Release activity — 104 releases across 20 days since Jul 22, 2026. Each cell is one day; darker means more releases that day. Nothing is recorded before Jul 22, 2026. Older weeks are hidden at this screen width.
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sunday
No releases on Jul 26, 2026
1 release on Aug 2, 2026
No releases on Aug 9, 2026
No releases on Aug 16, 2026
MonMonday
8 releases on Jul 27, 2026
4 releases on Aug 3, 2026
3 releases on Aug 10, 2026
No releases on Aug 17, 2026
Tuesday
2 releases on Jul 28, 2026
5 releases on Aug 4, 2026
8 releases on Aug 11, 2026
WedWednesday
1 release on Jul 22, 2026
5 releases on Jul 29, 2026
10 releases on Aug 5, 2026
6 releases on Aug 12, 2026
Thursday
7 releases on Jul 23, 2026
11 releases on Jul 30, 2026
7 releases on Aug 6, 2026
7 releases on Aug 13, 2026
FriFriday
3 releases on Jul 24, 2026
9 releases on Jul 31, 2026
5 releases on Aug 7, 2026
1 release on Aug 14, 2026
Saturday
No releases on Jul 25, 2026
No releases on Aug 1, 2026
1 release on Aug 8, 2026
No releases on Aug 15, 2026
104 releases since Jul 22, 2026, busiest day 11No recordLessMore
Changelog
Encrypted Client Hello (ECH) is now supported on Vercel CDN
Vercel CDN now supports Encrypted Client Hello (ECH) for domains managed by Vercel DNS. ECH encrypts the Server Name Indication (SNI) in the TLS handshake, the last part of an HTTPS connection that re…
Added 1
Vercel CDN now supports Encrypted Client Hello (ECH) for domains managed by Vercel DNS
The best way to learn is by shipping product to users in production, and that's why we don’t treat our interns as temporary guests. Every intern at Vercel is expected to operate like a core part of ou…
Gemini 3.7 Flash now available on AI Gateway for 50% off
Gemini 3.7 Flash from Google is now available on AI Gateway for 50% off till December 31st, 2026. Gemini 3.7 Flash improves on prior Flash models at software engineering and agentic work. It resolves…
Added 1
Gemini 3.7 Flash from Google is now available on AI Gateway
GLM 5.2 free for eve agents through August 27 via Blackbox on AI Gateway
GLM 5.2 , the open-weights coding model from Z.ai with a 1M-token context window, is free for eve agents through August 27, served by Blackbox AI on AI Gateway . New eve agents come with GLM 5.2 as th…
Added 1
GLM 5.2 open-weights coding model with 1M-token context window available free for eve agents through August 27 via Blackbox on AI Gateway
Grok Build is now available in the AI SDK harness layer
The AI SDK harness layer lets you run established coding-agent runtimes through one unified interface, so you can switch runtimes without changing your application code. Today we are adding Grok Build…
Added 1
Grok Build is now available in the AI SDK harness layer for running coding-agent runtimes through a unified interface
Team owners and members can now upgrade all projects using Node.js 20 or earlier to Node.js 24 with one click from the Vercel Dashboard. This updates the Node.js version in project settings . If your…
Added 1
Team owners and members can upgrade all projects using Node.js 20 or earlier to Node.js 24 with one click from the Vercel Dashboard
Exa is now available on the Vercel Agent Marketplace as a native integration. Exa's neural search engine delivers high-quality, relevant results to ground AI in fresh, current information. Add Exa to…
Added 1
Exa is now available on the Vercel Agent Marketplace as a native integration
Use ACP-compatible harnesses with the AI SDK harness layer
The AI SDK harness layer now supports any Agent Client Protocol (ACP)-compatible harness with HarnessAgent through the new @ai-sdk/harness-acp package. Previously, every harness adapter wrapped one sp…
Added 1
AI SDK harness layer now supports Agent Client Protocol (ACP)-compatible harnesses with HarnessAgent through the new @ai-sdk/harness-acp package
DeepSeek V4 Pro now runs updated weights on AI Gateway
DeepSeek V4 Pro now runs on updated weights on AI Gateway. They are used by default when you call deepseek/deepseek-v4-pro , so existing requests pick them up with no change to the model ID or your co…
Changed 1
DeepSeek V4 Pro now runs on updated weights on AI Gateway and uses them by default when calling deepseek/deepseek-v4-pro
Exa web search free through August 31 on AI Gateway and eve
Exa web search is now free on AI Gateway through August 31, and it's now the default web search for eve agents. The tool works with any AI Gateway model, with no separate Exa API key. When the model c…
Added 1
