Vercel new features in July 2026

Everything Vercel shipped in July 2026: 103 releases, grouped by product, each linked to Vercel's release notes.

June 2026 August 2026

GA 1Preview 8Beta 9Deprecation 1Pricing 1Update 83

Vercel platform58

Vercel platformJul 31, 2026

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.postEphemeral() or channel.postEphemeral() to send native, targeted messages that only the intended user sees, like permission prompts.

UpdateSecurityDeveloper toolsSource

Vercel platformJul 31, 2026

Run background tasks with Celery on Vercel

Celery , an asynchronous distributed task queue for Python, is now supported natively on Vercel. Tasks are executed as Vercel Functions and automatically scale with traffic. By default, task results are stored in Runtime Cache , which is sufficient for small data sizes and relatively short workflow runtimes.

UpdatePricingSource

Vercel platformJul 31, 2026

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 2025 protocol keep working exactly as before, and clients that understand the new specification pick it up automatically.

UpdateMCPObservabilityDeveloper toolsSource

Vercel platformJul 31, 2026

Vercel Passport is now generally available

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 provider before viewing a protected deployment, and Vercel forwards a signed identity token to the deployment so application code can build on who the visitor...

GASecuritySource

Vercel platformJul 30, 2026

Deployments are now up to 7 seconds faster

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 up to 2 seconds more. The improvements are most noticeable on smaller builds, where orchestration represents a larger share of the total build time.

UpdateStreamingBIDeveloper toolsSource

Vercel platformJul 30, 2026

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 draw directly from your existing commitment making it easier to provision the infrastructure and services your applications need.

UpdatePricingDeveloper toolsSource

Vercel platformJul 30, 2026

Latest MCP spec now supported in mcp-handler

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 servers on popular web frameworks including Next, Nuxt, Svelte, and more.

UpdateMCPStreamingDeveloper toolsSource

Vercel platformJul 30, 2026

Project-scoped Tokens

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 token is scoped to. Requests to any other project, a user-level resource, or a team-level resource will be denied.

UpdateDeveloper toolsSource

Vercel platformJul 30, 2026

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 and cache hits. These values appear in the browser's network panel and as PerformanceServerTiming entries through the Performance API.

UpdateSQLObservabilityDeveloper toolsSource

Vercel platformJul 30, 2026

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 alternative to long-lived Personal Access Tokens (PATs).

UpdateGovernanceDeveloper toolsSource

Vercel platformJul 29, 2026

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 , qa , or any named stage between preview and production , and each environment gets its own branch tracking, environment variables, and domains.

PreviewSecurityPricingBISource

Vercel platformJul 29, 2026

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 install an integration: Integrations write their files directly into your project and can add anything an eve agent uses, from a single tool to a channel to a...

UpdateAI agentsGovernanceObservabilitySource

Vercel platformJul 29, 2026

Edge Config is now Global Config

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 runtime, such as feature flags, redirects, and experimentation settings.

UpdatePricingDeveloper toolsRegionsSource

Vercel platformJul 29, 2026

Sign in with ChatGPT is now available on Vercel

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 Vercel plugin to ChatGPT, you can easily sign in to Vercel and grant team and project permissions without leaving ChatGPT.

BetaSecurityObservabilitySource

Vercel platformJul 28, 2026

Vercel Connect now supports Custom Environments

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, Preview, and Development when you add or edit a project on a connector in the dashboard.

PreviewPricingData integrationBISource

Vercel platformJul 27, 2026

Nuxt July 2026 security advisory

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.

UpdateSecurityDeveloper toolsSource

Vercel platformJul 27, 2026

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. Continue conversations without repeated mentions Mentions no longer have to carry the conversation.

UpdateAI agentsDeveloper toolsSource

Vercel platformJul 24, 2026

Vercel WAF for Blob is now in beta

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 @vercel/blob . Every blob is already served through Vercel's CDN , so protection is a switch on the store, not a new proxy.

BetaBIObservabilityDeveloper toolsSource

Vercel platformJul 23, 2026

Evaluation metrics for Vercel Flags

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 shifts to specific configuration changes. You can group and filter evaluations by variant, reason, environment, SDK key, client, and reporting project.

