Vercel News
Articles about Vercel News
Muse Wonder now available on AI Gateway
Muse Wonder from Meta is now available on AI Gateway. The model is designed for coding, long-running agents, and computer use. It can plan multi-step tasks, delegate work to sub-agents, and recover from errors as work progresses.
Agents can now buy domains with the Vercel CLI
Your agent can now use the Vercel CLI to buy a domain. The agent discovers candidates with vercel domains search, checks availability and registrar pricing with vercel domains check and vercel domains price, and initiates the purchase with vercel domains buy. The purchase decision itself stays with you by design. Run non-interactively, vercel domains buy returns a structured, machine-readable error and the suggested next commands, so the agent hands the confirmation back to you, prohibiting it from spending money without your approval.
New Pro teams now default to 30-day deployment retention
New Pro teams now default to a 30-day deployment retention period. Coding agents have accelerated development, increasing deployment frequency and the amount of stored deployment history. Shorter retention keeps recent history available while limiting older history and its storage costs. You can choose a longer retention period in your team's settings when you need more history for inspection or rollback. Deployment Storage and Functions Storage each cost $0.10 per GB-month. Older deployments may be deleted under your retention policy.
Deployment Storage billing begins for existing Pro teams
Deployment Storage and Functions Storage billing will begin for all Pro teams at $0.10 per GB-month. Check your email for details about when billing will start for your team. To keep storage costs low, the deployment retention window also changes to 30 days.
How Rillet ships 3× faster with AI agents on Vercel
Rillet on VercelTripled shipping rate in three months with eve agents deployed on Vercel Two-person team closed 800+ Linear tickets in its first 4 months Builder access via Enterprise Managed Users, SSO, and Directory Sync Ships customer-requested changes to production in as little as two hours Gives every builder access to models through AI Gateway Rillet is an AI-native enterprise resource planning (ERP) platform. Their AI agents do accounting work inside a real-time general ledger, with human approval and a full audit trail.
Liquid AI's d1 is available on AI Gateway
Liquid d1 is now available on AI Gateway. d1 is a decision model that evaluates shared state against typed questions for classification, routing, and scoring. It returns structured answers with probabilities without generating text tokens. d1 also has vision support: the model can answer typed questions about images for visual classification, inspection, and scoring. Use liquid/d1 through the AI SDK decision API, the OpenAI-compatible Decisions API, or the TypeSafe-compatible API. These examples ask whether a support agent issued a refund:
Microsoft Decision-1 now available on AI Gateway
Decision-1 from Microsoft is now available on AI Gateway. It answers typed questions about text with probabilities, choices, and scores. Use it to classify support requests, select the next step in a workflow, or assess an AI response against a rubric.
Skip sending request bodies to Routing Middleware
You can now skip sending client request bodies to Routing Middleware with skipMiddlewareRequestBody. This reduces incoming Fast Origin Transfer usage for middleware invocations and can improve time to first byte, especially for requests with large bodies.
Vercel Sandbox creation now returns a ready sandbox
A new Vercel Sandbox is now ready to run commands and read or write files when creation completes. Sandbox.create() now resolves only after snapshot restoration completes, so the first command or file operation no longer waits for it. Startup errors also reject Sandbox.create() instead of surfacing during that operation. Snapshot restoration time now counts toward creation instead of the first operation. Creation is about 50 ms longer at p50, with a larger increase possible for uncached snapshots.
Grok Imagine Video 1.5 Lite on AI Gateway
Grok Imagine Video 1.5 Lite from xAI is now available on AI Gateway. This lightweight model turns text prompts and images into video with native audio.
Step 5 Preview now available on AI Gateway
Step 5 Preview, StepFun's flagship model, is now available on AI Gateway. It's built for agentic coding, professional knowledge work, and financial analysis, from building apps and debugging code to research and analytical reports.
Glyph Cluster is now available in stealth for free on AI Gateway
Glyph Cluster is now available on AI Gateway as a stealth model for teams on Pro and Enterprise plans with purchased AI Gateway credits. It is free to use during the stealth period.
OpenAI Decisions API now available on AI Gateway
OpenAI's Decisions API is now available on AI Gateway through an OpenAI-compatible /v1/decisions endpoint. Use it with GPT-6 Luna Decisions or any other decision model on AI Gateway.
Claude Haiku 5.5 now available on AI Gateway
Claude Haiku 5.5 from Anthropic is now available on AI Gateway. It is built for high-volume, cost-sensitive tasks such as summaries, context compaction, database queries, and classification, and works as a subagent alongside larger Claude models on coding work. It is also the fastest Claude model at standard speed, which suits live customer support and browser use. Test it as a direct upgrade wherever you use Claude Haiku 4.5 today. Haiku 5.5 is the first Haiku model with effort levels.
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.
