Vercel — Cloud, Developer Tools product updates and releases, tracked on megachangelog.
Fireworks' Ember-1, a reasoning model optimized for coding and agentic workflows, is now available on Vercel's AI Gateway. It generates approximately 40% fewer tokens than comparable models while maintaining quality, helping reduce costs and context overhead for agents making repeated calls.
You can now push container images from GitHub Actions to Vercel Container Registry using GitHub OIDC authentication, eliminating the need for long-lived registry credentials. The vercel/vcr-action/login action exchanges your workflow's OIDC token for a short-lived Vercel access token that is automatically revoked when the job ends.
Vercel's skills.sh registry reached one million agent skills in seven months with nearly 280 million installs. The report analyzes skill adoption patterns across categories, showing high demand for business operations and writing skills, while most installs concentrate on cross-industry and portable skills that apply broadly across jobs and industries.
Pixel Canary, a new AI model optimized for coding and frontend development, is now available for free in stealth on Vercel's AI Gateway. The model achieves 90.3% success on Next.js evals and 96.8% with documentation, enabling developers to use it for app migrations, data fetching, and web interface implementation.
Vercel Sandbox now includes memory usage data accessible through the dashboard and CLI. You can view average, P75, and P95 memory metrics, track memory usage against the sandbox ceiling, and create custom queries and alerts using the memoryUsedBytes measure.
Vercel has consolidated its private and open-source bug bounty programs into a single public HackerOne program. The move expands researcher access to discover vulnerabilities across the entire Vercel platform while leveraging improved security processes and tooling to handle the increased volume of submissions.
Klaviyo launched a citizen developer program on Vercel that enabled 512 employees to deploy 356 full-stack internal apps in two weeks, with built-in security through SSO, Secure Compute, and identity provider integration requiring no builder configuration.
Vercel Connect adds support for TanStack AI agents to call OAuth-protected MCP servers with automatic token management and no credential storage required. The new connectMCPTransport subpath export integrates Connect-backed auth that provides fresh tokens before every request and handles consent challenges before the model executes.
Vercel Blob now allows unlimited store creation across all plans, removing previous limits of 100 (Hobby), 500 (Pro), and 1,000 (Enterprise). Store creation is billed as an advanced operation, enabling better data separation for production/staging environments, multi-tenant applications, and preview deployments.
Google's Gemini 3.8 Flash-Lite TTS and Gemini 3.8 Flash TTS models are now available on Vercel's AI Gateway, supporting 100+ languages with long-form narration, delivery control, and multi-speaker dialogue. Users get unified API access, usage tracking, and cost per-request visibility alongside other models.
Claude Opus 5.5 from Anthropic is now available via Vercel's AI Gateway with improved agentic coding, long-context reasoning, and a 1M-token context window. The model includes two breaking API changes: adaptive thinking (no longer allows disabling thinking or fixed budgets) and removal of forced tool use in favor of structured outputs.
Drives provide persistent storage that can be mounted as directories in Vercel Sandbox and reused across multiple sandbox instances. Each Drive supports up to 16 TiB of configurable storage with read/write pricing, enabling users to preserve agent workspaces, datasets, and models across sandbox runs.
Vercel's AI Gateway now supports OpenAI's GPT-6 Sol and Luna models, offering improved performance in coding, professional work, and factuality at lower cost than GPT-6 Astra. Sol is optimized for complex workflows requiring quality iteration, while Luna is the cost-effective option for high-volume agentic tasks.
Vercel Connect now includes a managed connector for Microsoft Teams, allowing organizations to create a Teams bot that their apps and agents can run. The bot can be mentioned in channels or messaged directly, and Vercel handles Entra app registration and Azure Bot resource management without requiring manual client secret storage.
Deployments now display their billable duration and CPU minutes in the dashboard, REST API, and CLI, helping users understand how each build contributes to their usage. Billable duration is the combined build and post-build time rounded up to the next whole minute, and CPU minutes are that figure multiplied by the machine's vCPUs.