UpdateObservabilityDeveloper toolsSource

Vercel platformJul 23, 2026

GitHub tools are now an installable eve extension

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 rules built in.

UpdateAI agentsSecurityData integrationSource

Vercel platformJul 23, 2026

Inspect feature flag history with Vercel CLI

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 revision's author, message, timestamp, and changed environments.

UpdateDeveloper toolsCoding agentsSource

Vercel platformJul 23, 2026

Vercel MCP can now deploy code

The Vercel MCP server can now deploy code directly to a new or existing project. When your AI assistant finishes building something, it can ship it to Vercel and hand back a shareable URL without leaving the chat. Point the deploy_to_vercel tool at your files and Vercel creates the project, detects the framework, installs dependencies, and builds.

UpdateLLMsMCPCoding agentsSource

Vercel platformJul 23, 2026

WebSocket support is now available for Python Functions

Vercel now supports WebSocket connections for Python applications. WebSockets enable bidirectional communication between client- and server-side code, powering real-time features like interactive AI streaming, real-time chat, and multiplayer live collaboration.

UpdateStreamingDeveloper toolsSource

Vercel platformJul 21, 2026

Python function bundles now include precompiled bytecode

Vercel now compiles Python functions to bytecode at build time. In our benchmarks, cold starts for the median-sized function dropped from 2.8s to 1.3s . Cold starts are already rare in practice.

UpdatePricingPerformanceSource

Vercel platformJul 21, 2026

Vercel Connect adds 100+ preset connectors

Vercel Connect now includes preset connectors for 100+ services, including Shopify, Resend, Sanity, Okta, Workday, and Jira. Preset connectors are predefined configurations for supported services. They reduce manual setup by pre-populating the brand name, icon, auth type, and MCP or discovery URL.

UpdateMCPData integrationBISource

Vercel platformJul 21, 2026

Vercel MCP now supports purchases

Vercel MCP now supports purchasing Vercel products. You can: Upgrade your team to the Pro plan Add prepaid credits for v0 (requires a paid v0 plan) or AI Gateway Purchase the SIEM add-on (requires an Enterprise plan) Purchase and register a domain Vercel MCP quotes the price, explains whether the charge is one-time or recurring, and completes the purchase...

UpdateMCPPricingSource

Vercel platformJul 20, 2026

Purge your Remote Cache's build and CI artifacts

Team Owners can now clear the team's Remote Cache of all artifacts in one click. This is useful when you believe there are poisoned artifacts in your cache. In your team's Build and Deployment settings, visit the Remote Caching section and clear the Remote Cache. Visit the docs to learn more. Read more

UpdateSource

Vercel platformJul 17, 2026

Optimized CDN caching and deploying of immutable static assets

Vercel now reuses static files across deployments for frameworks that output content-addressed assets. It's zero-config: Vercel uses Framework-defined infrastructure to manage these immutable files alongside your code changes, handling the hard parts like hash collisions, file lifecycles, and efficient routing.

PreviewSQLPricingDeveloper toolsSource

Vercel platformJul 17, 2026

Runtime logs now show cache reasons

Runtime logs now show a Cache Reason explaining why a request wasn't a fresh cache hit, for example a time-based or tag-based revalidation. Use cache reasons to debug misses and improve your hit rate.

UpdateGovernanceObservabilityDeveloper toolsSource

Vercel platformJul 17, 2026

Vercel Plugin now available in Kimi Code CLI

The Vercel Plugin is now available in the Kimi Code CLI . Kimi Code can now draw on Vercel platform knowledge on demand, with skills for Next.js, AI SDK, Vercel Functions, and more. The Vercel Plugin also helps Kimi Code stay up to date with the latest Vercel APIs and recommended patterns.

UpdateDeveloper toolsSource

Vercel platformJul 16, 2026

Write utilization now available in ISR Observability

The ISR Observability page now shows Observability Plus subscribers a write utilization metric, helping identify routes that regenerate often but receive few requests. Write utilization is the ratio of cached requests to ISR writes.