Exa web search is now available free through August 31 on AI Gateway
Changed 2
Exa web search is now the default web search for eve agents
Exa web search works with any AI Gateway model without requiring a separate Exa API key
Set up coding agents in one command with AI Gateway
Using coding agents means setting up multiple accounts, provisioning API keys, and scattering observability and billing. Now, you can route them through AI Gateway to centralize all of this and add co…
Added 1
Route coding agents through AI Gateway to centralize accounts, API keys, observability, and billing in one place
We recently announced that new Pro teams are eligible to claim a free domain for their first year . We are now extending this offer to all Pro teams. Existing Pro teams can now also claim a free domai…
Added 1
All Pro teams can now claim a free domain for their first year
The AI SDK is one of the most popular open-source AI projects in the world. It serves over 20 million npm downloads a week and the repo has over 26,000 stars. Maintaining the codebase means tracking f…
Grok 4.6 from SpaceXAI is now available on AI Gateway . The model has a 500K token context window and accepts text and image inputs. Grok 4.6 supports low, medium, high, and xhigh reasoning levels and…
Added 4
Grok 4.6 from SpaceXAI is now available on AI Gateway
Grok 4.6 model supports 500K token context window
Grok 4.6 accepts text and image inputs
Grok 4.6 supports low, medium, high, and xhigh reasoning levels
Vercel Connect now gives teams line-level visibility into the token lifecycle. See who created a token, what app or project used it, when, and whether it is still active. Every connector's detail page…
Added 1
Vercel Connect adds line-level visibility into the token lifecycle, showing who created a token, what app or project used it, when it was created, and whether it is still active
How we migrated the database behind every Vercel build
Every build on Vercel starts in the build warm pool, which is a set of standby containers that let builds begin without waiting for new compute. The pool runs on state that tracks which containers are…
Enterprise Managed Users is now generally available
Enterprise Managed Users (EMU) gives organizations full control over the Vercel accounts tied to their verified domains. It makes the organization's identity provider the single source of truth for au…
Added 1
Enterprise Managed Users (EMU) is now generally available, allowing organizations full control over Vercel accounts tied to their verified domains by making the organization's identity provider the single source of truth for authentication
Vercel Connect now supports CLI setup for 100+ connectors
You can now integrate 100+ services through Vercel Connect from the CLI. Previously, vercel connect create completed setup in the terminal for some services, and opened the dashboard for everything el…
Added 1
Vercel Connect now supports CLI setup for 100+ connectors
Over the past year, AI models have become much more capable of performing cybersecurity work. These changes are reshaping both the threats facing the web and the tools available to defend it. Right no…
DeepSeek overtakes Google on volume, cost per token falls 13.6%
AI Gateway Production Index — August 2026 Every month, AI Gateway routes tens of trillions of tokens between production applications and AI labs. That traffic gives us a view of what AI usage actually…
A sandbox without a network boundary is only half a sandbox
Running untrusted code safely requires more than separating it from the host. You also have to control what that code can reach. This matters more as AI agents gain the ability to read files, execute…
LaunchDarkly is now available on the Vercel Marketplace
LaunchDarkly is now available on the Vercel Marketplace , allowing you to quickly get started with feature flags without additional setup. You can: Sync flags into Global Config and evaluate them loca…
Added 1
LaunchDarkly is now available on the Vercel Marketplace for quick setup of feature flags without additional configuration
Today we are introducing Vercel Managed Images (VMI), a set of versioned, open-source base images you can use as-is or extend. The source for every image lives in the public vercel/sandbox repository.…
Added 1
Vercel Managed Images (VMI), a set of versioned, open-source base images that can be used as-is or extended
Bun runtime for Vercel Functions now accepts Bun.serve as an entrypoint
The Bun runtime for Vercel Functions now supports Bun.serve() as a function entrypoint, including WebSocket handlers. The server you run locally with Bun deploys as-is, without being wrapped in a fram…
