Vercel new features in June 2026

Everything Vercel shipped in June 2026: 22 releases, grouped by product, each linked to Vercel's release notes.

July 2026

GA 1Preview 3Beta 3Pricing 1Update 14

AI SDK and AI Gateway12

AI SDK and AI GatewayJun 30, 2026

An expanded Vercel Agent: chat, investigations, and approved actions, now in public beta

Today, we're launching expanded capabilities for Vercel Agent in public beta. Vercel Agent now lives in your dashboard and can investigate production issues, answer questions about your projects, and take action on your behalf.

BetaAI agentsSecurityPricingSource

AI SDK and AI GatewayJun 30, 2026

Claude Sonnet 5 now available on Vercel AI Gateway

Claude Sonnet 5 from Anthropic is now available on AI Gateway . Sonnet 5 improves on Sonnet 4.6 across coding and agentic work, reaching outcomes on many tasks that previously needed an Opus model, at Sonnet pricing. The model is more agentic and follows instructions more closely. Document parsing and long-context memory use are also stronger.

UpdateAI agentsLLMsPricingSource

AI SDK and AI GatewayJun 30, 2026

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) now on AI Gateway

Nano Banana 2 Lite from Google is now available on AI Gateway . This Flash-Lite-tier image model is built for fast, low-cost generation. It generates images alongside text in The cost is also lower than previous Nano Banana models.

UpdateLLMsStreamingPricingSource

AI SDK and AI GatewayJun 30, 2026

Vercel Agent has updated pricing

Vercel Agent pricing is changing. You no longer need to pre-load credits or manage a separate wallet for Vercel Agent. Instead of a $0.30 per-request fee, you now pay a Vercel Token Rate of $0.25 per million tokens, plus provider inference costs at the underlying token rate. The new Vercel Token Rate scales with the actual work each task requires.

PricingAI agentsPricingObservabilitySource

AI SDK and AI GatewayJun 30, 2026

Vercel Sandbox now support Custom Images

Vercel Sandboxes now supports custom images. Launching in public beta today, images allow Sandboxes to start with your own custom root filesystem. Images are pulled from Vercel Container Registry , so anything you docker push is immediately available.

BetaPerformanceSource

AI SDK and AI GatewayJun 29, 2026

Realtime voice, speech, and transcription now supported on AI Gateway

AI Gateway now supports voice and audio models. You can build realtime voice agents, generate speech from text, and transcribe audio to text. This provides the same observability, spend controls, and bring-your-own-key support as text, image, and video models in AI Gateway, with no markup or platform fees.

BetaAI agentsStreamingObservabilitySource

AI SDK and AI GatewayJun 29, 2026

Sandboxes now expire based on last use

Vercel Sandbox snapshots now expire based on when they were last used, not when they were created. Active snapshots stay alive as long as workflows depend on them, while unused snapshots expire on their retention policy. Every time a snapshot is used, its expiration timer resets.

UpdateGovernanceSource

AI SDK and AI GatewayJun 29, 2026

xAI Grok audio models now available on Vercel AI Gateway

xAI's audio models are now live on AI Gateway. Realtime voice, text to speech, and speech to text are all available through the AI SDK with the same routing, observability, and spend controls as your other models. These capabilities are available on the AI SDK 7 release.

UpdateAI agentsStreamingObservabilitySource

AI SDK and AI GatewayJun 26, 2026

Trace and debug eve agent sessions with Vercel Observability

You can now view Agent Runs in your Vercel dashboard for eve , the open-source agent framework. The Agent Runs tab appears automatically for every eve project, surfacing trigger, duration, and token usage for each session at a glance. Drill into any run to inspect every turn, model call, and tool call in the conversation.

UpdateAI agentsSecurityPricingSource

AI SDK and AI GatewayJun 25, 2026

AI SDK 7 is now available

AI SDK 7 is a major release for building production agents in TypeScript. The SDK has grown from model calls and chat primitives into a broader agent platform for developing, running, integrating, and observing agents across text, audio, realtime, image, and video. Every major provider is supported out of the box.

UpdateAI agentsLLMsMCPSource

AI SDK and AI GatewayJun 25, 2026

Deep Agents and OpenCode are now available in the AI SDK Harness

The AI SDK Harness lets you run established coding-agent runtimes through one unified interface, so you can switch runtimes without changing your application code. Today we're adding two new adapters, Deep Agents and OpenCode, both running inside a Vercel Sandbox.