UpdateAI agentsPricingObservabilitySource

Vercel platformJul 15, 2026

Chat SDK adds Discord Components V2 support

You can now send Discord bot messages with Components V2 , an opt-in layout system that treats text, images, files, and buttons as flexible components you can arrange in any order. Set the adapter's contentFormat option to ComponentsV2 and cards render with native containers, sections, media galleries, separators, buttons, and string selects.

UpdateGovernanceSecurityDeveloper toolsSource

Vercel platformJul 15, 2026

Faster, predictable project linking in the Vercel CLI

The Vercel CLI now resolves your team before discovering projects, then searches for projects only in that team instead of sweeping every team you belong to. Linking is faster and more predictable, and every command that establishes a link ( vercel link , deploy , pull , dev , and git connect ) follows the same flow: Teams resolve from an explicit signal...

UpdateAI agentsDeveloper toolsPerformanceSource

Vercel platformJul 15, 2026

Vercel Connect support in GitHub Tools

GitHub Tools now has first-class support for Vercel Connect through the new @github-tools/sdk/connect subpath. Instead of storing a long-lived personal access token, your agent mints short-lived, scoped GitHub tokens at runtime from a connector. There is no secret to store, rotate, or leak.

UpdateAI agentsSecurityData integrationSource

Vercel platformJul 14, 2026

Chat SDK adds X adapter support

Chat SDK now supports X, extending its single-codebase approach to Slack, Discord, GitHub, Teams, Telegram, and WhatsApp with the new X adapter . Teams can build bots that reply to public mentions and hold direct message conversations through the X API v2 and the X Activity API .

UpdateStreamingSecurityDeveloper toolsSource

Vercel platformJul 14, 2026

Endform joins the Vercel Marketplace

Endform is now available on the Vercel Marketplace . It runs your Playwright tests in parallel, so your suite finishes in the time of your slowest test. Key capabilities: Run every test on its own isolated machine Bring your existing Playwright tests with no config changes Get a pass/fail check on every production and preview deployment, linked to full...

PreviewBIDeveloper toolsSource

Vercel platformJul 14, 2026

Node.js 20 is being deprecated on October 1, 2026

Following the Node.js 20 end of life on April 30, 2026, we are deprecating Node.js 20 for Builds and Functions on October 1, 2026. How can I see which of my projects are affected? You can see which of your projects are affected by this deprecation with: Will my existing deployments be affected?

DeprecationAI agentsSecurityCoding agentsSource

Vercel platformJul 14, 2026

Vercel Blob now supports consistent reads on private storage

Vercel Blob now supports consistent reads on private storage. Pass useCache: false to get() or presignUrl() for a read that reflects the latest write. A blob written to a fresh pathname has no existing cached entry, so reads reflect the latest write immediately.

UpdateAI agentsSQLDeveloper toolsSource

Vercel platformJul 14, 2026

Vercel Plugin now available in VS Code and GitHub Copilot CLI

The Vercel Plugin is now available in VS Code and the GitHub Copilot CLI. GitHub Copilot now has Vercel platform knowledge on demand, with skills for Next.js, AI SDK, Vercel Functions, and more. The Vercel plugin also helps Copilot stay up to date with the latest Vercel APIs and recommended patterns.

UpdateDeveloper toolsCoding agentsSource

Vercel platformJul 13, 2026

Configure which sources can create deployments with Deployment Policies

Deployment Policies are now available and enable teams to restrict which mechanisms, organizations, and repositories are allowed to create deployments. Each policy can be configured per environment at the team and project level, allowing flexible combinations of rules. Learn more about Deployment Policies . Read more

UpdateGovernanceSource

Vercel platformJul 13, 2026

Manage Vercel Flags targeting rules from the CLI

You can now manage targeting rules for Vercel Flags through the Vercel CLI . With the vercel flags rules command, you and your agents can add new rules, move existing ones, and inspect the current ordering without leaving your terminal. Rules you create from the CLI use the same model as the dashboard.

UpdateAI agentsBIDeveloper toolsSource

Vercel platformJul 13, 2026

Web Analytics and Speed Insights are now more cost-efficient

Web Analytics and Speed Insights are now almost 10% more cost-efficient for all Pro and Enterprise teams. Infrastructure and event-processing improvements reduced cost across both products, so page views, referrers, top routes, and Core Web Vitals are now processed more efficiently, and savings scale with your event volume.