Added 2
Bun runtime for Vercel Functions now accepts Bun.serve as a function entrypoint
Support for WebSocket handlers in Bun.serve entrypoints
deepsec , the open-source security review harness from Vercel, now lets you set up a repository and run its first security review with a single command. The init command now automates the standard set…
Added 1
Init command now automates setup of a repository and running its first security review with a single command
Grok Imagine Image 2.0 now available on Vercel AI Gateway
Grok Imagine Image 2.0 Preview from xAI is now available on AI Gateway. The model follows detailed instructions closely and plans typography and layout together, so dense, multi-part visuals like info…
Added 1
Grok Imagine Image 2.0 Preview from xAI is now available on AI Gateway
Vercel AI Gateway and Vercel Sandbox now available on Hermes Agent
Hermes Agent can now use Vercel AI Gateway as its inference layer and run its agent commands in an isolated Vercel Sandbox microVM. Access 200+ models through AI Gateway at no markup on tokens, and ev…
Added 3
Hermes Agent can now use Vercel AI Gateway as its inference layer
Hermes Agent can now run its agent commands in an isolated Vercel Sandbox microVM
Access 200+ models through AI Gateway at no markup on tokens
Vercel Container Registry repositories can now be made public
Vercel Container Registry now lets you make a repository public, so anyone with a Vercel account can pull and use its images. Sharing already granted read access to up to 100 teams, and making a repos…
Added 1
Vercel Container Registry repositories can now be made public, allowing anyone with a Vercel account to pull and use their images
Audit Log Drains now support Datadog, Splunk, and Panther
Audit Log Drains now stream your team's audit events into Datadog , Splunk , and Panther , joining the existing custom HTTPS endpoint and Amazon S3 destinations. An Audit Log Drain forwards every even…
Added 1
Audit Log Drains now support streaming audit events to Datadog, Splunk, and Panther in addition to custom HTTPS endpoints and Amazon S3
You can now bundle multiple agent skills into a shareable pack on skills.sh . Build a pack from community skills, your own local folders and zips, or public and private GitHub repositories. Every pack…
Added 1
Bundle multiple agent skills into a shareable pack on skills.sh from community skills, local folders and zips, or public and private GitHub repositories
Free domain now included with new Pro subscriptions
New Pro subscriptions now include a domain free for the first year. The offer covers six TLDs: .online .site .space .store .tech .website Each team has 30 days after subscribing to claim one domain, e…
Added 1
Free domain for the first year now included with new Pro subscriptions covering .online, .site, .space, .store, .tech, and .website TLDs
Terminal coding agents like Claude Code, Codex, and OpenCode can now each run in their own isolated Vercel Sandbox , orchestrated from Herdr , a tmux-style manager that runs them side by side in panes…
Added 1
Terminal coding agents can now each run in their own isolated Vercel Sandbox, orchestrated from Herdr, a tmux-style manager that runs them side by side in panes
Seedance 2.5 from ByteDance is now available on AI Gateway. It generates up to 30 seconds in a single clip, holding camera movement and continuity without stitching shots together in post. Short clips…
Added 1
Seedance 2.5 from ByteDance is now available on AI Gateway
Marketplace integrations now install provider skills
When you install a Vercel Marketplace integration from the Vercel CLI, it now also installs that provider's agent skills from skills.sh , so your agents know how to use it: This happens automatically…
Added 1
Vercel Marketplace integrations now automatically install provider agent skills from skills.sh when installed from the Vercel CLI, enabling agents to know how to use the integration
Agent Plugins 1.0.0 is now available. It is an open, vendor-neutral standard for packaging Agent Skills and MCP servers into portable plugins. Compatible agent clients can discover and load them. Agen…
Added 1
Introduced Agent Plugins 1.0.0, an open, vendor-neutral standard for packaging Agent Skills and MCP servers into portable plugins
You can build human-in-the-loop approvals with Chat SDK through the new chat/workflow subpath. One requestApproval call posts a card with Approve and Deny buttons and suspends a Workflow SDK workflow…
