AI BriefingVercel Blog news
The latest AI and developer news from Vercel Blog, with short summaries.
Visit website →Speed Insights Adds Free Tier
Vercel Speed Insights now offers a free tier across all plans, while the paid service has been renamed to Speed Insights Plus.
Introducing Run SDK: Safe eval for Agents
Vercel has launched the Run SDK to safely execute untrusted code.
The End of Credential Sprawl for Agents
Vercel Connect addresses agent security issues with short-lived, runtime-based tokens.
Vercel AI Gateway Offers Free Access to MiniMax M3 and M2.7
MiniMax M3 and M2.7 models are available for free on Vercel AI Gateway until September 6.
Wan 3.0 Now Available on AI Gateway
Alibaba's Wan 3.0 video model has launched on Vercel AI Gateway, offering integrated video generation capabilities.
Vercel Connect Now Generally Available on All Plans
Vercel Connect is now generally available, enabling secure connections to over 100 services using short-lived tokens at runtime.
AI Gateway Adds Support for Asynchronous Video Generation
Vercel AI Gateway has added asynchronous video generation capabilities via webhooks and polling.
Chat SDK Now Supports Slack Enterprise Grid
The Chat SDK's Slack adapter now supports Slack Enterprise Grid, enabling integration across all workspaces in an organization.
Vercel Connect Now Supports Linq
Vercel Connect added support for the Linq connector, enabling iMessage and SMS-based messaging capabilities.
Chat SDK Now Supports XChat
The Chat SDK now supports the XChat adapter, enabling the development of encrypted chat bots.
Connect Agents to Notion via Chat SDK
The new Notion adapter for the Chat SDK allows existing agents to be integrated into comment discussions on Notion pages.
Elastic Build Machines Prevent Downgrades Based on Turborepo Cache Hits
Vercel improved Elastic build machines to prevent incorrect downgrades by considering Turborepo cache hits.
Vercel Sandbox Now Generally Available Worldwide
Vercel Sandbox has launched globally across 4 regions, offering region selection and failover capabilities to reduce latency.
Environment Variables Now Use Config and Secret Types
Vercel has strengthened security management by categorizing environment variables into Config and Secret types.
Bun Runtime Now Supports Large Functions and Extended Max Duration
Vercel's Bun runtime now supports large functions up to 5GB and a maximum execution time of 30 minutes.
How Ora Benchmarks Major AI Agents on Vercel
Ora built a platform on Vercel infrastructure to compare-test major AI agents on live websites in real time.
v0 Apps Connect with Slack, Google, and Over 100 Services
Vercel launched Vercel Connect, enabling v0 apps to securely connect with over 100 third-party services.
Deployment Storage: Maintain a Rollback-Ready Deployment Environment
Vercel has launched Deployment Storage, enabling instant rollbacks by preserving deployment files.
GPT-5.6 Sol: 50% Discount at Lower Prices
OpenAI has lowered the price of GPT-5.6 Sol and is offering a 50% discount on Vercel AI Gateway until September 18.
GPT-5.6 Sol Price Drop on AI Gateway, 50% Discount Still Applies
OpenAI announced a price reduction for GPT-5.6 Sol and confirmed that the 50% discount on Vercel AI Gateway will remain in effect.