Vercel News

Zero Data Retention on AI Gateway

8 Apr 2026

Building with multiple AI models means wrestling with fragmented data policies. With many different model providers, it's not just fragmented, it's just too much time spent on the wrong things. You

Optimizing Vercel Sandbox snapshots

7 Apr 2026

When we recently shipped [filesystem snapshots](https://vercel.com/changelog/filesystem-snapshots-supported-on-vercel-sandboxes) in Vercel Sandbox to let teams capture and restore a sandbox's

How Waldium made a blog platform work for humans and AI alike

7 Apr 2026

[Waldium](https://www.waldium.com) is a two-person, YC-backed startup that built an agentic CMS for businesses. Co-founded by Amrutha Gujjar and CTO Shivam Singhal, the platform automates content

How FLORA shipped a creative agent on Vercel's AI stack

7 Apr 2026

### FLORA on Vercel - 2x faster to production with their generation system - Zero infrastructure debates after migration - 50+ image models orchestrated * * * A seasonal fashion launch is a story,

Agent responsibly

7 Apr 2026

*The following is based on an internal talk given at Vercel. We're sharing it publicly because the problem it describes isn't unique to us, and the framework is useful for any team shipping with

Making Turborepo 96% faster with agents, sandboxes, and humans

7 Apr 2026

[Turborepo](https://turborepo.dev/blog/2-9) is now 81-91% faster to compute its task graph in our repositories, scaling with repo size. On our 1,000+ package monorepo, `turbo run` now feels instant.

Unified reporting for all AI Gateway usage

7 Apr 2026

If you're shipping AI features, you already have usage data. The problem is that it's split across providers, keys, and dashboards, so it's hard to answer basic questions before the bill shows up.

new.website joins forces with v0

7 Apr 2026

v0 and new.website have joined forces to accelerate our vision of helping anyone ship complete, production-ready software with AI. new.website was founded to make it effortless to create beautiful

SERHANT.'s playbook for rapid AI iteration

7 Apr 2026

## Impact at a glance - Started with Next.js on Vercel, which made it easier to expand to a React Native iOS app without rebuilding their backend - Engineers focus on AI design and iteration instead

Build knowledge agents without embeddings

7 Apr 2026

Most knowledge agents start the same way. You pick a vector database, then build a chunking pipeline. You choose an embedding model, then tune retrieval parameters. Weeks later, your agent answers a

Two startups at global scale without DevOps

7 Apr 2026

Leonardo.AI processes more than 4.5 million images every day across cities worldwide, and Relevance AI's agents run autonomously across time zones, touching Salesforce, HubSpot, Slack, and dozens of

Chat SDK brings agents to your users

7 Apr 2026

In early January, we gave the entire company a challenge: figure out how to multiply your output. People created agents. Mostly chat bots, but dedicated ones, purpose-built for real workflow

360 billion tokens, 3 million customers, 6 engineers

7 Apr 2026

## Impact at a glance - Durable ships new production agents to customers in a single day - AI features and agents serve ~1.1B tokens per day (360B per year) - 10x leverage for every engineer,

Meet the 2026 Vercel AI Accelerator Cohort

7 Apr 2026

The Vercel AI Accelerator is back, and this year we selected 39 early-stage teams from across the US, Europe, Asia, and Latin America to build with us for six weeks. The next generation of AI

Introducing the AI Gateway

7 Apr 2026

**Note**: This blog is outdated, please reference [this page](https://vercel.com/ai-gateway) for the latest information or read the docs [here](https://vercel.com/docs/ai-gateway). The Vercel AI

Team-wide Zero Data Retention and prompt training controls now on AI Gateway

7 Apr 2026

AI Gateway now supports Zero Data Retention (ZDR) at the team level, removing the need to configure opt-outs or reach agreements with each provider individually. It routes requests only to providers

Vercel CLI commands now scoped to local directory

7 Apr 2026

Commands like `vc project ls` and `vc domains ls` now automatically use the scope of your linked local directory instead of defaulting to your global team. Previously, querying projects or domains

Query and manage Marketplace databases from the dashboard

7 Apr 2026

You can now run SQL queries, view and edit data, and inspect your database schema directly from the Vercel dashboard. This capability is available for supported marketplace database integrations,

Custom Class Serialization in Workflow SDK

7 Apr 2026

Workflow SDK now supports custom class serialization, letting you pass your own class instances between workflow and step functions. Workflow SDK serializes standard JavaScript types like

Build an MCP server with Nuxt

7 Apr 2026

Developers building AI features with [Nuxt](https://nuxt.com/) can now create Model Context Protocol (MCP) servers directly within their applications using the [Nuxt MCP

Base fee for Observability Plus removed

7 Apr 2026

We've eliminated the $10 base fee for Observability Plus for all customers. We now only charge you for the observability events collected. [Observability

Qwen 3.6 Plus on AI Gateway

7 Apr 2026

Qwen 3.6 Plus from Alibaba is now available on [Vercel AI Gateway](https://vercel.com/ai-gateway). Compared to Qwen 3.5 Plus, this model adds stronger agentic coding capabilities, from frontend

Gemma 4 on AI Gateway

7 Apr 2026

Gemma 4 26B (MoE) and 31B (Dense) from Google are now available on [Vercel AI Gateway](https://vercel.com/ai-gateway). Built on the same architecture as Gemini 3, both open models support

Zero-configuration Go backend support

7 Apr 2026

Go API backends can now be deployed on Vercel with zero-configuration deployment. Vercel now recognizes Go servers as first-class backends and automatically provisions the right resources and

Chat SDK adds Zernio support

7 Apr 2026

Chat SDK now supports [Zernio](https://zernio.com/), a unified social media API, with the new [Zernio adapter](https://chat-sdk.dev/adapters/zernio). This is an official vendor adapter built and

GLM 5V Turbo on AI Gateway

7 Apr 2026

GLM 5V Turbo from Z.ai is now available on [Vercel AI Gateway](https://vercel.com/ai-gateway). GLM 5V Turbo is a multimodal coding model that turns screenshots and designs into code, debugs

Transfer Marketplace resources between teams

7 Apr 2026

You can now transfer Marketplace resources between teams directly from the Vercel dashboard without relying on the API. This simplifies resource management during team or project changes. Both owner

Vercel CDN now respects Cache-Control headers from external origins by default

7 Apr 2026

New Vercel projects will honor `cache-control` [headers](https://vercel.com/docs/caching/cache-control-headers#behavior) by default when proxying requests to external origins, starting April 6th.