Grok 4.7 from xAI is now available on Vercel's AI Gateway with a 500K token context window, configurable reasoning levels, and 40% off pricing through September 27. The model works with AI SDK, OpenAI-compatible APIs, and coding agents like fx and eve.
Xiaomi's MiMo V2.6 model family (Pro, Flash, and Pro UltraSpeed) is now available on Vercel's AI Gateway. These multimodal models support text, image, audio, and video understanding with 1M token context, structured outputs, and tool use capabilities for coding and agent workflows.
AI Gateway now supports calling Jev, a probabilistic decision model from TypeSafe AI, through TypeSafe clients, an HTTP API, or the AI SDK. All requests are billed through AI Gateway and appear in unified usage and observability, with support for boolean, choice, and score evaluation types.
Spend Management is now available at no additional cost to Enterprise teams on Flexible Commitment plans. Teams can set budgets per billing cycle and receive email notifications, trigger webhooks, or pause production deployments when metered usage approaches the budget threshold.
mcp-handler now has experimental support for WebMCP, a web standard for exposing tools to in-browser agents. Add a script tag to your site to make your MCP tools available to browser agents, with authentication handled transparently for signed-in users.
v0 now installs private packages from npm and custom registries using credentials stored as shared environment variables on Vercel, making it easier for teams to build with their existing design systems and internal packages directly in v0.
Jev, a specialized probabilistic decision model from TypeSafe AI, reached 13% of paid teams within 24 hours of launch on AI Gateway, doubling the adoption of any previous model. The model is optimized for structured decision-making in software with typed output and was reported to be up to 194x faster and 445x cheaper than general-purpose language models.
GLM 5.3 FlashX, a high-speed serving option for Z.ai's multimodal coding model, is now available on AI Gateway, delivering inference at ~200 tokens per second. This enables faster streamed responses for coding agents, tool loops, and interactive applications.
A remote code execution vulnerability was discovered in libheif, an AVIF image decoder used upstream by Next.js image optimization. Vercel coordinated with Hacktron and open source maintainers to responsibly disclose and fix the issue, deploying platform-wide mitigations and releasing patched versions across the dependency chain.
Vercel CLI now supports deploying static artifacts (HTML, HTM, and Markdown files) to live URLs in under one second by skipping the build step for eligible deployments. Users can share prototypes, publish reports, or preview agent-generated pages with a single command.
You can now opt into Turbo build machines on a per-deployment basis via Git commit message, CLI flag, or REST API, allowing you to temporarily increase build resources without modifying project settings.
You can now run Harbor evaluations, including Terminal-Bench and other benchmarks like SWE-bench and OSWorld, on Vercel Sandbox. Each trial runs in an isolated Firecracker microVM with network policy enforcement and optional credential injection, allowing you to parallelize benchmarking beyond local machine capabilities and test multiple models via AI Gateway.
The skills CLI now accepts Notion-hosted skills databases as an install source, allowing teams to author, review, and manage reusable agent skills directly in their Notion workspace without requiring a Git repository. Access and installation permissions follow Notion's built-in page sharing model.
Vercel's monthly AI Gateway Production Index shows open-weight models processed 56% of tokens in August 2026, their first month capturing majority volume. The data reveals shifting competitive dynamics as Anthropic's Opus 5 gained share when Fable 5 lost demand, while OpenAI's new GPT-6 Astra captured one-third of OpenAI spend within two days of launch, outpacing Anthropic's Fable 5.1.
GPT-Live 1, a full-duplex voice model from OpenAI, is now available on Vercel's AI Gateway. It can listen and speak simultaneously without turn detection, and supports client delegation to run background text models while maintaining the conversation.
Native Marketplace resources can now be connected to custom environments in addition to production, preview, and development. This lets you scope environment variables created by connections to specific custom environments via the dashboard, CLI, or REST API.
Hobby projects now keep only their 3 most recent production deployments and 3 most recent deployments of any type, with older deployments deleted immediately if a team exceeds the 10GB storage limit. This change helps dormant projects stop consuming storage needed by active projects.
