AI BriefingVercel Blog news
The latest AI and developer news from Vercel Blog, with short summaries.
Visit website →TypeSafe AI Releases Probabilistic Decision Model 'Jev' on AI Gateway
TypeSafe AI has released Jev, a decision model that provides typed probabilistic answers without text generation, on AI Gateway.
Vercel Hobby Plan Changes Deployment Retention Policy to Secure Storage
The Vercel Hobby plan has reduced the number of retained deployments and applied an immediate deletion policy to prevent exceeding storage limits.
Build Start Speed Improved by 64% for Secure Compute and Static IP
Build start time for Secure Compute and Static IP was reduced by 64%, from 6.7 seconds to 2.4 seconds.
Mem0 Offers Native Integration on Vercel Marketplace
Mem0 has integrated with Vercel Marketplace to provide long-term memory capabilities for AI agents.
Is Agentic Introduces Site-Type-Specific Audit Report Customization
Is Agentic has launched an audit report feature that adjusts highlighted check items based on site type.
Delphi Deploys Python Backend 100 Times a Day with Vercel Workflows and Queues
Delphi shortened its Python backend deployment cycle to over 100 times a day by leveraging Vercel Workflows and Queues.
AI Gateway Begins Supporting Gemini 3.8 Live and Extended Thinking Models
AI Gateway has added support for Gemini 3.8 Live and Extended Thinking models, enabling real-time voice interactions.
AI SDK Harness Layer Adds Native Subscription Authentication Support
The AI SDK harness layer now supports native subscription authentication without requiring code changes.
How Featured Handles 100,000 Monthly Media Pitches on Vercel
Featured evolved into an AI PR platform where a three-person team handles 100,000 monthly media pitches through its migration to Vercel.
Tailscale Builds 'Aperture', a Customer-Facing Model Router Based on Vercel AI Gateway
Tailscale built Aperture, a customer-facing AI model router, leveraging Vercel AI Gateway and Sandbox.
Vercel Introduces Connector Permission Restrictions for Connect
Vercel has released a feature restricting the creation and management permissions of Connect connectors for Pro and Enterprise teams.
Vercel Sandbox Storage Expanded to 64GB
The default storage for Vercel Sandbox has doubled from 32GB to 64GB.
AI SDK Harness Layer Officially Supports GitHub Copilot
The AI SDK harness layer now supports GitHub Copilot via an official adapter, enabling coding agent switching without code changes.
OpenAI Agents API Integrates with Vercel Sandbox to Provide Agent Execution Environment
The OpenAI Agents API integrates with Vercel Sandbox to provide isolated code execution environments and session persistence.
Tako Search is free on AI Gateway until September 30
Vercel AI Gateway has extended the free access period for Tako Search, a model-agnostic search tool, until September 30.
Vercel Reduces P99 Latency by 91% with Shard-Based Metadata Lookup
Vercel reduced CDN metadata lookup P99 latency by 91% and improved build speeds by introducing Shard-based Group Fetching.
Serving Static Files from FastAPI Frontends via CDN
Vercel promotes FastAPI frontends and static files to the CDN at build time, serving them without function invocations.
Vercel Expands Sandbox Support to All Regions: From 4 to 20 Regions
Vercel Sandbox has expanded its support from 4 to all 20 computing regions.
DeepSeek V4.1 Flash Released on AI Gateway with Image Understanding Support
DeepSeek V4.1 Flash is now available on AI Gateway, supporting native image understanding and a 1 million token context window.
Vercel Adds Changelog Viewing and Search Features to CLI
Starting with Vercel CLI 59.6.0, users can view and search changelogs directly from the terminal.