Vercel plugin now supported on OpenAI Codex and Codex CLI

7 Apr 2026

The [Vercel plugin](https://vercel.com/changelog/introducing-vercel-plugin-for-coding-agents) now supports OpenAI Codex and the Codex CLI. With the plugin, teams can access over 39 platform skills,

Automatic persistence now in beta on Vercel Sandbox

7 Apr 2026

[Vercel Sandboxes](https://vercel.com/docs/vercel-sandbox) can now automatically save their filesystem state when stopped and restore it when resumed. This removes the need for manual snapshots,

Vercel Sandboxes now allow unique, customizable names

7 Apr 2026

[Vercel Sandboxes](https://vercel.com/docs/vercel-sandbox) created with the latest beta package will now have a unique, customizable name within your project, replacing the previous ID-based

Chat SDK now supports concurrent message handling

7 Apr 2026

[Chat SDK](https://chat-sdk.dev/) now lets you control what happens when a new message arrives before a previous one finishes processing, with the new `concurrency` option for the Chat class. Four

Chat SDK now supports scheduled Slack messages

7 Apr 2026

[Chat SDK](https://chat-sdk.dev/) now supports scheduled messages on Slack, allowing you to deliver a message at a future time. Use `thread.schedule()` and pass your message and a `postAt` date,

Elastic build machines now available in beta

7 Apr 2026

Elastic build machines are now available in beta for all paid plans, giving teams control over build performance without project-level micromanagement. You can configure elastic builds at the team or

Enterprise teams can now set their default build machine

7 Apr 2026

Enterprise team owners can now set a default build machine at the team level. This setting automatically applies to newly created projects, though you can still override it on a per-project basis.

Activity Log now available in Vercel CLI

7 Apr 2026

The [activity log](https://vercel.com/docs/activity-log) provides a list of all activities on a team, along with the user who performed the event, the type of event, and time. We've now added the

View specific error codes in runtime logs

7 Apr 2026

You can now view specific error codes in runtime logs. [Runtime logs](https://vercel.com/docs/logs/runtime) helps you view and troubleshoot errors in your applications on Vercel. In addition to the

Sandbox SDK adds file permission control

7 Apr 2026

[Vercel Sandbox SDK](https://www.npmjs.com/package/@vercel/sandbox) `1.9.0` now supports setting file permissions directly when writing files. By passing a `mode` property to the `writeFiles` API,

MiniMax M2.7 is live on AI Gateway

7 Apr 2026

MiniMax M2.7 is now available on [Vercel AI Gateway](https://vercel.com/ai-gateway) in two variants: standard and high-speed. M2.7 is a major step up from previous M2-series models in software

End-to-end encryption for Vercel Workflow

7 Apr 2026

Vercel Workflow now encrypts all user data end-to-end without requiring any code changes. Workflow inputs, step arguments, return values, hook payloads, and stream data are automatically encrypted

New GitHub App permissions for Actions and Workflows

7 Apr 2026

The [Vercel GitHub App](https://github.com/apps/vercel) now requests two additional repository permissions on install: **Actions** (`read`) and **Workflows** (`read` & `write`). These

Try Grok 4.20 on AI Gateway

7 Apr 2026

Grok 4.20 is now available on [Vercel AI Gateway](https://vercel.com/ai-gateway) in three variants: Reasoning, Non-Reasoning, and Multi-Agent. As xAI's newest flagship model, Grok 4.20 delivers

Inception Mercury 2 is live on AI Gateway

7 Apr 2026

Mercury 2 from Inception is now available on [Vercel AI Gateway](https://vercel.com/ai-gateway). Mercury 2 from Inception is now available on AI Gateway. Mercury 2 delivers reasoning-grade quality

Custom reporting now available on AI Gateway

7 Apr 2026

Custom Reporting for [AI Gateway](https://vercel.com/ai-gateway) is now available in beta for Pro and Enterprise users. Slice your AI spend by any dimension: model, provider, user, custom tags, or

58% of PRs in our largest monorepo merge without human review

7 Apr 2026

One of our oldest and largest Next.js apps is a monorepo that contains multiple critical properties: the Vercel marketing site, our docs, the sign-up flow, dashboards, and internal tooling. The repo

Vercel Queues now supports 7-day message TTL

1 Apr 2026

Axios package compromise and remediation steps

31 Mar 2026

Vercel Open Source Program: Winter 2026 cohort

17 Mar 2026

In April, we launched the Vercel Open Source Program (https://vercel.com/open-source-program) to give maintainers the resources, credits, and support they need to ship faster and scale confidently.

How Notion Workers run untrusted code at scale with Vercel Sandbox

12 Mar 2026

Notion Workers let you write and deploy code to give Custom Agents new powers: sync external data, trigger automations, call any API. With Workers, developers can build agents that sync CRM data on a

How we run Vercel's CDN in front of Discourse

10 Mar 2026

Vercel's CDN can front any application, not just those deployed natively on the platform, and it's simple to set up. This allows you to add firewall protection, DDoS mitigation, and observability to