Builds using Secure Compute or Static IPs now start 64% faster by using prewarmed containers with network configuration attached at build start, reducing average startup time from 6.7 to 2.4 seconds with no configuration changes required.
Mem0 is now available as a native integration on the Vercel Marketplace, providing AI agents and apps with long-term memory capabilities for user preferences, facts, and context across sessions. Setup is simplified with integrated billing, automatic provisioning of a scoped Mem0 project and API key, and no separate account management required.
TypeSafe AI's Jev, a probabilistic decision model for software, is now available on AI Gateway. Jev evaluates questions in parallel and returns typed answers with probabilities directly, enabling faster and cheaper decision-making compared to traditional language models for structured reasoning tasks.
Is Agentic audit reports now let you filter and view checks across four site types—Docs & content, Business, App, or Commerce—each highlighting checks relevant to that site category. You can set your default view with a meta tag, and your score remains consistent across all views.
Delphi rebuilt its Python backend on Vercel and now ships 100+ times a day with feature flags, eliminating heavyweight staging deployments and enabling faster iteration. New engineers can reach production in minutes instead of a day, and the entire team—including product and design—can deploy changes as everyday work.
Google's Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking models are now available through Vercel's AI Gateway, supporting real-time spoken interactions via the realtime API with features like multi-language support and parallel reasoning.
The AI SDK harness layer now authenticates through native subscriptions where supported by the underlying harness. Credentials remain on the host while the harness receives placeholder credentials, enabling seamless agent switching without code changes across adapters like Claude Code, Cline, and GitHub Copilot.
Vercel Sandbox now provides 64 GB of storage, increased from 32 GB, across all sandbox types including those created from Vercel Managed Images or custom images. This additional capacity supports larger repositories, dependencies, build artifacts, and disk-based data workloads.
Tailscale built Aperture, a customer-facing AI model router on Vercel's AI Gateway and Sandbox, enabling companies to control model access through network identity while ensuring zero data retention and safe agent execution without building infrastructure in-house.
Featured, a PR co-pilot platform, migrated from AWS Elastic Beanstalk to Vercel, enabling their 3-engineer team to handle 100,000+ monthly media pitches across 374 sites. The move simplified infrastructure management by consolidating single-click deploys, unified AI model routing through AI SDK and AI Gateway across 17 models, and enabled rapid feature development using Workflow SDK and Vercel's eve agent framework.
Pro and Enterprise teams can now restrict who creates and manages connectors using a new Connector Manager permission. Once enabled, only Owners and users with the Connector Manager role can manage credentials and external service access.
The AI SDK harness layer now supports GitHub Copilot through an official adapter, enabling developers to switch between different coding agents without changing application code. The harness layer uses the Agent Client Protocol (ACP) to connect multiple coding agents including Claude Code, Cline, Cursor, and others.
FastAPI frontends and static files are now automatically promoted to the Vercel CDN at build time, serving requests directly from the CDN without invoking your Function. Route precedence and runtime access are preserved, with configuration options to exclude directories or override CDN behavior.
Vercel Sandbox is now available across all 20 compute regions instead of four, enabling lower latency and better regional control. Teams can set default regions, configure failover options, and ensure compliance with data residency requirements.
Vercel optimized CDN metadata lookup by grouping path metadata into shards instead of storing individual cache entries per path. This reduced P99 latency by 91% and sped up deployments, especially for large sites with hundreds of thousands of paths.
Tako Search, a model-agnostic search tool that combines curated knowledge with live web data and source citations, is now available for free on AI Gateway through September 30th. Developers can integrate it via the AI SDK using gateway.tools.takoSearch() in text generation requests.
Vercel now integrates with OpenAI Agents API to enable long-running, tool-using agent workflows hosted on Vercel's infrastructure. Developers can leverage OpenAI's managed agent loop combined with Vercel Sandbox for isolated code execution and Vercel Queues for webhook processing, creating scalable agent applications without maintaining virtual machines.
