What changed in the Vercel API

DeepSeek V4.1 Flash is now available in Token Pass

WebSocket support is now generally available
WebSocket support in Vercel Functions, used for multiplayer apps, chat streaming, and AI Gateway's realtime models, is now GA.
DeepSeek V4.1 Flash is now available in Token Pass
DeepSeek V4.1 Flash joins Kimi K3 and GLM 5.3 in Token Pass.
Walter Korman, Krish Krish

MiniMax M3.1 Flash now available on AI Gateway for free

Updates to Hobby and Pro Terms of Service
Updates to Vercel's Hobby and Pro Terms of Service.
Mercury 3 now available on AI Gateway
Call Inception's Mercury 3 through Vercel AI Gateway with one API key, no provider account, spend tracking, and request traces.
MiniMax M3.1 Flash now available on AI Gateway for free
Call MiniMax M3.1 Flash through Vercel AI Gateway with one API key: no provider account, automatic fallbacks, spend tracking, and traces on every request.

DeepSeek V4.1 Flash 1017 now available on AI Gateway

AI Gateway logs now show session affinity
Vercel AI Gateway logs now group requests into sessions, with cache hit rate, cost, turns, and the coding agent behind each conversation.
Sam Chitgopekar, Jerilyn Zheng
DeepSeek V4.1 Flash 1017 now available on AI Gateway
Call DeepSeek V4.1 Flash 1017 through Vercel AI Gateway with one API key, image input, spend tracking, and traces on every request.
Elorian AI's Glimpse now available on AI Gateway
Call Elorian's Glimpse through Vercel AI Gateway with one API key, no provider account, spend tracking, and request traces.
Jerilyn Zheng, Rohan Taneja, and 1 other

Reflection AI's Beam now available on AI Gateway for free

Perplexity's Decider V1.2 models now available on AI Gateway
Call Perplexity Decider V1.2 and Decider Flash V1.2 through Vercel AI Gateway with one API key, shared budgets, and usage tracking.
Reflection AI's Beam now available on AI Gateway for free
Try Reflection AI's Beam for free for a limited time on Vercel AI Gateway with one API key, spend tracking, and request traces
Jerilyn Zheng, Kevin Dawkins, and 2 others

Cat Jam is now available in stealth for free on AI Gateway

Vercel Token Pass, now in early access, gives your team $80 in monthly credit for featured open-weight models for $30, starting with GLM 5.3 and Kimi K3. Use it with your coding agent or to power a personal agent on Vercel.
Jas Garcha, Krish Krish, and 2 others
Vercel Daemons is now in public beta
Run queue consumers, workflow workers, and self-hosted CI runners on Vercel.
Steren, Gal Schlezinger, and 2 others
Liquid AI's d1-ultra now available on AI Gateway
Call Liquid AI's d1-ultra through Vercel AI Gateway with one API key, unified spend tracking, and request logs.
Muse Spark Open now available on AI Gateway
Call Meta's Muse Spark Open through Vercel AI Gateway with one API key, no provider account, automatic fallbacks, spend tracking, and request traces.
Vercel Connect now supports Secure Compute
Connectors can now reach providers that restrict access by IP address, using your Secure Compute network’s static IPs.
Dima Voytenko, Hedi Zandi, and 2 others
Cat Jam is now available in stealth for free on AI Gateway
Call the stealth model Cat Jam for free through Vercel AI Gateway with one API key: no provider account, spend tracking, and traces on every request.
Vercel Drives is now

Amazon S3 is now available in the Vercel Marketplace and v0 with guided setup and automatic project configuration built into the Vercel dashboard.

Amazon S3 joins the Vercel Marketplace
Amazon S3 is now available in the Vercel Marketplace and v0 with guided setup and automatic project configuration built into the Vercel dashboard. 
Nemotron 3.5 Lightning now available on AI Gateway for free
Use Nvidia's Nemotron 3.5 Lightning for free through Vercel AI Gateway with one API key: no provider account, spend tracking, and traces on every request.