UpdatePricingSource

Vercel platformJul 10, 2026

Traces now support Tree and Waterfall views

Traces in Vercel Logs now support Tree and Waterfall views. See span hierarchy, critical path, and timing without leaving the log entry. The Tree view groups spans by parent and child. On load, spans are sorted by duration so the slowest appear first.

UpdateObservabilitySource

Vercel platformJul 9, 2026

Build logs now redact Sensitive Environment Variable values

When an Environment Variable is marked Sensitive and has a value 32 characters or longer, Vercel now replaces it with [REDACTED] in the deployment's build logs. The Build Logs view also indicates when redaction happened, giving teams visibility into why output was masked without ever exposing the underlying value.

UpdateSecurityObservabilitySource

Vercel platformJul 9, 2026

You can now deploy Lovable apps to Vercel

Vercel now supports Lovable applications with zero configuration. To get started, sync your Lovable project to GitHub , then import the repository to Vercel. Vercel automatically detects the framework ( TanStack Start ) and deploys your app. Once connected, every change you make in Lovable syncs to GitHub and triggers a new deployment on Vercel.

UpdateSource

Vercel platformJul 8, 2026

Chat SDK adds Dial support

Chat SDK now supports Dial with the new vendor-official adapter . Build bots that send and receive SMS, MMS, and iMessage on a real phone number, with bidirectional media and inbound voice-call transcripts. Replies use the standard Chat SDK thread and message APIs, with HMAC-verified webhooks and stable per-conversation threading.

UpdateDeveloper toolsSource

Vercel platformJul 8, 2026

Chat SDK adds Photon support

Chat SDK now supports Photon with the new vendor-official adapter . Build bots that send and receive iMessages directly and in group chats, share media, and react with native tapbacks. Run the adapter against Spectrum Cloud, your own server, or directly on a Mac. Each Photon conversation becomes a Chat SDK thread, and tapbacks come through as reactions.

UpdateDeveloper toolsSource

Vercel platformJul 8, 2026

Chat SDK now supports Vercel Connect

You can now use Vercel Connect to manage credentials for your Chat SDK bots, with no tokens or signing secrets to store or rotate yourself. The new @vercel/connect/chat subpath provides adapter helpers for Slack, GitHub, and Linear. Each helper takes a connector UID and returns a config you spread into the matching adapter factory.

UpdateSecurityData integrationDeveloper toolsSource

Vercel platformJul 8, 2026

Flags SDK now evaluates flags 10x faster

Flags SDK and Vercel Flags now evaluate multiple feature flags in bulk around 10x faster. Flag evaluation time improved by reducing microtask queue overhead and creating fewer promises. The improvement scales with the number of flags.

UpdateDeveloper toolsPerformanceSource

Vercel platformJul 8, 2026

Update Project Settings from the Vercel CLI

You can now update a project's framework preset and build settings directly from the CLI, without opening the dashboard. Run vercel project update from a linked project, or pass a project name directly: Settings can also be returned to automatic detection instead of an explicit override: For automation or further inspection, return the result as JSON: JSON...

UpdateAI agentsBIDeveloper toolsSource

Vercel platformJul 8, 2026

Use any Chat SDK adapter with eve

eve now supports Chat SDK adapters with the new Chat SDK channel . One channel connects your eve agent to Facebook Messenger, WhatsApp, Resend, Liveblocks, and any other surface with an adapter . You write normal Chat SDK handler code, and calling send inside a handler hands the message to your agent.

UpdateAI agentsDeveloper toolsSource

Vercel platformJul 8, 2026

Vercel Microfrontends checks for missing configuration

The Microfrontends Config Present deployment check prevents broken production routing by blocking any default app deployment that is missing its microfrontends.json . This appears alongside other Native Deployment Checks , such as lint and typecheck. The check is blocking by default for eligible apps, with no opt-in required.

