Vercel — Cloud, Developer Tools product updates and releases, tracked on megachangelog.
Vercel is updating Terms of Service for Hobby and Pro customers effective October 19, 2026, clarifying credit policies, managed accounts, auto-renewal practices, and adding statutory cancellation and refund rights for UK and EU consumers, including protections for service changes with negative impact.
MiniMax M3.1 Flash, an open-weight multimodal model with 1M-token context window for coding and agentic work, is now available on Vercel's AI Gateway at no cost through October 20. The model excels at complex agent tasks, coding applications, and cybersecurity work, and can be used through multiple APIs and coding agents.
Inception's Mercury 3 model is now available on Vercel's AI Gateway with 50% launch pricing and generation speeds exceeding 1,000 tokens per second. The model enables parallel text refinement with a 1M-token context window, ideal for real-time applications like browser agents and customer support.
AI Gateway logs now include a Sessions view that groups requests into sessions and displays how session affinity routed each request, including details about the coding agent, cost, models, providers, and cache hit rates across conversation turns.
DeepSeek V4.1 Flash 1017 is now available on AI Gateway, offering improvements in reasoning, coding, agentic tasks, and image understanding with faster task completion and reduced token usage. The model can be accessed via the unified AI Gateway API with provider pricing and no platform fees.
Vercel Shop, an open source Next.js storefront template, is now generally available and enables AI agents to interact with online stores through machine-readable product data and the Universal Commerce Protocol. Teams can build storefronts that serve both human shoppers and agents with shared cart and checkout experiences.
Reflection AI's Beam, a low-latency open-weight reasoning model for coding and agentic tasks, is now available on Vercel's AI Gateway at no cost during the launch period. The model is accessible through AI Gateway's unified API and integrates with popular coding tools like Claude Code, Codex, and Cursor.
Elorian's Glimpse visual reasoning model is now available on AI Gateway, enabling users to analyze images and video for object tracking, spatial reasoning, and action-consequence interpretation. The model supports use cases like scientific chart analysis, video captioning, and robotics annotation, with integration available via the elorian/glimpse model identifier.
Perplexity's Decider V1.2 27B and Decider Flash V1.2 4B multimodal decision models are now available through Vercel's AI Gateway. These models can classify content, route requests, and score text and images with probability-based answers, enabling use cases like support ticket routing and product damage flagging.
Vercel expanded its Enterprise Apps and Agents platform with new governance, security, and integration features to help enterprises safely enable citizen developers and AI adoption. The platform now includes centralized access control through identity providers, Secure Compute for private connectivity, Vercel Passport for authentication, enhanced observability, and Enterprise-Managed Authorization for agent integrations.
Vercel now offers Python backends as generally available with frameworks like FastAPI and Django, container support for custom runtimes through Vercel Functions, and introduces Vercel Daemons in public beta for continuously running background workers. These capabilities enable developers to build and deploy full-stack applications on Vercel using their preferred languages and execution patterns.
Python is now generally available on Vercel, allowing you to build and run Python applications with automatic framework detection, full-stack development capabilities, and idiomatic Python SDKs for storage, queues, workflows, and AI integration. Your applications run on Vercel's Fluid compute platform with shared development and deployment workflows for Python backends and JavaScript frontends.
Vercel's AI Gateway monthly index shows open-weight models now account for 71.5% of tokens and 23% of spend, with Chinese-origin models gaining traction through US-based providers. Enterprise AI spending grew 1,180% since December while token prices fell 47%, and teams increasingly diversify across multiple models and labs.
Vercel Daemons is now available in public beta, enabling you to run long-running background processes that pull work from queues, databases, or third-party systems without needing an HTTP server. Daemons run on Fluid compute instances alongside your app, with automatic container management, regional scaling, and built-in observability.
Vercel Token Pass is now in early access for Pro teams, offering $80 monthly credit for $30/month to use with AI models like GLM 5.3 and Kimi K3 through AI Gateway. The service includes Zero Data Retention by default, ensuring prompts and responses are deleted after each request and not used for model training.
Vercel Drives enables agents to persist files independently of their execution environment, allowing them to resume work across different sandboxes and runtimes. Agents can mount the same drive in new environments, share drives across multiple agents with read-only access, or fork drives to explore different approaches in parallel.
Cat Jam, a reasoning model optimized for coding and agentic tasks with low-latency inference, is now available as a free stealth release on Vercel's AI Gateway. It supports function calling, structured outputs, and configurable reasoning efforts, and integrates with popular IDEs and frameworks via the stealth/cat-jam model identifier.