Pro teams can now purchase Password Protection on a per-project basis for $20 per month instead of team-wide, allowing visitors to enter a password to view project deployments. This provides more granular control and cost management for teams that only need protection on specific projects.
Vercel Authentication and Deployment Protection are now available at no cost on all plans, allowing users to protect production and preview deployments without the $150/month add-on. Deployment Protection Exceptions also let you selectively make specific preview domains public.
v0 now supports one-click integrations with providers like Resend, Clerk, MongoDB Atlas, Algolia, and Amazon OpenSearch. Users can prompt v0 to build features, and when a provider is needed, v0 renders a connect card in chat to automatically handle environment variables, configuration, and provider-specific agent skills.
DeepSeek V4.1 Flash is now available on Vercel's AI Gateway with native image understanding, supporting text and images in the same request, a 1 million token context window, and responses up to 384,000 tokens. The model includes reasoning, tool use, and prompt caching capabilities with optimized architecture for reduced computation.
You can now read and search the Vercel changelog feed directly from your terminal using the vercel changelog command, allowing you and your agents to discover new products, features, and updates relevant to your projects.
Eve agents can now retain context across sessions using persistent memory organized into slots with configurable providers and scopes. Memory is automatically retrieved before each turn and added to the model's context, with support for file storage, Supermemory, Upstash, and custom providers.
The deployment step is now approximately 10% faster by combining separate routing metadata files into a single manifest. This optimization applies automatically to all builds without requiring any changes.
Vercel Sandbox now resolves public domains from nearest regional replicas instead of a centralized store, reducing median domain lookup latency from 62ms to 3.4ms and improving performance by up to 146x in remote regions like Cape Town.
Vercel launches Flat Rate CDN, a predictable monthly billing model for CDN usage that eliminates surprise overages from traffic spikes while maintaining premium network quality. All new Pro teams get it by default, and existing Pro teams can opt in to choose a capacity tier matching their usage profile.
Flat Rate CDN, an alternative to usage-based billing that provides a fixed monthly bill with included capacity, is now generally available for Pro teams. New Pro teams have it enabled by default, and existing teams can switch over in their billing settings.
Vercel's AI Gateway now supports OpenAI's GPT Image 2.5 Flare and Sunburst models for image generation and editing. Flare is optimized for faster generation while Sunburst provides tighter control for detailed creative work, both supporting complex visual instructions and transparent backgrounds.
Ling 3.0 Flash Sante, a health and medicine-focused AI model, is now free to use on AI Gateway through October 4. The model offers 124B parameters with 256K token context and function calling, built for medical reasoning and healthcare tasks, with no platform fees or data retention.
OpenAI's GPT 6 Astra model is now available on Vercel AI Gateway for long-running agentic work including software engineering, browser automation, research, and professional workflows. Access it via the openai/gpt-6-astra model identifier in your code or integrate it with coding agents like Cursor and Codex.
Cursor Cloud Agents can now execute in Vercel Sandbox instead of Cursor's hosted machines, leveraging Vercel Functions and Vercel Workflow to provide isolated Firecracker microVMs per agent request with automatic provisioning, monitoring, and cleanup.
Pro and Enterprise teams can now select Basic build machines with 2 vCPUs and 8 GB memory as a cost-efficient alternative, while new projects continue to default to automatically-scaling Elastic machines. Pricing remains at $0.007 per build minute.
Pro teams can now claim a free domain for one year across eight eligible TLDs, including the newly added .app and .dev extensions. The offer covers one domain per team, with automatic renewal at regular pricing after the first year.
Muse Spark 1.3 from Meta is now available on Vercel's AI Gateway with improved agent work and coding capabilities, featuring a 1M token context window and support for text, image, and PDF input. A new contributor pricing tier offers lower rates in exchange for allowing Meta to use inputs and outputs for model training.
Gemini 3.8 Flash is now available on AI Gateway with a 1M token context window, multi-modal input support, tool calling, and web search capabilities. The model is 50% off through December 31st and features improved performance on software engineering and reasoning tasks.