MAI-Image-2.6 and MAI-Image-2.6-Flash now available on AI Gateway

Drama 3 now available on AI Gateway
Generate expressive speech with Fish Audio's Drama 3 through Vercel AI Gateway, using one API key with spend tracking and request traces
MAI-Image-2.6 and MAI-Image-2.6-Flash now available on AI Gateway
Generate and edit images with MAI-Image-2.6 and Flash through Vercel AI Gateway, with one API key, unified billing, and request traces
Kevin Dawkins, Jerilyn Zheng, and 1 other
Repository checkout and Git LFS downloads are now faster
Git deployments now spend less time getting your project's files ready before the build runs. The improvements apply automatically.
Gemini 4 Argon now available on AI Gateway
Call Google's Gemini 4 Argon through Vercel AI Gateway with one API key: no provider account, spend tracking, and traces on every request.
Zachary Chen, Jerilyn Zheng

Muse Wonder now available on AI Gateway

Muse Wonder now available on AI Gateway
Call Meta's Muse Wonder through Vercel AI Gateway with one API key, no provider account, spend tracking, and request traces.
Jerilyn Zheng, Zachary Chen

Microsoft Decision-1 now available on AI Gateway

Agents can now buy domains with the Vercel CLI
Agents can now use the Vercel CLI to purchase domains.
Melkey Moksyakov, Esteban Suárez
New Pro teams now default to 30-day deployment retention
New Pro teams use 30-day deployment retention by default, with the option to keep longer history.
Pranav Kanchi, Jay Gengelbach, and 1 other
Deployment Storage billing begins for existing Pro teams
Existing Pro teams will pay $0.10 per GB-month for Deployment Storage and Functions Storage, and the retention window moves to 30 days on October 23.
Jay Gengelbach, Pranav Kanchi, and 1 other
Microsoft Decision-1 now available on AI Gateway
Call Microsoft's Decision-1 through Vercel AI Gateway with one API key to classify text, route requests, and track usage and spend
Jerilyn Zheng, Kevin Dawkins, and 2 others
Liquid AI's d1 is available on AI Gateway
Evaluate typed questions with Liquid d1 on Vercel AI Gateway using the AI SDK, HTTP API, or TypeSafe-compatible API.
Zachary Chen, Rohan Taneja, and 2 others

OpenAI Ultrafast mode now available on AI Gateway

Skip sending request bodies to Routing Middleware
Set skipMiddlewareRequestBody to stop forwarding the client request body to Routing Middleware, reducing Fast Origin Transfer usage and helping improve Time to First Byte.
Vercel Sandbox creation now returns a ready sandbox
Vercel Sandbox creation is now more consistent and now includes startup time previously spent waiting in the first command.
Software Engineer, Infrastructure
Grok Imagine Video 1.5 Lite on AI Gateway
Call xAI's Grok Imagine Video 1.5 Lite through Vercel AI Gateway with one API key, unified billing, and request traces.
Step 5 Preview now available on AI Gateway
Call StepFun's Step 5 Preview through Vercel AI Gateway with one API key, no provider account, spend tracking, and request traces.
OpenAI Ultrafast mode now available on AI Gateway
Use OpenAI Ultrafast for GPT-6 Astra and GPT-6.1 Sol on AI Gateway with the AI SDK, Responses API, Chat Completions, or WebSocket.
Kevin Dawkins, Jerilyn Zheng, and 1 other
FLUX 3 Image now available on AI Gateway
Generate and edit images with FLUX 3 Image through Vercel AI Gateway, with one API key, unified billing, and request traces.
Jerilyn Zheng, Rohan Taneja, and 1 other

Vercel Flags now support timestamp attributes for date-based rule evaluation. Enable flags between two dates, for account age, or other time-based conditions.