Vercel Connect now supports MCP Events in public beta, enabling applications and agents to subscribe to webhook events from compatible MCP servers. Connect automatically manages subscriptions, verifies webhooks, and delivers authenticated events to your application.
Jev 1.14, a decision model for software classification and routing, is now available on Vercel's AI Gateway. The new version adds support for image inputs and an experimental long-context mode for processing documents and conversation histories, enabling parallel answering of typed questions with probabilities.
Enterprise teams can now run Vercel Functions in their own AWS account while Vercel handles deployments, routing, and static assets. This gives users full control over function execution with their own IAM permissions, network access, and resource policies.
Vercel Drives, persistent storage that mounts as a directory in Vercel Sandboxes, is now generally available on Hobby, Pro, and Enterprise plans. Drives preserve files across sandbox runs and can be forked into independent writable copies, enabling agents to maintain workspace state and share datasets across parallel workers.
Meta's Muse Spark Open, an open-weight reasoning model for coding and agentic workflows, is now available on Vercel's AI Gateway with support for text and image input, a 1M-token context window, and integration across multiple API formats including OpenAI-compatible and Anthropic-compatible APIs.
Vercel Connect now supports Enterprise-Managed Authorization (EMA) in public beta, allowing apps and agents to access supported services on behalf of signed-in users without separate consent prompts. Administrators can manage access through identity providers like Okta, and Connect handles token exchange, caching, and renewal with scoped access control.
Liquid AI's d1-ultra decision model is now available on Vercel's AI Gateway. The multimodal model returns structured answers with probabilities for classification, routing, and scoring across text and images, supporting a 32,768-token context window and billed on input tokens only.
Python is now a first-class language and runtime on Vercel, enabling you to build APIs, full-stack applications, and AI agents with native Python SDKs alongside JavaScript frontends in a unified deployment workflow. Vercel provides automatic framework support for FastAPI, Flask, and Django, plus SDKs for building agents, orchestrating workflows, and running isolated workloads.
Vercel Connect now supports Secure Compute routing, allowing connectors to reach providers with IP allowlists like Salesforce and Snowflake using dedicated static IP addresses instead of shared IPs. Provider requests and token refresh flows now route through selected networks while maintaining the same credential management experience.
Vercel disclosed results from a $1M Sandbox security challenge involving external researchers and Trail of Bits. Key findings include a critical Linux kernel networking defect allowing host memory leaks and escape vectors, plus a cross-tenant snapshot data leak. No customer data theft was confirmed. Vercel has paid $242,000 in bounties and implemented mitigations.
Nemotron 3.5 Lightning, an open-weight 30B parameter reasoning model from NVIDIA, is now available for free on AI Gateway. The model supports long-running agents, chatbots, and RAG systems with a 1M token context window, tool calling, and structured outputs, accessible via multiple APIs and coding agents.
Amazon S3 is now available in the Vercel Marketplace, allowing you to create and connect S3 resources directly from your project dashboard with automatic environment variable setup and short-lived OIDC authentication. The integration also works with v0 for prompt-based resource provisioning and code generation.
Google's Gemini 4 Argon model is now available through Vercel's AI Gateway with support for coding, agentic work, and complex reasoning tasks. The model features a 1M token context window, multimodal input capabilities (text, image, PDF, video), tool calling, and configurable thinking levels for enhanced performance.
Microsoft's MAI-Image-2.6 and MAI-Image-2.6-Flash models are now available on AI Gateway, enabling image generation and editing through a single API key without requiring separate provider accounts. Both models support photorealistic imagery, text rendering, targeted edits, and up to five reference images with output sizes up to 1536×1536.
Fish Audio's Drama 3 text-to-speech model is now available on AI Gateway with preview access and 80% discount for 30 days. The model enables natural-language voice direction for voiceovers, character dialogue, and audio storytelling with support for emotion, pacing, multi-speaker dialogue, and custom delivery tags.
Repository checkout and Git LFS downloads are now faster on Vercel, reducing build preparation time. Average checkout time improved by 20%, with LFS-enabled projects seeing a 54% improvement and saving approximately 13 seconds per deployment.
Meta's Muse Wonder model is now accessible through Vercel's AI Gateway, supporting coding tasks, multi-step agent workflows, and computer use with a 1M-token context window. Users can access the model via a single API key without creating a separate Meta account and use it for text, image, PDF processing, tool calling, and structured outputs.
Vercel CLI now enables agents to discover, check availability, and initiate domain purchases through structured commands, with purchase confirmation remaining under user control via interactive terminal or dashboard approval.
Pro teams now default to a 30-day deployment retention period to balance keeping recent history available while reducing storage costs. You can configure a longer retention period in team settings if needed.