Added 1
Build human-in-the-loop approvals with Chat SDK through the new chat/workflow subpath with requestApproval calls that post approval cards with Approve and Deny buttons and suspend Workflow SDK workflows
Today, Agent Plugins 1.0.0 is publicly available. Agent Plugins is an open, vendor-neutral standard for plugins that extend AI agents. Agent Skills provide reusable instructions and resources for AI a…
Added 1
Agent Plugins 1.0.0 is now publicly available as an open, vendor-neutral standard for plugins that extend AI agents
Ling 3.0 Tiny from ANT Group is now on AI Gateway, free to use till 8:00am PT on 8/14. Ling 3.0 Tiny takes the free slot from Ling 3.0 Flash . Ling 3.0 Tiny is a MOE model with 7.9B total parameters a…
Added 1
Ling 3.0 Tiny from ANT Group is now available on AI Gateway
You can now set a project's avatar from its settings in the Vercel dashboard. Until now, Vercel set it automatically, using the favicon from the project's production deployment. That's still the defau…
Added 1
Allow users to set a project's avatar from its settings in the Vercel dashboard
Buying a domain on Vercel now takes you to a setup page that tracks registration live, with direct paths to deploy a new project, connect an existing one, proxy or redirect a site you already run, or…
Added 1
Buying a domain on Vercel now shows a setup page that tracks registration live with direct paths to deploy a new project, connect an existing one, proxy or redirect a site you already run
AI Gateway now produces an OpenTelemetry trace for every request. Pro and Enterprise teams can send these traces through Vercel Drains to any OTLP/HTTP-compatible endpoint, including native integratio…
Added 2
AI Gateway now produces an OpenTelemetry trace for every request
Pro and Enterprise teams can send AI Gateway traces through Vercel Drains to any OTLP/HTTP-compatible endpoint
Today we're introducing the new v0 API : programmatic, headless access to v0's app-building agent. Send a prompt and v0 generates an app, starts a dev server in a Vercel Sandbox , and gives you a prev…
Added 2
Introduce new v0 API for programmatic, headless access to v0's app-building agent
API accepts a prompt and generates an app with an automated dev server in a Vercel Sandbox
AI Gateway is available on AWS Marketplace . Teams can procure AI Gateway through their existing AWS account, consolidating inference spend onto their AWS bill and streamlining procurement. Purchases…
Added 1
AI Gateway is now available on AWS Marketplace for teams to procure through their existing AWS account
You can now measure the time between any two steps in the trace viewer for Vercel Workflows and the Workflow SDK . Select a step, hold Option on macOS or Alt on Windows and Linux, then hover another s…
Added 1
Measure the time between any two steps in the trace viewer for Vercel Workflows by selecting a step, holding Option on macOS or Alt on Windows and Linux, then hovering another step
You can now search for and purchase domains from the Vercel dashboard . Open the domain search panel from the Buy button in domain settings or the + button on the project overview. Nameservers are con…
Added 2
Search for and purchase domains from the Vercel dashboard
Access domain search panel from the Buy button in domain settings or the + button on the project overview
Muse Spark 1.2 is now available on Vercel AI Gateway
Muse Spark 1.2 from Meta is now available on AI Gateway. It is a coding-focused update to the previous Muse Spark model. While keeping its general capabilities, 1.2 ships with improvements in code gen…
Added 1
Muse Spark 1.2 from Meta is now available on AI Gateway
Full Sandbox egress firewall now available on Hobby plan
All Vercel Sandbox firewall features are now available on the Hobby plan. This brings the same network isolation that protects production workloads to the free tier, giving Hobby builders control over…
Added 1
Full Sandbox egress firewall features now available on Hobby plan
Vercel Sandbox now supports 10,000 concurrent sandboxes and 5,000 vCPUs per minute
We've increased the default quotas for Vercel Sandbox on Pro and Enterprise plans: Quota Before After Concurrent sandboxes 2,000 10,000 vCPUs allocation rate 200/min (Pro), 400/min (Enterprise) Up to…
Changed 2
Increased default concurrent sandboxes quota from 2,000 to 10,000 for Pro and Enterprise plans
Increased vCPUs allocation rate to 5,000 per minute across Pro and Enterprise plans