UpdateDeveloper toolsSource

Vercel platformJul 7, 2026

You can now view the Activity Log at a project-level

Project Settings now includes its own project-specific A ctivity Log . This view pulls the relevant user events from the Activity Log in Team Settings. Review project-level activity without leaving your project settings. Visit your project settings to try it out. Read more

UpdateObservabilitySource

Vercel platformJul 3, 2026

Manage Vercel Flags segments with Vercel CLI

Vercel Flags segments can now be managed from the Vercel CLI with the new vercel flags segments command. A segment is the targeting primitive a flag uses to decide who sees what. Membership composes from three repeatable tokens: include: , exclude: , and rule: . Pass them to --add or --remove for incremental edits.

UpdateAI agentsData integrationDeveloper toolsSource

Vercel platformJul 1, 2026

Dry-run deployments with Vercel CLI

You can now preview the framework preset and files that Vercel CLI includes in a deployment before creating one. Run vercel deploy --dry from a linked project: For automation or further inspection, return the complete file manifest as JSON: JSON output includes the detected framework, included and ignored paths, directory size distribution, largest files...

PreviewAI agentsDeveloper toolsSource

Vercel platformJul 1, 2026

Resend joins the Vercel Marketplace

You can now provision and manage Resend directly from the Vercel Marketplace. This integration helps developers start sending messages within minutes, build emails as React components, and track delivery events in real time.

UpdateAI agentsStreamingDeveloper toolsSource

Vercel platformJul 1, 2026

Secure internal communication between services (beta)

Service Bindings make it easy for one Vercel service to securely call another within the same deployment. When a service declares a binding for another service, Vercel automatically injects the configured environment variable.

BetaPricingObservabilityDeveloper toolsSource

Vercel platformJul 1, 2026

Vercel Security Dashboard is in private beta

The Vercel Security Dashboard is now in private beta. It aggregates the security posture of every account and project on Vercel. As teams grow and coding agents make it easy to spin up new projects, small misconfigurations can add up quietly and quickly.

BetaAI agentsSecurityBISource

AI SDK and AI Gateway45

AI SDK and AI GatewayJul 31, 2026

10x more capacity for Laguna S 2.1 on AI Gateway

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 far more requests, good for high-volume agentic coding and long-running tasks.

UpdateAI agentsPricingDeveloper toolsSource

AI SDK and AI GatewayJul 31, 2026

AI Gateway adds unified fast mode support

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's available and falls back to standard speed when it isn't. Fast mode trades a higher per-token cost for lower latency or higher throughput.

BetaAI agentsLLMsPricingSource

AI SDK and AI GatewayJul 31, 2026

AI Gateway logs now have a dedicated page

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. Open any request to see how it was routed. It's available at the team scope and per project.

UpdatePricingObservabilityRegionsSource

AI SDK and AI GatewayJul 31, 2026

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 once the limit is reached, until the budget resets or you raise it. Scopes A budget attaches to one of three scopes.

UpdateBIDeveloper toolsSource

AI SDK and AI GatewayJul 31, 2026

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. Requests to deepseek/deepseek-v4-flash pick up the new weights automatically, with no change to the model ID or your code.

PreviewAI agentsPricingDeveloper toolsSource

AI SDK and AI GatewayJul 31, 2026

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 ID, region , or any custom run attribute. Paste a run ID to pull up that exact run.

PreviewSQLObservabilityRegionsSource

AI SDK and AI GatewayJul 30, 2026

AI Gateway: GPT-5.6 pricing and speed updates

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 to both short and long context pricing.

PricingLLMsStreamingPricingSource

AI SDK and AI GatewayJul 30, 2026

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 per task. It is a broad generalist with native reasoning over audio and images, and it holds up well on reasoning, agentic coding, and tool use.

UpdateAI agentsPricingBISource

AI SDK and AI GatewayJul 30, 2026

MiniMax H3 now available on AI Gateway

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 image-to-video, the model supports first-to-last keyframe transitions and multimodal reference-to-video, conditioning a generation on reference images, video...

UpdateDeveloper toolsSource

AI SDK and AI GatewayJul 30, 2026

Run multiple isolated agents in a single Sandbox

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 opens a shared workspace when they need to collaborate. This makes multi-agent systems easier to build.