Pro teams will now be charged for Deployment Storage and Functions Storage at $0.10 per GB-month. The default deployment retention window changes to 30 days, with deployments older than 30 days deleted automatically unless you adjust your retention settings beforehand.
Rillet, an AI-native ERP platform, deployed AI agents on Vercel using the eve framework to automate internal workflows and customer requests, tripling their shipping rate within three months. The two-person engineering team now closes 800+ Linear tickets in four months and ships customer changes to production in as little as two hours, powered by standardized agents, Vercel Connect for integrations, and AI Gateway for model access.
Liquid AI's d1 decision model is now available on Vercel's AI Gateway, enabling structured classification and scoring without text generation. The model supports multiple APIs (Decision API, OpenAI-compatible, TypeSafe-compatible) and includes vision capabilities for image classification and inspection.
Microsoft Decision-1, a classification model for answering yes/no questions and categorizing text, is now available through Vercel's AI Gateway. The model supports choice classification, scoring, and boolean decisions with probability scores, accessible via AI SDK, OpenAI-compatible, and TypeSafe APIs using only an AI Gateway API key.
Enterprise teams can now automatically add Git committers to their Vercel team without waiting for owner approval, with options for auto approval or manual approval modes. Committers are added with the Developer role and count toward team seats under the Enterprise agreement.
Vercel now allows you to skip sending client request bodies to Routing Middleware via the skipMiddlewareRequestBody configuration option, reducing middleware invocation costs and improving time to first byte for requests with large bodies.
Vercel Sandbox instances are now ready to run commands and access files immediately upon creation completion. The Sandbox.create() method now waits for snapshot restoration to finish before resolving, eliminating delays on the first command or file operation.
xAI's Grok Imagine Video 1.5 Lite model is now available on AI Gateway, enabling users to generate videos from text prompts and images with native audio support in multiple resolutions and aspect ratios. The model integrates seamlessly with AI Gateway's unified API for model management, cost tracking, and routing configuration.
StepFun's Step 5 Preview model is now available on Vercel's AI Gateway, supporting text and image input with a 1M-token context window optimized for agentic coding, professional knowledge work, and financial analysis. The model can be accessed via the unified AI Gateway API for tracking usage, cost management, and performance optimization.
Microfrontends Routing charges are now waived for requests that the Web Application Firewall denies, challenges, or rate limits. This change applies automatically to all projects using microfrontends.
Glyph Cluster, a reasoning model for coding and long-context analysis, is now available as a stealth model on Vercel's AI Gateway for Pro and Enterprise plan teams with purchased AI Gateway credits at no cost during the stealth period. The model supports function calling, streams responses, and can be accessed via AI SDK, OpenAI-compatible APIs, and coding agents.
Vercel Flags now supports timestamp attributes for entities, allowing you to create time-based targeting rules. Use this feature to run limited-time campaigns, show content between specific dates, or target users based on registration date.
OpenAI's Decisions API is now accessible through Vercel's AI Gateway with an OpenAI-compatible endpoint, enabling decision models to answer typed questions and return probabilities, choices, and scores for routing, triage, and guardrails use cases. Support is available across the OpenAI SDK, AI SDK, HTTP API, and CLI with the latest versions.
Claude Haiku 5.5 is now available through Vercel's AI Gateway, featuring adaptive thinking with effort levels and zero data retention. The fastest Claude model is optimized for high-volume cost-sensitive tasks like summarization, classification, and live customer support.
AI Gateway now supports escalating requests to a fallback model when the primary model's confidence falls below a threshold you set. Configure confidence conditions using providerOptions.gateway.models to automatically route low-confidence responses to secondary models, with support for Choice, Score, and Boolean questions.
Mistral Large 4, an open-weight multimodal model supporting text and image understanding, is now accessible through AI Gateway with a single API key. You can use it via OpenAI-compatible Chat Completions, Responses, or Anthropic Messages APIs, or in coding agents without needing a separate Mistral account.
Nano Banana 2.1, an improved image generation and editing model, is now available on Vercel's AI Gateway. The model offers better product recontextualization, mask- and ink-based editing, and factuality while maintaining Flash-tier latency and cost.
FLUX 3 Image from Black Forest Labs is now accessible through AI Gateway, enabling text-to-image generation and image editing with support for up to ten reference images and multiple resolution tiers from 768×768 to 4K. Users can access it via a single API key without needing a separate Black Forest Labs account.
AI Gateway now supports OpenAI's Ultrafast service tier for GPT-6 Astra, enabling faster output for interactive applications and rapid coding iterations. Ultrafast can be requested via AI SDK, Chat Completions API, or Responses API, with pricing at 6× the standard per-token rate.
