# Vercel updates

Every Vercel update in one feed — release notes, features and changes, straight from the source.

1309 updates

- ## [Introducing Geist Serif](<https://creatorstoolbox.com/blog/vercel-introducing-geist-serif>)

Geist Serif is a high-contrast display face for headlines, available now on npm and as a download in Regular weight, with more weights to follow.

2026-10-30

- ## [Add liveness checks to your Daemons](<https://creatorstoolbox.com/blog/vercel-add-liveness-checks-to-your-daemons>)

Daemons in Public Beta on all plans can now point a livenessProbe at an HTTP endpoint, and Vercel restarts the container when it fails.

2026-10-30

- ## [Ling 3.1 Flash 1019 now available on AI Gateway for free](<https://creatorstoolbox.com/blog/vercel-ling-3-1-flash-1019-now-available-on-ai-gateway-for-free>)

InclusionAI's 1M-token coding and agent model costs nothing on AI Gateway until November 3, 2026, and works in Claude Code, Codex and Cursor.

2026-10-30

- ## [Simplifying runtime caching on Vercel](<https://creatorstoolbox.com/blog/vercel-simplifying-runtime-caching-on-vercel>)

Pro projects get 8x the cache storage and Enterprise 10x, but reads and writes that were unbilled under Data Cache will now be charged.

2026-10-30

- ## [Data Cache is moving to Runtime Cache](<https://creatorstoolbox.com/blog/vercel-data-cache-is-moving-to-runtime-cache>)

Pro projects get 8x the cache storage, but previously unbilled reads and writes now cost from $0.40 and $4.00 per million units.

2026-10-30

- ## [Vercel Daemons can now call services with bindings](<https://creatorstoolbox.com/blog/vercel-vercel-daemons-can-now-call-services-with-bindings>)

Daemons declare a binding that names a service and an env variable, then call the private service's URL with a plain HTTP request.

2026-10-30

- ## [Mistral Large 4 updated weights and lower pricing on AI Gateway](<https://creatorstoolbox.com/blog/vercel-mistral-large-4-updated-weights-and-lower-pricing-on-ai-gateway>)

Existing mistral/mistral-large-4 calls on AI Gateway pick up the new weights and lower token prices automatically, with no change to the model ID.

2026-10-29

- ## [IP geolocation now covers more visitors at higher resolution](<https://creatorstoolbox.com/blog/vercel-ip-geolocation-now-covers-more-visitors-at-higher-resolution>)

Enabled for all Vercel projects, the update gives postal codes for 90% of traffic, and VPN and hosting-provider visitors may now resolve elsewhere.

2026-10-29

- ## [Vercel Plugin is now available in Antigravity](<https://creatorstoolbox.com/blog/vercel-vercel-plugin-is-now-available-in-antigravity>)

The Vercel Plugin adds Vercel API guidance and skills for AI SDK, Functions and Workflow, installed from Customizations → Marketplace in Antigravity.

2026-10-29

- ## [Block AI crawlers and assistants independently with managed rules](<https://creatorstoolbox.com/blog/vercel-block-ai-crawlers-and-assistants-independently-with-managed-rules>)

The AI Bots managed ruleset lets you set separate log or block actions for crawlers and assistants, from the dashboard or CLI, on all plans.

2026-10-29

- ## [Vercel Flags starts 7x faster and no longer extends function duration](<https://creatorstoolbox.com/blog/vercel-vercel-flags-starts-7x-faster-and-no-longer-extends-function-duration>)

Updating @flags-sdk/vercel to 1.5.3 cuts p75 cold-start initialization from over 70 ms to 10 ms and stops usage reporting from adding function time.

2026-10-29

- ## [Vercel Connect adds webhook triggers for more providers](<https://creatorstoolbox.com/blog/vercel-vercel-connect-adds-webhook-triggers-for-more-providers>)

Connect adds webhook triggers for Resend, X, Twilio, Notion and Telegram, joining Slack, Discord, Teams, GitHub and Linear.

2026-10-29

- ## [Strix now supports Vercel AI Gateway](<https://creatorstoolbox.com/blog/vercel-strix-now-supports-vercel-ai-gateway>)

Strix users can set one AI Gateway key and pick from 400+ models, with usage and cost tracked in Vercel and no markup.

2026-10-29

- ## [Node.js 26 LTS is now Generally Available on Vercel](<https://creatorstoolbox.com/blog/vercel-node-js-26-lts-is-now-generally-available-on-vercel>)

Projects whose engines.node range already allows 26, such as &gt;=20, move to it on their next deployment, and HTTP/2 fetch can be switched off.

2026-10-29

- ## [fx is now available in T3 Code](<https://creatorstoolbox.com/blog/vercel-fx-is-now-available-in-t3-code>)

T3 Code users can add fx as a provider on web, desktop and mobile, with Supervised and Auto modes and their existing fx models and skills.

