model Serving
    AWS, read it on their docsAzure(not on this cloud)GCP, read it on their docsSAP(unknown)
  13. Anthropic Claude Opus 4.1 now available as a Databricks-hosted foundation model

    Accessible via Foundation Model APIs on a pay-per-token basis.

    #Model Serving
    AWS, read it on their docsAzure, read it on their docsGCP, read it on their docsSAP(unknown)
  14. 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.

    #Model Serving
    AWS, read it on their docsAzure, read it on their docsGCP, read it on their docsSAP(unknown)

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.