Vercel Sandbox now supports Devin Outposts . Each Devin session executes in its own isolated Sandbox microVM, with no local Outpost worker to keep online. The Devin control plane stays with Cognition,…
Added 1
Vercel Sandbox now supports Devin Outposts with isolated Sandbox microVMs for each Devin session
Yesterday the Next.js team announced the release of Next.js 16.3 , with leaner prefetching, immutable static assets, and instant navigations. As part of this release, we worked with the Next.js team t…
Added 1
Support for Next.js 16.3 with leaner prefetching and immutable static assets
Deploys are now up to 33% faster for apps with many ISR pages
Deploys are now up to 33% faster for apps using Incremental Static Regeneration (ISR). The more prerendered pages you have, the more you're likely to save. ISR combines the speed of static generation…
Changed 1
Deploys are now up to 33% faster for apps using Incremental Static Regeneration (ISR), with larger speed improvements for apps with many prerendered pages
Your eve agent can now navigate the web like a human with agent-browser . The @agent-browser/eve extension gives any eve agent a full set of browser tools: navigate pages, read content, click, fill fo…
Added 1
Eve agents can now navigate the web using the @agent-browser/eve extension with browser tools including page navigation, content reading, clicking, and form filling
DeepSeek V4 Flash is 90% off through Novita on AI Gateway
DeepSeek v4 Flash is 90% off on AI Gateway when you route to Novita. The discount is available to Vercel Pro customers through August 11. To get the discounted rate, set the model to deepseek/deepseek…
Added 1
DeepSeek v4 Flash model available at 90% discount through Novita on AI Gateway for Vercel Pro customers through August 11
Vercel WAF for Blob is now generally available and supported for production use on all plans. If you protected a store during the beta , nothing has changed: your rules and setup carry over exactly as…
Added 1
Vercel WAF for Blob is now generally available and supported for production use on all plans
How Factory scaled its cloud backend to tens of millions of daily requests on Vercel
Factory on Vercel Tens of millions of backend API requests served daily 350ms p95 response time Scaled backend, internal tooling, and security without a dedicated infrastructure team Factory's mission…
How Factory scaled its cloud backend to one billion monthly requests on Vercel
Factory on Vercel One billion backend API requests served daily 350ms p95 response time Scaled backend, internal tooling, and security without a dedicated infrastructure team Factory's mission is to b…
Share Vercel Container Registry repositories across teams
Vercel Container Registry now lets you share a repository with other Vercel teams to grant read access to its images. Sharing is read-only and covers the whole repository. Recipients can pull and use…
Added 1
Vercel Container Registry now supports sharing repositories across teams to grant read access to images
Qwen 3.8 Max is now available on AI Gateway. Qwen 3.8 Max handles text-only and vision-language work in one model, with 2.4 trillion parameters and a context window of up to 1 million tokens. The mode…
Added 1
Qwen 3.8 Max model is now available on Vercel AI Gateway
AI Gateway now supports team and project spend budgets
AI Gateway spend budgets can now be scoped to a team or a project, in addition to individual API keys. Set a dollar limit on a scope, and the gateway meters spend against it and stops further requests…
Added 1
AI Gateway spend budgets can now be scoped to a team or a project in addition to individual API keys, with the ability to set a dollar limit and meter spend against it
DeepSeek V4 Flash now runs updated weights on AI Gateway
DeepSeek V4 Flash now runs on updated weights by default on AI Gateway, with notably stronger agentic capabilities. On Terminal-Bench, it scores 82.7, up 25.8 points from 56.9 in the April preview. Re…
Changed 1
DeepSeek V4 Flash now runs updated weights by default on AI Gateway with stronger agentic capabilities
Chat SDK now supports reactions and ephemeral messages on Teams
Chat SDK's Microsoft Teams adapter now supports reactions and ephemeral messages through the same API as other adapters. Bots can add and remove reactions on Teams messages, and call thread.postEpheme…
Added 3
Chat SDK's Microsoft Teams adapter now supports reactions on messages through the same API as other adapters
Chat SDK's Microsoft Teams adapter now supports ephemeral messages through the same API as other adapters