UpdateAI agentsDeveloper toolsSource

AI SDK and AI GatewayJul 29, 2026

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, transcription accuracy, and conversation. The model reasons in parallel with speech, so it can think through a query while talking without adding latency.

UpdateAI agentsSQLStreamingSource

AI SDK and AI GatewayJul 28, 2026

Vercel Sandbox supports forking

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 latest saved state, not the live in-memory state. If the source has no snapshot, it falls back to a fresh create, using the source's runtime and config.

UpdateAI agentsDeveloper toolsSource

AI SDK and AI GatewayJul 27, 2026

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 supported for both models. Running Kimi K3 on US-based providers lets teams with data residency and compliance requirements use the model on US infrastructure.

UpdateGovernancePricingBISource

AI SDK and AI GatewayJul 27, 2026

Regional inference now available on AI Gateway

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 there, and any data the provider keeps is stored there.

UpdateGovernancePricingDeveloper toolsSource

AI SDK and AI GatewayJul 27, 2026

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 , instead of re-sending the full context over a fresh HTTP request every turn.

UpdateAI agentsStreamingDeveloper toolsSource

AI SDK and AI GatewayJul 24, 2026

Claude Opus 5 now available on AI Gateway

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 feature work, and completing full tasks rather than leaving stubs or placeholders.

UpdateAI agentsLLMsSecuritySource

AI SDK and AI GatewayJul 24, 2026

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_EXTENDED_MAX_DURATION to 1 in your project's Environment Variables, then redeploy. Requires Fluid compute and a supported Node.js or Python runtime.

BetaPricingSource

AI SDK and AI GatewayJul 23, 2026

Connect to and manage Sandboxes from the dashboard

You can now connect to any running Sandbox from the Vercel dashboard. Run commands, browse the filesystem, upload and download files, and inspect open ports without leaving the browser. From the same view, you can also manage the sandbox lifecycle: take snapshots, and stop or resume persistent sandboxes. Open the Connect tab on any sandbox to try it out.

UpdateBISource

AI SDK and AI GatewayJul 23, 2026

Ling 3.0 Flash is now available on AI Gateway

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 parameters and about 5.1B active per token. It has a 256K token context window and runs in thinking and non-thinking modes.

UpdateAI agentsPricingDeveloper toolsSource

AI SDK and AI GatewayJul 22, 2026

AI Gateway now supports streaming transcription

AI Gateway now supports streaming transcription . Previously, transcription required a complete audio file and returned the full transcript in a single response. Now you can stream audio in as it's captured and get transcript updates back as the model produces them, keeping latency low for uses like live captioning and voice input.

BetaAI agentsStreamingDeveloper toolsSource

AI SDK and AI GatewayJul 22, 2026

Extend eve agents with installable extensions

You can now package tools, connections, skills, instructions, and hooks into extensions that any eve agent can import. Extensions can be published to package registries, then installed, versioned, and upgraded like any other project dependency.

UpdateAI agentsSource

AI SDK and AI GatewayJul 21, 2026

Gemini 3.6 Flash and Gemini 3.5 Flash-Lite are now available on AI Gateway

Gemini 3.6 Flash and Gemini 3.5 Flash-Lite are now available on AI Gateway. Gemini 3.6 Flash improves quality across coding, agentic tasks, and web development while consuming fewer tokens and making fewer model calls. It produces cleaner web and app development output.

UpdateAI agentsLLMsPricingSource

AI SDK and AI GatewayJul 21, 2026

Laguna S 2.1 is now available on AI Gateway

Laguna S 2.1 from Poolside is now available on AI Gateway. There are 2 versions of the model available: Free version (256K context window): poolside/laguna-s-2.1-free Paid version (1M context window): poolside/laguna-s-2.1 Laguna S 2.1 is an open-weight Mixture-of-Experts model that supports a context window of up to 1M tokens and runs in thinking and...

UpdateAI agentsPricingData integrationSource

AI SDK and AI GatewayJul 21, 2026

Service tiers now available on AI Gateway

AI Gateway now supports service tiering. Service tiers let you optimize for latency, throughput, and cost per request to match your use case. Pick a faster tier for interactive workloads (less queueing, higher token throughput), or a lower cost tier for background jobs that can tolerate more latency.