Vercel released the AI SDK for Python with experimental support for Jev, a new AI model designed for making narrow classification decisions. Developers can now use the evaluate() API to build classifiers and decision-making tools without training custom models.
Rogo uses Vercel to deploy AI-generated code and manage production with agent swarms, achieving over 73,000 deployments monthly and zero manual incident triage through automated agent-based remediation.
Speed Insights will stop recording First Input Delay (FID) measurements on November 1st and will use Interaction to Next Paint (INP) as the responsiveness metric instead. No action is required on your side and existing FID data remains viewable.
Vercel's AI Gateway now supports Microsoft AI models including MAI-Voice-2.1, MAI-Voice-2.1-Flash for speech generation, and MAI-Transcribe-2 Streaming for live transcription. These models are billed at listed rates with no platform markup, offering users control over data and transparency with Microsoft's zero data retention policy.
Laya, an evaluation and decision model from Convai Innovations, is now available on Vercel's AI Gateway. It evaluates context against yes/no, choice, or scoring questions and returns structured answers with probabilities. The model is free to use through October 31, 2026 via Boundless.
Vercel Agent can now install private dependencies from npm and custom registries using team-shared environment variables. Credentials are securely stored outside the sandbox, and npm, pnpm, and classic Yarn authenticate the same way as in Vercel builds.
Browserbase Search and Fetch tools are now available through AI Gateway, allowing you to add web search and page retrieval capabilities to any model that supports tool calling. These helpers are included in AI SDK 7.0.116 and later.
Edge Requests has been renamed to CDN Requests across the platform, including usage dashboards, invoices, and notifications. Pricing, limits, and usage measurement remain unchanged, and saved queries continue to work.
Vercel Sandbox now integrates with Secure Compute, allowing sandboxes to connect to dedicated networks with static IP addresses and access private AWS VPC resources through VPC peering. Users can attach sandboxes to networks via code or CLI, and existing sandboxes can update their network assignments.
Voyage AI's Rerank 3 and Rerank 3 Lite models are now available through AI Gateway for reordering search results by relevance. Rerank 3 prioritizes accuracy while Rerank 3 Lite optimizes for latency and cost, both supporting up to 32K tokens per query-document pair.
Ling 3.1 Flash, a hybrid reasoning model with 560B parameters optimized for coding and multi-step analysis, is now available on Vercel's AI Gateway and free to use through October 13, 2026. The model offers a 262K-token context window and is designed for agents using tools and workflows with long documents and extended task histories.
Vercel CDN has changed its caching behavior to exclude responses with the Vary: Cookie header, as cookies often contain visitor-specific values that create cache entries with poor reuse rates. Users can identify affected responses via the x-vercel-cache header showing MISS and vary_key_denied:cookie in Runtime Logs, and can restore caching by removing Cookie from the Vary header or using Cache-Control: private if the response depends on cookies.
Users can now submit their own services to the Vercel Connect connectors directory instead of waiting for Vercel to build a connector. The submission process involves describing your service, adding OAuth or API key connection methods, verifying OAuth methods, and sending for review.
The Vercel CLI now supports searching trace spans directly from the terminal via the vercel traces search command, allowing developers to investigate errors, latency, and security issues without accessing the dashboard. The command returns up to 100 spans from the last hour by default and supports filtering by environment, service, span name, status, deployment ID, request ID, trace ID, span ID, and time range.
OpenAI's GPT-6.1 Sol model is now available on Vercel's AI Gateway with improved performance for coding, document analysis, and multi-step workflows. The model offers lower pricing than GPT-6 Astra and cheaper cached input, making it ideal for agents and applications that process complex tasks and reuse long context.
Claude Sonnet 5.5 from Anthropic is now available on Vercel's AI Gateway as anthropic/claude-sonnet-5.5. The new model improves coding task performance with better multi-step reasoning, enhanced document creation, and supports zero data retention across multiple API formats.
Domain name discovery and availability checking are now available without authentication through the Vercel CLI and Domains Registrar API, allowing users to search by keyword or check up to 200 domain names in a single request before signing in.
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.
The Vercel dashboard now includes a Redis database browser that lets you run Redis commands, browse and filter keys, and inspect values directly without needing external tools like redis-cli. It supports both Redis and Upstash for Redis integrations and includes features like transaction support, key grouping by prefix, and metadata inspection.
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.
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.
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.
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.
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.
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.
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.
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.
97 more changes from Vercel. Sign up to read the whole changelog.
Sign up freeGitHub or email — no card needed.