2026-10-28

- ## [Box Mount now runs in Vercel Sandbox](<https://creatorstoolbox.com/blog/vercel-box-mount-now-runs-in-vercel-sandbox>)

Box Mount is in private preview, with access requested from Box, and syncs a Box folder to a sandbox directory so agent output survives sandbox deletion.

2026-10-28

- ## [Vercel CI is now in beta](<https://creatorstoolbox.com/blog/vercel-vercel-ci-is-now-in-beta>)

Vercel CI runs only the Turborepo tasks a change affects, is open to all plans, and cut push-to-pass time 2-6x in Vercel's own repositories.

2026-10-28

- ## [Introducing Vercel CI](<https://creatorstoolbox.com/blog/vercel-introducing-vercel-ci>)

The Beta runs only Turborepo tasks tagged "ci", with Remote Cache on by default, and currently supports GitHub repositories on Linux.

2026-10-28

- ## [Agents can now enable Web Analytics and Observability Plus with Vercel CLI](<https://creatorstoolbox.com/blog/vercel-agents-can-now-enable-web-analytics-and-observability-plus-with-vercel>)

Vercel CLI 64.2.0 drops the interactive-terminal requirement, though Observability Plus still needs an existing team subscription.

2026-10-28

- ## [Vercel Container Registry now supports 2 GB compressed image layers](<https://creatorstoolbox.com/blog/vercel-vercel-container-registry-now-supports-2-gb-compressed-image-layers>)

Layers in Vercel's registry can now reach 2 GB compressed, up from 500 MB, while the total image limit stays at 15 GB.

2026-10-28

- ## [Particle-1 is now available on AI Gateway](<https://creatorstoolbox.com/blog/vercel-particle-1-is-now-available-on-ai-gateway>)

Particle-1, post-trained on DeepSeek V4.1 Flash with a 1M-token context, is callable as particle/particle-1 and works in Claude Code, Codex and Cursor.

2026-10-28

- ## [Run Paseo agents on Vercel Sandbox](<https://creatorstoolbox.com/blog/vercel-run-paseo-agents-on-vercel-sandbox>)

The plugin needs Paseo 0.9 and Node.js 24, and stopped sandboxes keep files and history as snapshots that expire after 24 hours.

2026-10-28

- ## [Introducing Virtual Models on AI Gateway](<https://creatorstoolbox.com/blog/vercel-introducing-virtual-models-on-ai-gateway>)

Teams can swap models, fallbacks and Zero Data Retention behind one ID in AI Gateway, with apps and coding agents picking changes up in minutes.

2026-10-28

- ## [HarnessAgent now supports image inputs for all harness adapters](<https://creatorstoolbox.com/blog/vercel-harnessagent-now-supports-image-inputs-for-all-harness-adapters>)

Developers can mix text and image file parts in one message, and all ten harness adapters, from Claude Code to Pi, process them with their vision models.

2026-10-27

- ## [Vercel Agent sessions now cost 67% less](<https://creatorstoolbox.com/blog/vercel-vercel-agent-sessions-now-cost-67-less>)

The 67% average saving applies to dashboard and Slack sessions with no action needed, and billing rates stay the same.

2026-10-27

- ## [ElevenLabs on AI Gateway](<https://creatorstoolbox.com/blog/vercel-elevenlabs-on-ai-gateway>)

Vercel's AI Gateway now carries 14 ElevenLabs speech, music and sound effect models, at half price through November 9th.

2026-10-27

- ## [AI traffic insights now available in Vercel Observability](<https://creatorstoolbox.com/blog/vercel-ai-traffic-insights-now-available-in-vercel-observability>)

The new Observability tab breaks down AI crawler and assistant requests, and CLI queries for the same data require Observability Plus.

2026-10-27

- ## [Deploy a container from a plain Dockerfile](<https://creatorstoolbox.com/blog/vercel-deploy-a-container-from-a-plain-dockerfile>)

Vercel's beta Container runtime builds a root Dockerfile or Containerfile on all plans, with Active CPU billing and no other framework detected.

2026-10-27

- ## [Vercel Plugin now available in OpenCode](<https://creatorstoolbox.com/blog/vercel-vercel-plugin-now-available-in-opencode>)

The plugin needs OpenCode 2 and adds Vercel skills, specialist agents, and deploy and env commands, with the Vercel MCP server connected separately.

2026-10-27

- ## [The fx adapter now runs the harness on the host](<https://creatorstoolbox.com/blog/vercel-the-fx-adapter-now-runs-the-harness-on-the-host>)

The AI SDK's experimental fx adapter keeps model credentials on the host and adds tool filtering, mid-turn steering, structured output and resumable sessions.

2026-10-27

[Open Vercel updates on Creators Toolbox](<https://creatorstoolbox.com/updates/vercel>)

---
Canonical source: https://creatorstoolbox.com/updates/vercel