UpdateLLMsPricingDeveloper toolsSource

AI SDK and AI GatewayJul 20, 2026

Configure where run state lives in Vercel Workflows

Vercel Workflows now keeps each run's state, queue dispatch, and output streams in a single home region: the region where the run starts by default, or any target region you choose.

BetaAI agentsStreamingDeveloper toolsSource

AI SDK and AI GatewayJul 17, 2026

Chat SDK adds native Slack agent support

You can now build native Slack agents with Chat SDK's Slack adapter . The adapter supports the full Slack agent messaging experience , from agent conversations in the Messages tab to suggested prompts, rotating status messages, token-by-token streamed replies, and native feedback buttons.

UpdateAI agentsStreamingPricingSource

AI SDK and AI GatewayJul 17, 2026

Data downloaded by Vercel Sandbox is now free

Vercel Sandbox no longer bills for data it downloads from the internet. Installing packages, cloning a Git repository, or pulling artifacts and datasets from an external source does not count toward Sandbox Data Transfer usage. Traffic received on a Sandbox's exposed ports is still billable, as is outbound traffic the Sandbox sends to the internet.

UpdatePricingSource

AI SDK and AI GatewayJul 17, 2026

GLM 5.2 is 35% off via Novita on AI Gateway

GLM 5.2 is 35% off on AI Gateway through July 24 when routed through Novita. To get the discounted rate, set the model to zai/glm-5.2 in the AI SDK and route requests through Novita: After July 24, the model stays available at standard provider rates with no markup. Try GLM 5.2 in the model playground . Read more

UpdateDeveloper toolsSource

AI SDK and AI GatewayJul 16, 2026

Kimi K3 is now available on AI Gateway

Kimi K3 from Moonshot AI is now available on AI Gateway. K3 is an open-source model with a 1M-token context window and native visual understanding, accepting text, image, and video inputs.

UpdatePricingDeveloper toolsPerformanceSource

AI SDK and AI GatewayJul 15, 2026

Inkling from Thinking Machines is now available on AI Gateway

Inkling from Thinking Machines is now available on AI Gateway. Inkling is a broad generalist model, trained across agentic, reasoning, coding, instruction-following, factuality, vision, and audio tasks rather than optimized for a single domain. The model also supports controllable thinking effort.

UpdateAI agentsPricingDeveloper toolsSource

AI SDK and AI GatewayJul 15, 2026

Vercel Workflows trace viewer now has a minimap

The trace viewer for Vercel Workflows now has a minimap that shows the entire run in one view. Drag the viewport to pan, resize it to zoom, or drag across the minimap to select a new section. Click anywhere on the minimap to jump to that point, or scroll and use arrow keys to step through the run.

BetaDeveloper toolsSource

AI SDK and AI GatewayJul 14, 2026

Access and share AI Gateway leaderboard data

We are making the data behind the AI Gateway leaderboards open under the CC BY 4.0 license . You can now download or query the data through the leaderboard-export API endpoint and render any chart as a shareable image. The AI Gateway leaderboards show how AI is used in production, ranking traffic for models, labs, apps, and providers.

UpdateSQLPricingObservabilitySource

AI SDK and AI GatewayJul 14, 2026

AgentMail joins the Vercel Marketplace

You can now provision and manage AgentMail directly from the Vercel Marketplace. Your AI agents can send, receive, and respond to email from a real inbox. AgentMail handles the mail servers and deliverability.

UpdateAI agentsDeveloper toolsSource

AI SDK and AI GatewayJul 13, 2026

Agent Runs now show subagent activity on eve projects

You can now inspect subagent activity for eve projects in Agent Runs . The new Subagents tab shows every subagent, organized by which turn started it. Each row shows the prompt, duration, and any failures, all on a shared timeline. Click any subagent to open its run.

UpdateAI agentsPricingSource

AI SDK and AI GatewayJul 11, 2026

Seedream 5.0 Pro is now available on AI Gateway

Seedream 5.0 Pro is now available on AI Gateway . Seedream 5.0 Pro is an image generation and editing model. It generates images from text, rendering text without spelling errors and following typographic rules, and produces dense infographics with charts, timelines, and layouts alongside realistic imagery.