GLM-5.3 model is available at 50% discount through September 8 in partnership with DigitalOcean on AI Gateway. The model supports 1M token context window with 128K max output and can be used via the promo code zai/glm-5.3-promo-50 or through standard naming with provider options.
Vercel announced Fluid, a unified compute layer that dynamically provisions and optimizes machines for different workload types (builds, functions, sandboxes, agents). Fluid powers over 15 million daily builds and a trillion monthly requests by assembling hardware to fit each workload's needs instead of forcing workloads to fit fixed infrastructure.
Qwen 3.8 Max 0902 from Alibaba is now available on Vercel's AI Gateway. This snapshot improves coding on larger projects, long-horizon autonomous work, agent runs, and vision accuracy on charts and dense documents.
Claude Fable 5.1 from Anthropic is now available on Vercel's AI Gateway, featuring improvements in agentic coding, knowledge work, and multi-stage research. The model includes safety classifiers for cybersecurity and biology, with support for fallback models to ensure requests succeed when safety checks are triggered.
AWS PrivateLink is now available for Pro and Enterprise teams, enabling Vercel Functions and builds to securely connect to AWS-hosted services, databases, and internal resources without routing traffic over the public internet. The first connection is included with Advanced Networking, with additional connections priced at $30 per month plus $0.04 per GB for data transfer.
The AI SDK harness layer now supports fx, Vercel's lightweight open-source coding agent, enabling developers to integrate fx into their applications through a unified API without building separate integrations.
You can now set individual dollar spending limits for each user on your team in AI Gateway, controlling spend from all their API keys and app tokens. When a user reaches their budget, AI Gateway rejects new requests until the budget resets or increases, helping prevent uncontrolled spending from coding agents and shared workloads.
Vercel introduced design.md, a public guidance file that enables coding agents and external tools to build pages consistent with Vercel's design system and brand. The system combines design rules, a reusable stylesheet with design primitives, and an evaluation loop to ensure agents generate on-brand output without reinventing visual styles.
Vercel now calculates snapshot storage charges based on each day's average usage instead of a single monthly average, providing more granular billing that reflects actual daily usage patterns. The rate remains $0.08 per GB-month, and the change applies automatically at the next billing period for Pro and Enterprise teams.
MiniMax H3 and H3 Max video models are now 50% discounted on Vercel's AI Gateway through September 13. The discount applies to all requests billed through AI Gateway at any duration and aspect ratio, with no code changes required as model IDs remain unchanged.
You can now create and deploy agents directly from the Vercel dashboard with a builder that scaffolds the project, creates a private Git repository, and deploys it to your team. Configure the agent's identity, choose an AI model through AI Gateway, add a web chat or Slack interface, and connect tools and data from services like Linear, Notion, or custom MCP servers.
Hy4 Preview, a 770B parameter open-source Mixture-of-Experts model from Tencent, is now available on Vercel's AI Gateway. The model supports 1M token context windows and is optimized for coding, document analysis, and scientific reasoning, accessible via the AI SDK with no platform fees.
Vercel CLI now includes dedicated commands for managing DNS records, domains, and projects, enabling terminal-based configuration that was previously only available in the dashboard. New capabilities include updating DNS records, renewing domains, controlling project state and observability, and managing project members with JSON output support.
The AI SDK harness layer now supports Cursor through an official adapter, allowing applications to switch between different coding agents without changing application code. The adapter uses the Agent Client Protocol to connect Cursor to the HarnessAgent interface.
The Deployments page now features redesigned filters that enable faster discovery of specific deployments. Users can apply suggested filters for common searches, type to find options, and use natural language to describe what they're looking for for automatic filter application.
Vercel introduces Workflow SDK, a new durable execution framework that lets developers write workflows as normal sequential code without complex DAG configuration or infrastructure management. The open-source, spec-based system uses only standard infrastructure like databases and queues, with client-side execution and automatic versioning to handle code changes without breaking in-flight runs.