AI Gateway adds confidence-based decision fallbacks
Vercel AI Gateway adds decision fallbacks. Set a confidence condition on a fallback model and AI Gateway reruns the decision with it when the primary model’s answer is uncertain. Available in beta.
Mistral Large 4 now available on AI Gateway
Mistral Large 4 is now available on AI Gateway. The open-weight, natively multimodal model combines reasoning with text and image understanding. It is useful for cyber defense, manufacturing, and finance workflows.
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.
OpenAI Ultrafast mode now available on AI Gateway
AI Gateway now supports OpenAI's Ultrafast service tier for GPT-6 Astra, providing faster output for interactive applications and rapid coding iterations.
Jev for Python engineers
It's simply impossible to not hear about Jev. Seemingly everyone is tinkering with it in some way, from using it to make trading decisions (what could possibly go wrong?) to generating UIs with it (maybe we're onto something here!).
How Rogo ships agent-written code to production in 5 minutes on Vercel
Rogo on Vercel73,000+ deployments in a single month Agent-written code shipped to production in 5 minutes 6 production AI agents automating work from churn analysis to deal desk Zero manual triage during production incidents with agent swarms on AI SDK Rogo builds Felix, an AI agent that generates decks, financial models, and reports for a majority of the world's largest financial institutions. The Rogo team is rearchitecting its internal applications on Vercel, where agent-written code ships in 5 minutes.
Speed Insights deprecates First Input Delay on November 1st
Speed Insights is deprecating First Input Delay (FID), ending new measurements on November 1. Existing data remains viewable, with no action required.
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
Vercel and Microsoft AI (MAI) have partnered to make MAI models available on AI Gateway. AI Gateway is one of a limited number of platforms offering access to MAI models.
Vercel Agent now installs private packages from npm and custom registries
Vercel Agent can install private dependencies from npm and custom registries using credentials stored as shared environment variables on Vercel. npm, pnpm, and classic Yarn running in Agent sessions authenticate as they do in Vercel builds.
AI Gateway adds Browserbase Search and Fetch tools
Browserbase Search and Fetch are now available through AI Gateway. Give your models access to current information, find relevant pages, and retrieve their contents, alongside Browserbase's existing AI SDK and Vercel Marketplace integrations.
Edge Requests are now called CDN Requests
CDN Requests is now the name for the usage metric previously called Edge Requests. This is a naming change only: pricing, limits, and how usage is measured are all unchanged.
Vercel Sandbox now supports Secure Compute
Vercel Sandbox now supports Secure Compute, connecting sandboxes to a team's dedicated network. Public-internet traffic exits through the network's static IPs, and sandboxes can reach private resources in an AWS VPC through VPC peering.
Vercel CDN no longer caches responses with Vary: Cookie
Vercel CDN no longer caches origin responses when Vary includes Cookie. Vary tells a cache which request headers may change the response. Because cookies often contain visitor-specific values, varying by Cookie can create many cache entries that are rarely reused. The response is still served normally but isn't stored for future requests. You can identify these responses by checking the x-vercel-cache header and Runtime Logs. The header is set to MISS, and Logs show vary_key_denied:cookie as the cache reason.
Voyage Rerank 3 and Rerank 3 Lite are now available on AI Gateway
Rerank 3 and Rerank 3 Lite from Voyage AI by MongoDB are now available on AI Gateway. The models reorder search results by relevance before passing documents to a language model. The series improves retrieval quality across domains, with the largest gains on long documents and code. Rerank 3 focuses on accuracy, while Rerank 3 Lite is optimized for latency and cost. Both handle up to 32K tokens per query-document pair and follow instructions in the query to guide ranking. To use Rerank 3, set the model to voyage/rerank-3: For Rerank 3 Lite,
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 Connect now accepts service submissions
Vercel Connect now lets you submit your own service to the connectors directory, so you no longer need to wait for Vercel to build a connector for it. Submitting a service takes four steps: Describe your service. Add one or more connection methods, using OAuth or an API key. Verify each OAuth method by requesting a real token through a test connector. Send the submission for review. Vercel reviews each submission before publishing it to the directory.
Search trace spans from the Vercel CLI
Search trace spans from the Vercel CLI with filters for service, environment, status, and time. Use custom KQL queries and export results as JSON Lines.
GPT-6.1 Sol now available on AI Gateway
GPT-6.1 Sol from OpenAI is now available on AI Gateway. It improves on GPT-6 Sol for coding, computer use, and professional work, including reading complex documents and carrying out multi-step workflows.
Claude Sonnet 5.5 now available on AI Gateway
Claude Sonnet 5.5 from Anthropic is now available on AI Gateway as anthropic/sonnet-5.5. Sonnet 5.5 improves on Claude Sonnet 5 for well-scoped everyday work, from building features and fixing bugs to creating documents, slides, and spreadsheets. On coding tasks, Sonnet 5.5 carries changes through multiple steps and checks its work before reporting completion. It produces more polished documents, slides, and spreadsheets with fewer follow-up edits, and writes clearer explanations and reports.