Microfrontends Routing is now free for Firewall-mitigated traffic
Requests that are denied, challenged, or rate limited by the Vercel Firewall do not count towards billed Microfrontends Routing requests.
OpenAI Decisions API now available on AI Gateway
Vercel AI Gateway now supports OpenAI's Decisions API, with GPT-6 Luna Decisions and other decision models through the OpenAI SDK, AI SDK, and AI CLI
Jerilyn Zheng, Nick Oates, and 2 others
Claude Haiku 5.5 now available on AI Gateway
Call Claude Haiku 5.5 through Vercel AI Gateway with one API key: no provider account, automatic fallbacks, spend tracking, and traces on every request.
Rohan Taneja, Zachary Chen, and 1 other
Glyph Cluster is now available in stealth for free on AI Gateway
Call the stealth model Glyph Cluster for free through Vercel AI Gateway with one API key: no provider account, spend tracking, and traces on every request.
Timestamp attributes are now supported in Vercel Flags
Vercel Flags now support timestamp attributes for date-based rule evaluation. Enable flags between two dates, for account age, or other time-based conditions.

Nano Banana 2.1 now available on AI Gateway

AI Gateway adds confidence-based decision fallbacks
AI Gateway can now escalate a decision to a fallback model when the primary model's answer trips a confidence condition you set.
Software Engineer, AI Gateway
Nano Banana 2.1 now available on AI Gateway
Generate and edit images with Nano Banana 2.1 through Vercel AI Gateway with one API key: no provider account, spend tracking, and traces on every request.
Mistral Large 4 now available on AI Gateway
Call Mistral Large 4 through Vercel AI Gateway with one API key, no provider account, spend tracking, and request traces.
Jerilyn Zheng, Zachary Chen

Voyage Rerank 3 and Rerank 3 Lite are now available on AI Gateway

Voyage Rerank 3 and Rerank 3 Lite are now available on AI Gateway
Use Voyage AI by MongoDB's Rerank 3 and Rerank 3 Lite through Vercel AI Gateway with one API key, unified billing, and request traces.

Speed Insights is deprecating First Input Delay on November 1, with no action required.

Speed Insights deprecates First Input Delay on November 1st
Speed Insights is deprecating First Input Delay on November 1, with no action required.
Damien Simonin Feugas, Vincent Derks, and 1 other

Laya decision model now available on AI Gateway, free through October 31

Laya decision model now available on AI Gateway, free through October 31
Laya from Convai Innovations is available on Vercel AI Gateway and free through October 31, 2026, when served by Boundless.
Microsoft AI models are now available on AI Gateway
Microsoft AI's latest audio models for speech and transcription are available on AI Gateway. 
Kevin Dawkins, Zachary Chen, and 1 other

Vercel's CDN no longer stores responses whose Vary header includes Cookie. They are still served normally, but no cache entry is written.

Vercel Agent now installs private packages from npm and custom registries
Vercel Agent installs private npm packages using your team's shared environment variables. Add NPM_TOKEN or NPM_RC to authenticate with private and custom registries.
Matan Kushner, Tom Dale, and 1 other
AI Gateway adds Browserbase Search and Fetch tools
AI Gateway now supports Browserbase Search and Fetch, giving models web discovery and page retrieval alongside AI SDK and Marketplace integrations.
Josh Lipman, Jerilyn Zheng, and 2 others
Edge Requests are now called CDN Requests
CDN Requests is the new name for the usage metric previously called Edge Requests. Pricing, limits, and how usage is measured are unchanged.
Member of the Technical Staff
Vercel Sandbox now supports Secure Compute
Connect Vercel Sandboxes to a dedicated Secure Compute network. 
Karim Hasebou, Brandon Tuttle, and 2 others
Ling 3.1 Flash is now available on AI Gateway
Call Ling 3.1 Flash through Vercel AI Gateway with one API key, no provider account, spend tracking, and request traces.
Vercel CDN no longer caches responses with Vary: Cookie
Vercel's CDN no longer stores responses whose Vary header includes Cookie. They are still serv

Search and filter trace spans directly from your terminal with the Vercel CLI.