UpdateAI agentsLLMsStreamingSource

AI SDK and AI GatewayJun 24, 2026

GLM 5.2 Fast via Wafer now available on AI Gateway

GLM 5.2 Fast via Wafer is now available on AI Gateway . Based on our own benchmarking across small-context, large-context, and tool-call scenarios, Wafer delivers a 2x higher throughput than other providers serving GLM-5.2 on serverless, leading on decode and end-to-end speed for sustained generation in the small- and large-context cases.

UpdatePricingDeveloper toolsPerformanceSource

Vercel platform10

Vercel platformJun 30, 2026

Bring your Dockerfile to Vercel Functions

Vercel Functions now support deploying HTTP servers from a Dockerfile or Containerfile , using Open Container Initiative (OCI) compatible images on Fluid compute. This makes it easier to bring existing applications written in any language to Vercel while keeping the preview deployments, logs, routing, and autoscaling benefits of using Vercel Functions and...

PreviewObservabilitySource

Vercel platformJun 30, 2026

Expanded Audit Log coverage, now delivered through Vercel Drains

Audit Logs now capture 400+ unique team activity events , giving teams broader coverage for security reviews, compliance workflows, and investigations. With Vercel Drains support, teams can export those events to custom HTTP endpoints or Amazon S3, replacing Custom SIEM Log Streaming with a flexible Drains-based workflow.

UpdateStreamingGovernanceSecuritySource

Vercel platformJun 30, 2026

Introducing VCR: Vercel Container Registry

You can now push, pull, and manage container images directly on Vercel. Vercel Container Registry is an OCI-compliant image registry hosted on Vercel infrastructure. It works with standard workflows like docker push , docker pull , and docker tag , so there's nothing new to learn or tooling to migrate. A Vercel project can have unlimited repositories.

UpdateGovernanceBISource

Vercel platformJun 30, 2026

Run multiple frameworks in one project with Vercel Services

You can now deploy multiple frontends and backends together within a single Vercel project. Vercel Services is now available , allowing you to deploy full stack apps with multiple frameworks on a shared domain, where services talk to each other privately and deployments build, preview, and roll back together.

PreviewPricingBIObservabilitySource

Vercel platformJun 30, 2026

Vercel Private Blob is now generally available

Vercel Private Blob is now generally available for all plans. Store sensitive files like user-uploaded photos, invoices, and agent memory, and control exactly who can read them. Private stores, Signed URLs, and OIDC authentication all graduate from beta with this release. Vercel Private Blob uses the same Blob API as public blobs.

GAAI agentsPricingBISource

Vercel platformJun 29, 2026

Query Speed Insights from the Vercel CLI

You can now query Speed Insights datapoints directly through the Vercel CLI. Using the vercel metrics command, you can pull core Web Vitals (LCP, INP, CLS) and other page performance metrics (FCP, TTFB) based on client-side measurements from real user traffic.

UpdateAI agentsSQLBISource

Vercel platformJun 29, 2026

Vercel Functions can now be up to 5GB in package size

Vercel Functions now support Node.js and Python deployments up to 5GB in package size on Fluid compute , a 20x increase over the previous 250MB limit. Large Functions support is in public beta .

PreviewBISource

Vercel platformJun 26, 2026

Query Web Analytics from the Vercel CLI

You can now query Web Analytics datapoints directly through the Vercel CLI. Using the vercel metrics command, you can pull page views, visitors, and custom events for your Vercel projects to analyze traffic, compare trends, and answer questions about site performance.

UpdateAI agentsSQLObservabilitySource

Vercel platformJun 24, 2026

Pro teams can now run up to 500 concurrent builds

Pro teams can run up to 500 concurrent builds, up from 12. Teams with large repos can ship faster without waiting on queued builds. On-demand concurrent builds are enabled by default for Pro and Enterprise, and you're billed only for the build minutes you use. Learn more about on-demand concurrent builds . Read more

UpdatePerformanceSource

Vercel platformJun 24, 2026

Vercel Flags no longer requires SDK Keys for Vercel deployments

New projects using Vercel Flags no longer need to configure SDK Keys or the FLAGS environment variable when evaluating flags inside a Vercel deployment. At runtime, the Vercel adapter automatically receives a short-lived OIDC token, so authentication is handled for you with zero configuration.

UpdateDeveloper toolsSource