Search domains without authentication
You can now discover domain names and check availability and pricing without signing in to Vercel or providing an access token. This works through the Vercel CLI and Domains Registrar API.
Ember-1 from Fireworks now available on AI Gateway
Ember-1 from Fireworks is now available on AI Gateway. Ember-1 is a research preview reasoning model built on Kimi K3 for coding and agentic workflows. Fireworks reports approximately 40% fewer generated tokens than Kimi K3 at comparable quality across its evaluations. For coding agents that make repeated model calls, shorter reasoning traces can reduce output costs and the amount of context carried into later steps. Ember-1 supports a 1M-token context window, text and image input, tool calling, and implicit prompt caching.
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.
State of agent skills
In seven months, the skills.sh registry grew to 1 million agent skills with nearly 280 million installs. This report uses aggregate data from that registry to examine what people teach agents, what gets installed, and what lasts.
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.
Vercel Sandbox now supports memory observability
Vercel Sandbox observability now includes memory usage data. You can access sandbox memory usage data in the dashboard and through the CLI via the vercel metrics command. Sandbox observability memory in the dashboardThe Memory Usage card reports average, P75, and P95 memory across your sandboxes, alongside the existing CPU usage and data transfer metrics on the sandbox overview page and the project and team-level pages. On the sandbox detail page, charts are designed to show how close a sandbox is running to its memory ceiling by:
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. Free while in stealth.
The Vercel Bug Bounty Program is now publicly available
In 2022, we launched a private bug bounty program through HackerOne. Over the last several years, we've worked with HackerOne's VIP program to refine our process, targets, and scope, onboarding thousands of their best researchers and hardening security across our platform.
How Klaviyo shipped 356 internal apps in two weeks on Vercel
Klaviyo on VercelBuilt a platform for shipping internal apps 512 builders and 356 live apps in two weeks Every app ships SSO-gated and private by default Builders go from idea to live app in 3 minutes Klaviyo is a B2C CRM for more than 200,000 brands. It brings marketing, service, agents, and data together in one platform so brands can deliver customer experiences at scale. Klaviyo built a platform on Vercel for shipping internal apps, then opened it to every employee through a citizen developer program.
Unlimited Vercel Blob stores on every plan
You can now create as many Vercel Blob stores as you need. The previous limits of 100 stores on Hobby, 500 on Pro, and 1,000 on Enterprise no longer apply.
Gemini 3.8 text-to-speech models now available on AI Gateway
Gemini 3.8 Flash-Lite TTS and Gemini 3.8 Flash TTS from Google are now available on AI Gateway. Both models take text and generate speech in more than 100 languages. They support long-form narration, control over delivery, and two-speaker dialogue. google/gemini-3.8-flash-lite-tts is suited to high-volume speech generation, with controls for tone, pacing, and line-by-line delivery. google/gemini-3.8-flash-tts adds voice and character design through natural-language prompts, including acting cues, accents, and conversational reactions.
GPT-6 Sol and Luna now available on AI Gateway
GPT-6 Sol and GPT-6 Luna from OpenAI are now available on AI Gateway. Both models bring GPT-6 improvements in professional work, coding, computer use, factuality, and communication at a lower price than GPT-6 Astra. GPT-6 Sol (openai/gpt-6-sol) is suited to complex professional workflows and sustained coding tasks where quality and room to iterate both matter. GPT-6 Luna (openai/gpt-6-luna) is the lower-cost option for high-volume agentic workflows, coding, and everyday tasks.
Drives for Vercel Sandbox are now in public beta
Drives for Vercel Sandbox are now available in public beta on Hobby, Pro, and Enterprise. A Drive is persistent storage that you mount as a directory in a Vercel Sandbox. It isn’t tied to a single sandbox, so you can reuse the same Drive across runs and different sandbox instances. Use Drives to preserve an agent's workspace or on-disk memory, or to reuse datasets, models, and dependency trees. Create and mount a DriveCreate or retrieve a Drive and mount it at a path when starting a sandbox.
Vercel Connect now supports Microsoft Teams
Vercel Connect now includes a managed connector for Microsoft Teams. Creating one gives your organization a Teams bot that your apps and agents run. People can @mention it in channels or message it directly, and your code receives the message and replies as the bot.
Deployments now show billable duration and CPU minutes
See each deployment’s build time, post-build time, billable duration, and CPU minutes in the Vercel dashboard, the CLI, 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.
Spend Management expands to Enterprise Flexible Commitment plans
Spend Management now supports Enterprise teams on Flexible Commitment plans. Set a budget per billing cycle and get alerts, webhooks, or an optional pause.