Search trace spans from the Vercel CLI
Search and filter trace spans directly from your terminal with the Vercel CLI.

Running Redis commands, browsing keys, and inspecting values for Redis marketplace integrations is now supported directly in the Vercel dashboard.

Search domains without authentication
Search for domains using the Vercel CLI and Domains Registrar API without signing in.
Claude Sonnet 5.5 now available on AI Gateway
Access Claude Sonnet 5.5 through Vercel AI Gateway with the AI SDK, compatible APIs, or coding agents for coding, clearer writing, and polished documents.
Rohan Taneja, Zachary Chen, and 1 other
Tom Lienard, Will Hopkins, and 1 other
Vercel Marketplace database browser now supports Redis
Running Redis commands, browsing keys, and inspecting values for Redis marketplace integrations is now supported directly in the Vercel dashboard. 

Ember-1 from Fireworks is now available on Vercel AI Gateway, a research-preview model for coding and agent workflows that reduces reasoning token usage.

Ember-1 from Fireworks now available on AI Gateway
Ember-1 from Fireworks is now available on Vercel AI Gateway, a research-preview model for coding and agent workflows that reduces reasoning token usage.

Pixel Canary is now available on Vercel AI Gateway, with strengths in coding, frontend development, and mobile app design.

Push images to Vercel Container Registry from GitHub Actions
The vercel/vcr-action/login GitHub Action logs workflows in to Vercel Container Registry with GitHub OIDC, removing long-lived registry credentials from secrets.
Andy Waller, Mark Roberts
Pixel Canary is now available in stealth for free on AI Gateway
Pixel Canary is now available on Vercel AI Gateway, with strengths in coding, frontend development, and mobile app design. 
Zachary Chen, Rohan Taneja, and 2 others
Vercel Sandbox now supports memory observability
Vercel sandbox memory usage data can now be accessed in the dashboard and CLI. 

Vercel Blob no longer caps how many stores you can create on any plan. Store creation is billed as one Blob Advanced Operation, and deleting a store is free.

Vercel Connect now supports TanStack AI
Authenticate TanStack AI MCP clients with Vercel Connect. Tokens are issued at runtime and consent is handled at the route boundary, so nothing is stored in your environment.
Unlimited Vercel Blob stores on every plan
Vercel Blob no longer caps how many stores you can create on any plan. Store creation is billed as one Blob Advanced Operation, and deleting a store is free.
Gemini 3.8 text-to-speech models now available on AI Gateway
Generate speech in more than 100 languages with Google's Gemini 3.8 Flash-Lite TTS and Flash TTS on Vercel AI Gateway.
Zachary Chen, Kevin Dawkins, and 1 other

Claude Opus 5.5 from Anthropic is now available on Vercel AI Gateway with adaptive thinking, fast mode, regional inference, a 1M context window, and up to max effort.

GPT-6 Sol and Luna now available on AI Gateway
GPT-6 Sol and GPT-6 Luna from OpenAI are now available on Vercel AI Gateway for coding, professional workflows, computer use, and agentic applications.
Drives for Vercel Sandbox are now in public beta
Vercel Sandbox Drives, persistent storage you mount into a sandbox, is now in public beta with drives up to 16 TiB and usage-based pricing.
Tom Lienard, Joe Haddad, and 2 others
Claude Opus 5.5 now available on AI Gateway
Claude Opus 5.5 from Anthropic is now available on Vercel AI Gateway with adaptive thinking, fast mode, regional inference, a 1M context window, and up to max effort.
Rohan Taneja, Zachary Chen, and 1 other

MiMo V2.6 Pro, Flash, and Pro UltraSpeed from Xiaomi are now available on Vercel AI Gateway with 1M context, multimodal input, reasoning, and tool calling.