Bots can add and remove reactions on Teams messages
Laguna S 2.1 from Poolside now has 10x more capacity on AI Gateway. The increase applies to the paid version, poolside/laguna-s-2.1 , and the free version, poolside/laguna-s-2.1-free , so you can send…
Changed 1
Laguna S 2.1 model from Poolside now has 10x more capacity on AI Gateway for both paid (poolside/laguna-s-2.1) and free (poolside/laguna-s-2.1-free) versions
Vercel MCP now supports the 2026-07-28 MCP specification
Vercel MCP now supports the 2026-07-28 MCP specification, giving newer clients a stateless request model and updated authorization behavior without any change on the client side. Clients built for the…
Changed 1
Support the 2026-07-28 MCP specification with stateless request model and updated authorization behavior
AI Gateway has a unified fast mode abstraction, now in beta. You can now request fast mode the same way for every model on AI Gateway. Set speed to fast , and the gateway serves the fast tier when it'…
Added 1
AI Gateway now has unified fast mode support that allows requesting fast mode the same way for every model
Vercel Passport is now generally available. Passport allows you to protect your Vercel deployments with your own identity provider. Visitors authenticate through Okta, Microsoft Entra ID, or any OIDC…
Added 1
Vercel Passport is now generally available for protecting Vercel deployments with custom identity providers including Okta, Microsoft Entra ID, and any OIDC provider
AI Gateway now has a dedicated Logs page listing every request your team sends through the gateway, newest first, with cost, token counts, duration, and the model, provider, and region that served it.…
Added 1
AI Gateway now has a dedicated Logs page that lists every request sent through the gateway with cost, token counts, duration, model, provider, and region information
Expanded search for workflow runs in Vercel Observability
The runs list for Vercel Workflows in Observability now has structured search, giving you more ways to find and investigate runs. Structured filters: Filter runs by workflow, environment, deployment I…
Added 1
Add structured search and filters to the runs list for Vercel Workflows in Observability to filter runs by workflow, environment, and deployment
Server-Timing response headers will pass through to the client
On August 10, 2026, Vercel's CDN will stop stripping the Server-Timing response header and begin passing it through to the client. Use Server-Timing to report backend metrics like database query time…
Changed 1
Server-Timing response headers will pass through to the client instead of being stripped by Vercel's CDN
The @vercel/sandbox SDK now supports multiple Linux users and groups, so you can run agents side by side in a single Sandbox. Each agent runs as its own user with a private home directory. A group ope…
Added 2
Support for multiple Linux users and groups in @vercel/sandbox SDK to run agents side by side in a single Sandbox
Each agent can run as its own user with a private home directory
Shopify and Vercel are rebuilding Hydrogen for faster storefronts
Shopify and Vercel Open source and runtime agnostic, runs anywhere JavaScript does Standard Actions brings agentic commerce to every storefront Feature development cut from months to a week for retail…
Added 2
Hydrogen is now open source and runtime agnostic, able to run anywhere JavaScript does
Standard Actions brings agentic commerce capabilities to every storefront
Changed 1
Feature development time reduced from months to a week for retail storefronts
Introducing Enterprise Flexible Commitment for Vercel Marketplace
Enterprise customers can now apply a portion of their Flexible Commitment toward eligible resources purchased through the Vercel Marketplace. With Flex Commit support, eligible Marketplace cost can dr…
Added 1
Enterprise customers can now apply a portion of their Flexible Commitment toward eligible resources purchased through the Vercel Marketplace
On AI Gateway , GPT-5.6 Luna and GPT-5.6 Terra are now cheaper and GPT-5.6 Sol is faster. AI Gateway adds no markup on token pricing, so these changes reach you at the upstream rate. The changes apply…
MiniMax H3 is now available on AI Gateway. H3 generates 2K video from a text prompt, a starting image, a pair of first and last frames, or reference material. Alongside text-to-video and first-frame i…
Added 1
MiniMax H3 is now available on AI Gateway for generating 2K video from text prompts, starting images, first and last frame pairs, or reference material
