Releasesby GlyphTwo new models and more controls over generative apps
🧠 Kimi K2.7 and Fable 5 Two new models are now available from the model picker: Claude Fable 5 (Anthropic's most capable model to date) and Kimi K2.7 (an open-source model, best known for its lower token costs).
Also shipped Jul 8, 2026Hex in July 2026 →
Object metadata column is now in Public Preview
The _object_metadata column is now in Public Preview. The _object_metadata column is a hidden metadata column that exposes object-level properties for objects in cloud storage, including MIME type, ETag, user-defined key-value metadata, system-defined metadata, and object tags. It is available starting from Databricks Runtime 18.1.
Genie products now use pay-as-you-go pricing
Starting July 8, 2026 at 00:00 UTC, Genie products, including Genie Agents , Genie Code , and Genie One , are billed following a pay-as-you-go pricing model that includes 150 Databricks units (DBUs) of free large language model (LLM) usage every month, equivalent to about $10.50 in the US East region.
Google Gemini 2.5 Flash and Pro are scheduled for retirement
Google Gemini 2.5 Flash and Gemini 2.5 Pro will be retired on October 2, 2026. The recommended replacement models are Gemini 3.1 Pro or Gemini 3.5 Flash. See Deprecated and retired models for migration guidance.
Anthropic Claude Sonnet 4 is scheduled for retirement
Anthropic Claude Sonnet 4 will be retired on October 9, 2026. Claude Sonnet 4.6 is the recommended replacement. See Deprecated and retired models for migration guidance.
Restrict access to AI Functions with Unity Catalog permissions (Public Preview)
You can now use Unity Catalog permissions to restrict which task-specific AI Functions your organization can access, independent of foundation model access. Contact your account team to enable this feature. See AI Functions Unity Catalog permissions .
Genie Agents now uses pay-as-you-go pricing
Starting July 8, 2026 at 00:00 UTC, Genie Agents is billed following a pay-as-you-go pricing model that includes 150 DBUs of free large language model (LLM) usage every month, equivalent to about $10.50 in the US East region. Usage beyond the free amount is billed in DBUs, reflecting the underlying LLM models and agents that power each Genie Agents session.
More from HexEvery Hex release →
More control over credits, thread metadata, and role requests
⤴️ Spend limits for auto top-ups Forecasting credit usage is notoriously difficult, but staying in budget should be a breeze. Hex supports workspace credit pool auto top-ups with an optional monthly spend limit. This means you only pay for what you need, and you never go over budget.
Get hands-on with your generative apps
✏️ Edit generative app code in Hex Sometimes you don't need the agent, you just need to change one line. Previously, you had to prompt the agent every time you wanted to make a simple fix. Now, generative apps can open in a real code editor right inside Hex, so when you want to change a label, adjust some styling, or fix a bit of logic, you can just do it.
Hex in Figma, IAM role support for AWS, and schema refresh history!
🧑🎨 Hex Connector for Figma There’s a new connector that allows you to use the Figma agent to pull data from Hex right into your Figma files. This is great if you want to incorporate facts from your data into things like feature mockups or web page designs.
Command (line) and conquer
🤖 Hex Agent via CLI and API You can now have conversations with the Hex Agent via CLI and API, so you can set it to work from the tools and scripts you already use, not just the browser.
That question you keep asking… can just run itself
🗓️ Introducing Agent Tasks Schedule the Hex Agent to answer your recurring questions automatically and deliver results straight to Slack or email. Most insights aren't one-offs. The same questions come back every week: before the Monday standup, before the all-hands, before every sales call. Agent Tasks handles them for you.
🧪 Introducing Evals
🧪 Introducing Evals Measure Hex Agent performance and test context changes safely before they ship, all from the CLI. If you've added a guide or tweaked a semantic model, Evals helps you measure whether it actually helped , before you publish. To do that, define a suite of test questions with expected outcomes and run them against the Hex Agent.
Agent web search, model picker, and Fable 5 support
🌐 Web search for the Hex Agent Hex already knows what's happening inside your business, now the Hex agent can fill in the gaps with what's happening outside. The Hex agent can search the web, powered by Parallel. Watch video Ask the agent an open-ended question and it'll search the web and synthesize an answer alongside your data.
Tune how the agent runs
⚡ Fast mode Need an answer now ? Flip on fast mode in the model picker to push Opus models to 2.5x faster token output, at increased usage. The boost is most dramatic on long blocks of pure token output: big explanations, large blocks of code, or heavy reasoning.