Vercel Connect now supports Microsoft Teams
Agents can now receive and reply to Microsoft Teams messages through Vercel Connect, with tokens managed for you across the Connect SDK, eve, and Chat SDK.
Bhrigu Srivastava, Owen Kephart, and 1 other
Deployments now show billable duration and CPU minutes
Deployments now show their billable duration and CPU minutes in the dashboard, vc inspect, and the REST API.
MiMo V2.6 models now available on AI Gateway
MiMo V2.6 Pro, Flash, and Pro UltraSpeed from Xiaomi are now available on Vercel AI Gateway with 1M context, multimodal input, reasoning, and tool calling.
AI Gateway now supports TypeSafe clients and an HTTP API for Jev
Call Jev on Vercel AI Gateway through the TypeSafe-compatible API, native HTTP API, or AI SDK to make typed decisions in agents and workflows.
Rohan Taneja, Jerilyn Zheng
Grok 4.7 now available and 40% off on AI Gateway, fx, and eve
Grok 4.7 from xAI is now available on Vercel AI Gateway, eve, and fx, and 40% off for a week starting September 21.

WebMCP support now available in mcp-handler

Spend Management expands to Enterprise Flexible Commitment plans
Enterprise teams on Flexible Commitment plans can now set a Spend Management budget, with email alerts, webhooks, and optional pausing of production deployments.
Lakshmi Subbramanian, Bryan Mishkin
WebMCP support now available in mcp-handler
mcp-handler adds experimental WebMCP support. Expose your MCP tools to in-browser agents with a single script tag, no separate OAuth flow required.
v0 now reads npm credentials from shared environment variables
v0 can now install private packages from npm and custom registries. Add an NPM_TOKEN or NPM_RC environment variable to build with your team's internal packages, design systems, and component libraries in v0.
Vishal Yathish, Sahaj Jain

Native Marketplace resource connections now support custom environments, giving you more control over where your integration resources are available.

GLM 5.3 FlashX now available on AI Gateway
Call Z.ai's GLM 5.3 FlashX through Vercel AI Gateway at 200 tokens per second, with one API key, automatic fallbacks, spend tracking, and request traces.
Zachary Chen, Jerilyn Zheng
Sub-second artifact deployments are now supported in Vercel CLI
Use the Vercel CLI to deploy static artifacts to Vercel in less than one second. 
Melkey Moksyakov, Andrew Healey , and 1 other
Turbo build machines can now be enabled per deployment
You can now opt into Turbo build machines on a per deployment basis. This keeps costs down for standard deployments and allows temporary upgrades when urgency is required
Run Terminal-Bench and other Harbor evals on Vercel Sandbox
Harbor 0.22.0 adds Vercel Sandbox as an eval environment. Pass --env vercel to run Terminal-Bench and other Harbor benchmarks with each trial in its own isolated microVM.
Elisabeth Rülke, George Fahmy
The skills CLI now supports Notion hosted skills
Install agent skills from a Notion skills database with the skills CLI, no Git repository required.
Andrew Qu, Jonathan Hefner, and 1 other
GPT-Live 1 now available on AI Gateway
Call OpenAI's GPT-Live 1 through Vercel AI Gateway for full-duplex v

TypeSafe AI's Jev now available on AI Gateway

Hobby projects now retain fewer deployments to free up storage
We're changing the retention exceptions for Hobby plans so that it's easier to stay within the free usage limits. Accounts above the 10GB limit will have inactive deployments automatically deleted.
Jay Gengelbach, Pranav Kanchi
Secure Compute and Static IP builds start 64% faster
Prewarmed build containers cut the average time from deployment creation to build start from 6.7 seconds to 2.4 seconds. No configuration changes required.
Ali Smesseim, Brandon Tuttle, and 1 other
Mem0 joins the Vercel Marketplace
Mem0 is now a native integration on the Vercel Marketplace, giving your AI agents and apps memory that persists across sessions.
TypeSafe AI's Jev now available on AI Gateway
Use Jev from TypeSafe AI on Vercel AI Gateway to classify, route, score, and automate workflows with typed outputs, probabilities, and confidence.
Rohan Taneja, Zachary Chen, and 1 other

Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking from Google are now available on Vercel AI Gateway for real-time audio conversations.