Turborepo and Vercel Remote Cache now support OpenID Connect (OIDC)
You can now exchange OIDC tokens from CI/CD workflows, including GitHub workflows , for short-lived Turborepo access tokens. These tokens grant access to Vercel's Remote Cache , and are a more secure…
Added 1
Turborepo and Vercel Remote Cache now support OpenID Connect (OIDC) for exchanging tokens from CI/CD workflows for short-lived Turborepo access tokens
Inkling Small from Thinking Machines is now available on AI Gateway
Inkling Small from Thinking Machines is now available on AI Gateway. Inkling Small reaches performance comparable to the larger Inkling model at about a quarter of the size, using much less compute pe…
Added 1
Inkling Small model from Thinking Machines is now available on AI Gateway
mcp-handler@2.0.0 is now available with support for the 2026-07-28 Model Context Protocol specification and MCP TypeScript SDK v2 . We originally built mcp-handler to make it easier to spin up MCP ser…
Changed 2
Add support for the 2026-07-28 Model Context Protocol specification
Over the past few months, we've made deployments up to 7 seconds faster end to end. We removed up to 5 seconds of fixed platform overhead from every build, and deploys from the latest Vercel CLI save…
Changed 1
Deployments are now up to 7 seconds faster end to end
You can now create Vercel Access Tokens that are limited to a project to authenticate and use the Vercel API . A project-scoped token can only read and write resources belonging to a project that the…
Added 1
Create Vercel Access Tokens that are limited to a project to authenticate and use the Vercel API
Grok Voice Think Fast 2.0 now available on AI Gateway
Grok Voice Think Fast 2.0 from xAI is now available on AI Gateway. It is a speech-to-speech voice model that takes audio in and audio out, improving on the previous Grok Voice model in reasoning, tran…
Added 1
Grok Voice Think Fast 2.0 from xAI is now available on AI Gateway as a speech-to-speech voice model
Edge Config is now Global Config . This rename better reflects that it is a globally replicated data store with ~1ms reads in every region, built for the configuration that applications read at runtim…
Changed 1
Edge Config renamed to Global Config to better reflect that it is a globally replicated data store with ~1ms reads in every region
Additional custom environments can now be purchased
Pro and Enterprise teams can now purchase additional custom environment capacity without contacting sales. Custom environments let you model your team's release process on Vercel. You can add staging…
Added 1
Pro and Enterprise teams can now purchase additional custom environment capacity without contacting sales
Discover and install eve integrations from the CLI
You can now discover and install integrations for eve agents directly from the eve CLI. Integrations come from the official eve catalog and third-party sources. Run eve add from your eve project to in…
Added 1
Discover and install integrations for eve agents directly from the eve CLI
Sign in with ChatGPT adds your ChatGPT account as an authentication option for Vercel. It is available when adding the Vercel plugin to ChatGPT and when signing in to Vercel or v0. When you add the Ve…
Added 1
Sign in with ChatGPT authentication option for Vercel accounts
Vercel Sandbox now supports forking with Sandbox.fork() . The fork starts from the source's current snapshot and inherits its config and environment variables. If the source is running, it forks the l…
Added 1
Vercel Sandbox now supports forking with Sandbox.fork()
Vercel Connect now lets you link a connector to a Custom Environment so deployments there can request provider tokens and receive forwarded webhooks. Custom Environments appear alongside Production, P…
Added 1
Vercel Connect now supports linking a connector to a Custom Environment so deployments there can request provider tokens and receive forwarded webhooks
AI Gateway now supports regional inference . Set inferenceRegion on a request to pin it to the US or EU. Every model provider that supports the selected region handles it the same way. Inference runs…
Added 1
Support regional inference on AI Gateway with inferenceRegion parameter to pin requests to US or EU regions
eve adds new Slack event hooks and session controls
eve agents on Slack can now keep replying in a thread without repeated mentions, cancel an in-progress response or reset a conversation entirely, and react to any event your Slack app subscribes to. C…
Added 4
eve agents on Slack can now keep replying in a thread without repeated mentions