Inclusion AI's Ling 3.0 Flash Fin, a finance-focused LLM with 256K token context and 32K output tokens, is now available on Vercel's AI Gateway at no cost through September 25. The model supports reasoning and function calling for financial research and multi-step analysis tasks.
The Vercel Security Dashboard is now generally available on all plans, automatically flagging security misconfigurations across accounts and projects with risk-ordered findings and actionable fixes. The dashboard is accessible via the Vercel UI and CLI, with support for muting noise, exporting results to CSV, and agentic remediation through the vercel security check command.
Google's Gemini 3.5 Transcribe model is now available on AI Gateway, supporting both streaming and batch audio transcription with multi-language detection and custom vocabulary. The AI SDK V7 adds streamTranscribeReadable for real-time streaming transcription via WebSocket.
Meta's Muse Image, their first image generation model, is now available on Vercel's AI Gateway. The model supports both image generation from text prompts and image editing with instructions, unified in a single model without switching.
Alibaba's Qwen 3.8 Flash model is now available on Vercel's AI Gateway, supporting text and image inputs with a 1M token context window and up to 65k token responses. The model is recommended for coding, tool use, and multi-step agent workflows.
GLM 5.3 Flash from Zhipu AI, a multimodal model with 1M token context window supporting text and vision input, is now available on Vercel AI Gateway. The model supports function calling, structured output, and streaming through the unified API interface.
Python projects can now use routing rules to set response headers or rewrite requests to internal paths. Rules are evaluated by the Vercel CDN before requests reach your application and take effect immediately without requiring a new deployment.
Two critical vulnerabilities affecting Next.js image optimization and Windows-hosted servers were disclosed in August 2026. Vercel-hosted applications are automatically protected and require no action, while self-hosted Next.js applications must upgrade to patched versions.
Speed Insights now offers a free tier providing high-level performance monitoring from real users across all plans with 10,000 events per team per month. The paid tier is renamed Speed Insights Plus with deeper diagnostics and historical data, while existing customers see only name changes with no impact to capabilities or pricing.
Vercel introduced the Run SDK, a package for safely executing untrusted JavaScript and TypeScript code in a sandboxed environment without direct access to application secrets or systems. It enables agents to write programs that call narrowly scoped host functions, with support for interrupting execution for authentication and human approval before resuming without repeating completed work.
Vercel Connect replaces long-lived credential tokens with short-lived, scoped tokens requested at runtime, eliminating the security risks of stored secrets. The platform provides 100+ pre-built connectors for services like Slack, GitHub, and Salesforce, along with fine-grained RBAC, audit logging, and trigger-based event handling without exposing secrets to applications.
The Chat SDK now includes an XChat adapter enabling bots to build end-to-end encrypted 1:1 and group conversations. The adapter automatically handles encryption, key management, and signature verification, with fallback rendering for XChat's limited markdown support.
Vercel Connect introduces a managed Linq connector enabling apps and agents to send and receive messages over iMessage, RCS, and SMS. Users can create a new Linq account or link an existing one without managing credentials directly.
Vercel's Chat SDK Slack adapter now supports Slack Enterprise Grid, enabling org-wide bot installations across workspaces with correct token resolution, tenant-scoped caches, and event deduplication. The adapter stores enterprise-wide installations by enterprise ID and handles multi-workspace deployments securely.
Vercel's Chat SDK now includes a Notion adapter, allowing agents to participate in Notion page comments and discussions using the same codebase as other platforms like Slack and Discord. The adapter supports mentions, message editing, conversation history, and file attachments.
AI Gateway can now run video generation asynchronously using webhooks, polling, or deferred job retrieval, allowing applications to avoid blocking HTTP requests that could exceed timeouts. This enables more flexible workflows where your application can receive completion notifications or check status later instead of waiting for potentially long-running video renders.
MiniMax M3 and M2.7 models are now available for free on AI Gateway via GMI Cloud through September 6. Use the -free model IDs or set GMI Cloud as your preferred provider to access these models across all AI Gateway APIs.
97 more changes from Vercel. Sign up to read the whole changelog.
Sign up freeGitHub or email — no card needed.