WebMCP support now available in mcp-handler
mcp-handler now has experimental support for WebMCP, the proposed web standard for exposing tools to in-browser agents. Add a single script tag to your site, and your existing MCP tools become available there too.
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.
Jev is the fastest-adopted model in AI Gateway history
Within 24 hours of launching on AI Gateway, Jev from TypeSafe AI reached more than twice as many paid teams as any previous model launch, making it the fastest-adopted model in gateway history.
Reproducing, disclosing, and fixing the libheif vulnerability with Hacktron and the maintainers
In August 2026, Hacktron reported what looked like a remote code execution (RCE) vulnerability in Next.js image optimization. Their investigation found that the vulnerable code was not in Next.js itself, but upstream in libheif, an AVIF image decoder used by Next.js, ImageMagick, WordPress, sharp, and much of the web.
GLM 5.3 FlashX now available on AI Gateway
GLM 5.3 FlashX is now available on AI Gateway. GLM 5.3 FlashX is a high-speed serving option for Z.ai's multimodal coding model, delivering inference at ~200 tokens per second for faster streamed responses. The higher serving speed is useful for coding agents, tool loops, and interactive applications where users wait on generated output. Use zai/glm-5.3-flashx across API formats and in coding agents:
Sub-second artifact deployments are now supported in Vercel CLI
You and your agents can now deploy static artifacts to Vercel in under one second through Vercel CLI. Run vercel deploy to share a prototype, publish an HTML report, or preview a page created by your coding agent. Vercel automatically detects eligible deployments, and valid artifacts will skip the build step, immediately returning a live URL. Instant deployments support directories with: Up to 10 HTML or Markdown files A total size of 5 MB or less Supported file extension include .html, .htm, and .md.
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
You can now run Harbor evals on Vercel Sandbox. Harbor is the open-source harness behind Terminal-Bench, whose registry includes many other benchmarks such as SWE-bench, tau3-bench and OSWorld. Pass --env vercel to harbor run and each trial executes in its own isolated Firecracker microVM, so you can parallelize far beyond what your local machine is capable of. A task's network policy is enforced at the sandbox firewall, outside the VM.
Open-weight models take 56% of token volume, Astra doubles Fable 5.1 spend
AI Gateway Production Index — September 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 looks like in today's enterprise, and we publish it here monthly. See the Production Index reports from June, July, and August. September 2026 summaryThe September index reports on AI Gateway data collected through August 2026. Open-weight models ran the majority of gateway tokens for the first time, up from 7% in December to 56% in August.
GPT-Live 1 now available on AI Gateway
GPT-Live 1 from OpenAI is now available on AI Gateway. GPT-Live 1 is a full-duplex voice model and can listen and speak at the same time. Many voice models use turn detection to respond. Full duplex removes that boundary, so a user can pause, interrupt, or add detail while GPT-Live is speaking. GPT-Live 1 also supports client delegation. Client delegation lets you choose the background model independently from GPT-Live 1. A basic session runs only the voice model.
Hobby projects now retain fewer deployments to free up storage
Hobby projects now retain fewer deployments past the 30-day retention window. Hobby teams get 10GB of Deployment Storage. Every deployment you keep uses some of it, and going over the limit can block you from deploying until you free some up. Deployment Retention for Hobby teams now deletes old deployments sooner, so dormant projects stop holding storage that your active projects need.
Is Agentic now tailors its audit by site type
Is Agentic reports now show checks by site type: Docs & content, Business, App, or Commerce. Your score stays the same, only the highlighted checks change.
TypeSafe AI's Jev now available on AI Gateway
Jev from TypeSafe AI is now available on AI Gateway. Jev is a probabilistic decision model for software: state goes in, typed Choice, Score, and Boolean answers come out. Regular language models generate text one token at a time, which the application then parses and validates. Jev evaluates all declared questions in parallel and returns typed answers plus probabilities directly. That removes unnecessary text generation and makes it straightforward to automate clear cases while routing uncertain ones to review.
How Delphi ships 100 times a day with its Python backend on Vercel
Delphi on Vercel10 engineers with no dedicated infrastructure role Everyone ships code, including product and design 100+ production deploys a day behind feature flags Delphi builds digital minds. They capture what someone has written, recorded, and taught, so anyone can tap that expertise on demand. Delphi is “a destination where you can find and interact with interesting minds,” says founding engineer Spencer Schoeben.
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 AI Gateway. Both models support real-time spoken interactions for voice assistants, conversational experiences, and applications that respond through audio. google/gemini-3.8-live supports real-time audio, visual grounding, automatic switching across 97 languages, and background tool calls while the conversation continues.
AI SDK harness layer now supports native subscription authentication
The AI SDK harness layer now supports authenticating harnesses through their native subscriptions, where the underlying harness supports them. The harness layer runs different coding agents through the same HarnessAgent interface, so you can switch agents without changing your application code.