Is Agentic now tailors its audit by site type
Is Agentic reports now let you view checks through four site types, highlighting what matters for your site without changing your score.
Gemini 3.8 Live models now available on AI Gateway
Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking from Google are now available on Vercel AI Gateway for real-time audio conversations.
Kevin Dawkins, Zachary Chen, and 1 other

AI SDK harness layer now supports native subscription authentication

AI SDK harness layer now supports native subscription authentication
The AI SDK harness layer can now authenticate harnesses through their native subscriptions where supported, with credentials kept at the host boundary.

Vercel Connect now lets teams on Pro and Enterprise plans restrict who can create and manage connectors.

Control who can manage connectors in Vercel Connect
Vercel Connect now lets teams on Pro and Enterprise plans restrict who can create and manage connectors.

GitHub Copilot is now available in the AI SDK harness layer

Vercel Sandbox now provides 64 GB of storage
Vercel Sandbox now provides 64 GB of storage per sandbox, up from 32 GB, by default on the latest SDK and CLI versions and when created with an image.
Andy Waller, Luke Phillips-Sheard
GitHub Copilot is now available in the AI SDK harness layer
GitHub Copilot now runs through the AI SDK harness layer via @ai-sdk/harness-github-copilot, using the same HarnessAgent interface as every other supported harness.
FastAPI frontends and static files served from the CDN
FastAPI frontends and static files are now promoted to the Vercel CDN at build time and served without invoking your Vercel Function.
Build with OpenAI Agents API on Vercel
Build and deploy an OpenAI Agents API app on Vercel with Next.js, Functions, Queues, and Sandbox for isolated, persistent code execution.
Anshuman Bhardwaj, Allen Zhou
Tako Search is free on AI Gateway through September 30
Tako Search search tool is live on AI Gateway and provides live web search for any AI Gateway model. The tool is free through September 30th.
Walter Korman, Zachary Chen, and 1 other
Vercel Sandbox is now available in all regions
Vercel Sandbox now runs in all Vercel compute regions. Choose a 

Password Protection is now available per project on Pro

Password Protection is now available per project on Pro
Password Protection is now $20 per month per protected project on Pro. Enterprise includes it at the team level.
Kit Foster, Caleb Boyd, and 2 others
Protect production deployments for free on every plan
You can now use Vercel Authentication to protect production domains at no additional cost. When enabled, visitors must sign in to Vercel and have access to the project before they can open a protected deployment. 
Kit Foster, Caleb Boyd, and 2 others
DeepSeek V4.1 Flash now available on AI Gateway
all DeepSeek V4.1 Flash through Vercel AI Gateway with one API key, native image input, spend tracking, and request traces.
You can now read and search changelogs from the CLI
You and your agents can now read and search the Vercel changelog from the CLI.
Persistent memory for eve agents
Give an agent context that outlives a session: eve owns the memory slots, scope, and lifecycle; a provider owns the storage and retrieval.
v0 adds one-click integrations for email, auth, search, and databases
You can now install a new set of native Marketplace integrations, including Resend, MongoDB Atlas, Auth0, Clerk, and Amazon OpenSearch, directly

GPT Image 2.5 Flare and Sunburst now available on AI Gateway

Vercel Sandbox routing is now 18x faster globally
Sandbox routing lookups are now served from region-local data in every compute region, making them up to 18x faster globally and up to 146x faster in the farthest regions.
Marc Codina Segura, Tom Lienard, and 2 others
GPT Image 2.5 Flare and Sunburst now available on AI Gateway
Generate images with GPT Image 2.5 Flare and Sunburst through Vercel AI Gateway using one API key, with spend tracking and request traces.
Flat Rate CDN is now GA for Pro teams
Flat Rate CDN charges a flat monthly price for CDN usage, with spike protection included.
Kacie Fijalkovich, Jeff Pope, and 5 others