UpdatePricingDeveloper toolsPerformanceSource

AI SDK and AI GatewayJul 9, 2026

GPT 5.6 Sol, Luna, and Terra now available on AI Gateway

GPT 5.6 is now available on AI Gateway in three models: Sol, Terra, and Luna. GPT 5.6 from OpenAI is now available on AI Gateway in a limited preview, across three models: Sol, Terra, and Luna. All three are stronger at agentic work across coding, biology, and cybersecurity, and are more token-efficient than the previous generation.

PreviewAI agentsLLMsSecuritySource

AI SDK and AI GatewayJul 9, 2026

Muse Spark 1.1 is now available on AI Gateway

Muse Spark 1.1 from Meta is now available on AI Gateway . It is a multimodal reasoning model with a 1M token context window built for agentic tasks, accepting text, image, video, PDF, and audio inputs.

UpdateAI agentsMCPPricingSource

AI SDK and AI GatewayJul 8, 2026

Grok 4.5 now available on AI Gateway

Grok 4.5 from SpaceXAI is now available on AI Gateway . Built for coding, knowledge work, and STEM, the model accepts text and image inputs. Grok 4.5 supports low, medium, and high reasoning levels and defaults to high. Set the level with reasoning to balance speed against depth.

UpdatePricingDeveloper toolsPerformanceSource

AI SDK and AI GatewayJul 7, 2026

Give your eve agent GitHub tools

GitHub Tools now ships an eve toolset through the new @github-tools/sdk/eve subpath. One file in agent/tools/ can register every GitHub tool, or use a preset such as maintainer , so you can build a complete GitHub agent in nine lines of code. Safe by default: Every write tool, such as mergePullRequest , requires approval unless you opt out.

UpdateAI agentsDeveloper toolsSource

AI SDK and AI GatewayJul 7, 2026

More granular observability for Vercel Sandbox

Vercel Sandbox observability now includes detailed resource metrics, giving you deeper visibility into how your sandboxes consume compute and networking. From the Observability tab in your dashboard, you can now monitor: Active CPU and CPU usage: Measures when your code actively uses the CPU.

UpdateAI agentsSQLPricingSource

AI SDK and AI GatewayJul 3, 2026

Agent Runs now available in the Vercel MCP and CLI

Your agent can now inspect Agent Runs via the Vercel MCP and CLI for eve , the open-source agent framework. eve traces are automatically ingested when deployed to Vercel and available as Agent Runs.

UpdateAI agentsMCPData integrationSource

AI SDK and AI GatewayJul 3, 2026

Vercel Sandbox now supports FUSE-based filesystems

Vercel Sandbox now supports FUSE, letting you mount remote storage and custom filesystems inside a running Sandbox. Use it to attach S3 buckets, network filesystems, or any other FUSE-compatible driver as a regular path.

UpdateStreamingDeveloper toolsSource

AI SDK and AI GatewayJul 2, 2026

Routing rules now available on AI Gateway

Vercel AI Gateway now supports routing rules . Routing rules are firewall-style rules that control which models your team can use, applied at the gateway level instead of in your application code. When a model goes down or gets retired, you usually have to ship a code change to move off it.

UpdateDeveloper toolsSource

AI SDK and AI GatewayJul 1, 2026

Claude Fable 5 access restored on AI Gateway

Access to Claude Fable 5, the Mythos-class model, has now been restored on AI Gateway following the US Government's decision to lift the export controls. Fable 5 is the same model that was available between June 9 and June 12. What has changed is the safety classifiers, which are now updated and more robust.

UpdateLLMsStreamingDeveloper toolsSource

AI SDK and AI GatewayJul 1, 2026

Enforce consistent code for agents and humans with konsistent

konsistent is now open source. konsistent is a CLI linter for TypeScript codebases that enforces structural conventions, giving agents and humans the consistent context they need to implement features correctly. Deterministic, fast, and covers structural patterns that TypeScript and ESLint don't model.

UpdateAI agentsDeveloper toolsSource