eve agents can cancel an in-progress response
eve agents can reset a conversation entirely
eve agents can react to any event your Slack app subscribes to
DeepsecBench: evaluating model performance in finding cybersecurity vulnerabilities
Last week, OpenAI evaluated two models on an exploit benchmark within an isolated sandbox. Guardrails were reduced for testing, and the models found a vulnerability in their environment, accessed the…
WebSocket support for OpenAI Responses API live on AI Gateway
AI Gateway now supports WebSocket mode for the OpenAI Responses API. You can keep a persistent connection open and continue each turn by sending only new input items plus previous_response_id , instea…
Added 1
WebSocket support for OpenAI Responses API on AI Gateway to maintain persistent connections and continue turns by sending new input items with previous_response_id
You can now run Claude Managed Agents with Chat SDK . Claude Managed Agents handles the agent loop server-side, including the model, tools, session state, and sandboxed web research. Chat SDK gives th…
Added 1
Run Claude Managed Agents with Chat SDK, which handles the agent loop server-side including the model, tools, session state, and sandboxed web research
The Nuxt team has released Nuxt 4.5.1 and 3.21.10, along with @nuxt/devtools 3.3.1, to address eight security advisories, including a high-severity server-side remote code execution vulnerability. Vul…
Security 3
Addressed a high-severity server-side remote code execution vulnerability in Nuxt
Released Nuxt 4.5.1 and 3.21.10 to address eight security advisories
Released @nuxt/devtools 3.3.1 to address security advisories
Kimi K3 and Kimi K3 Fast with ZDR and US-based providers now on AI Gateway
Kimi K3 from Moonshot AI and its faster serving path, Kimi K3 Fast , are now available from US-based providers on AI Gateway, including Baseten and Fireworks. Zero Data Retention (ZDR) is also support…
Added 3
Kimi K3 from Moonshot AI is now available from US-based providers on AI Gateway, including Baseten and Fireworks
Kimi K3 Fast is now available from US-based providers on AI Gateway, including Baseten and Fireworks
The Vercel WAF can now protect a Vercel Blob store. The same rules that guard your deployments (deny, challenge, rate limit) now apply to blob traffic with no changes to your code, blob URLs, or @verc…
Added 1
Vercel WAF can now protect a Vercel Blob store with the same rules that guard deployments (deny, challenge, rate limit) applying to blob traffic without code changes or modifications to blob URLs
Workflow steps now support extended function durations
Workflow steps on Pro and Enterprise plans can now run for up to 30 minutes (1800 seconds), up from 800 seconds, using extended function durations (in beta). To opt in, set VERCEL_ENABLE_WORKFLOW_EXTE…
Added 1
Workflow steps on Pro and Enterprise plans can now run for up to 30 minutes (1800 seconds) using extended function durations (in beta)
Claude Opus 5 from Anthropic is now available on AI Gateway. Opus 5 improves on previous Opus models for long-horizon agentic coding, handling multi-file features, larger refactors, and end-to-end fea…
Added 1
Claude Opus 5 from Anthropic is now available on AI Gateway
Vercel Flags now shows a live evaluation view on each flag's detail page. You can see evaluations per minute charted over time, with each flag version marked in the chart so you can tie evaluation shi…
Added 1
Live evaluation view on each flag's detail page showing evaluations per minute charted over time with flag versions marked in the chart
You can now add GitHub tools to your eve agent as an extension. Add the package, drop one file in agent/extensions/ , and your agent gets every tool with Vercel Connect auth, presets, and approval rul…
Added 1
GitHub tools are now available as an installable eve extension that can be added to your agent with Vercel Connect auth, presets, and approval rules
Vercel Flags version history can now be inspected from the Vercel CLI with the new vercel flags versions command. Run vercel flags versions to print the full revision history for a flag, with each rev…
Added 1
Add vercel flags versions command to inspect Vercel Flags version history from the Vercel CLI
Ling 3.0 Flash from Ant Group is now available on AI Gateway. The model is free to use for the next three weeks, through August 3rd. Ling 3.0 Flash is a Mixture-of-Experts model with 124B total parame…
Added 1
Ling 3.0 Flash from Ant Group is now available on AI Gateway