OpenAI fashions, together with GPT-5.1, at the moment are usually out there on the Databricks Information Intelligence Platform. This launch is a key a part of our Week of Brokers, showcasing new releases that will help you construct, govern, and deploy highly effective AI brokers securely at scale.
With GA, OpenAI fashions on Databricks attain full manufacturing readiness. This marks one other step towards Databricks’ mission to make main basis fashions out there natively inside a single, ruled platform so enterprises can construct high-quality brokers that motive over their knowledge securely and at scale.
Construct with OpenAI, The place Your Information Lives
Now, enterprises can deliver OpenAI’s frontier intelligence on to their ruled knowledge, with out shifting knowledge round. This integration permits techniques that not solely generate language but in addition perceive, motive, and act on enterprise knowledge in actual time.
Groups are already utilizing this mixture to:
- Enrich thousands and thousands of help tickets or product evaluations with automated insights
- Generate structured summaries and motion gadgets from assembly transcripts or contracts
- Construct conversational brokers that reply questions grounded in stay Delta knowledge
What You Can Do with OpenAI Fashions on Databricks?
Discover Fashions within the AI Playground
The AI Playground affords the quickest path to start out experimenting. Open the Playground tab, select an OpenAI mannequin, and examine GPT-5.1, GPT-5, GPT-mini, and GPT-nano facet by facet. Modify temperature, max tokens, and different parameters interactively, then export the very best immediate instantly right into a pocket book or SQL cell.
Apply OpenAI Fashions to Your Information
OpenAI fashions can be utilized like a built-in operator in SQL or Python, making it easy to research contracts, PDFs, transcripts, or photos instantly the place your knowledge lives. While you run these queries, Databricks routinely scales OpenAI mannequin capability within the backend to deal with every little thing from a handful of rows to thousands and thousands, making certain quick, dependable outcomes with out additional setup.
Automate Doc Intelligence
OpenAI fashions may be chained into Lakeflow Declarative Pipelines to construct GenAI ETL, ingesting knowledge from techniques like Dynamics 365, making use of AI transformations resembling summarization or classification, and orchestrating the circulation with built-in governance and observability. This sample scales to thousands and thousands of paperwork, creating end-to-end document-intelligence pipelines with lineage, auditability, and high quality monitoring in-built.
Construct Clever Brokers with OpenAI and Agent Bricks
Agent Bricks turns OpenAI fashions into clever brokers by connecting them to enterprise knowledge within the Lakehouse, vectorized information by way of Vector Search, and exterior techniques by way of MCP.
As soon as related, Agent Bricks automates immediate and mannequin optimization, selecting the right mixture for every use case and constantly enhancing efficiency by way of built-in analysis, observability, and governance.
When prepared, brokers may be securely deployed at scale, absolutely ruled by Unity Catalog and monitored by way of AI Gateway.
Govern and Monitor with AI Gateway
All OpenAI site visitors on Databricks is managed by way of AI Gateway, the unified management airplane for enterprise AI workloads. Each GPT-5.1 request is ruled, logged, and auditable — absolutely built-in with Unity Catalog. Groups achieve visibility into utilization and token spend, can implement price limits, and allow fallbacks to make API calls extra dependable.
