Search headlines, summaries and articles to connect the dots.
The build cache size limit on Vercel's build machines has been raised to 5 GB, enabling projects to retain more installed dependencies and framework files across deployments, thereby reducing install and build times. This change applies automatically to all build machine types without additional cost or configuration.
Parallel Decisions Fast is now available on AI Gateway at no cost until November 23, 2026. It searches the live web to answer questions about companies, products, policies, and other dynamic information, providing probabilities and cited evidence. The model supports boolean, choice, and score question types, with related questions sharing context and evidence in a single request. It can be used to enrich CRM records, verify claims, check eligibility, or route leads. The model name is 'parallel/parallel-decisions-fast', requiring no separate Parallel account. Citations include source URLs, optional titles, and excerpts, applicable to the entire request. Applications can act on high-probability answers and route uncertain ones for review. Requests are tracked in AI Gateway logs and spend budgets.
Vercel Security Review can now scan code changes in GitHub repositories not yet linked to a Vercel project, automatically reviewing commits upon push and offering enhanced analysis when used with linked projects.
Inkling 2 Small, a multimodal reasoning model supporting coding agents, visual understanding, and professional knowledge work, is now available on AI Gateway. It accepts text and image inputs and produces text output, enabling extended coding tasks, tool use for information gathering, document generation, and visual analysis including reading text in images, interpreting charts, and inspecting interfaces. The model can be used via the Vercel CLI with the identifier 'thinkingmachines/inkling-2-small' and integrated into tools like Claude Code, Codex, and Cursor. AI Gateway offers a unified API with features such as usage tracking, cost monitoring, retry configurations, failover, performance optimization, custom reporting, Zero Data Retention, budget controls, and routing rules. Pricing reflects provider rates with no markup or platform fees, including for Bring Your Own Key requests.
Agents interact with software through a funnel similar to humans: Discovery, Selection, Access, and Success. To measure whether agents complete user tasks correctly, end-to-end (E2E) evaluations are essential. These evaluations assess the full sequence of steps an agent takes, ensuring outcomes meet user requirements. Using frameworks like Harbor, developers can design tasks with defined environments, verifiers, and known-good solutions, then run trials across variants to measure success rate, pass@k, pass^k, efficiency, time, and cost. Analyzing traces reveals root causes of failures, enabling targeted improvements. Iterative evaluation helps catch regressions, test changes, and guide product development, turning evaluations into ongoing infrastructure for building better agent-driven products.
Data from custom environments in Speed Insights and Web Analytics is now correctly attributed to the respective custom environment, enabling separate tracking for staging, QA, or canary environments. This update allows users to view and query data via the dashboard, CLI, query builder, and aggregation API without additional configuration, available on Pro and Enterprise plans.
Vercel Sandbox has improved snapshot creation speed by up to 10x, with median time dropping to under 0.4 seconds from 4.4 seconds, and restore speed improving by 50% to 250ms at p50. The enhancements leverage the Vercel Hive Snapshot (VHS) format with more efficient data indexing, enabling parallel read and write operations and faster restoration of both base images and user data. Persistent sandboxes now automatically snapshot upon session end and resume from the latest snapshot by default, using the new format for all new snapshots while existing ones retain the previous format.
Our first deep dive with an AI data company. In roughly a year, Handshake built an AI training business doing nearly $1 billion in gross annualized revenue. What are frontier labs buying? Garrett Lord joins us with the people building reinforcement lea...
Claude Fable 5.2, designed for open-ended technical tasks, is now available on AI Gateway with improved coding, reasoning, and vision capabilities. It operates as an orchestrator or advisor, supports model fallbacks for cybersecurity classifier rejections, requires data retention (no Zero Data Retention), and can be accessed via the AI SDK, APIs, or integrated tools like Claude Code and Cursor. AI Gateway offers unified API access, cost tracking, failover options, and pricing transparency without markup.
In November 2026, decision models accounted for 26% of all AI Gateway requests and 0.53% of total spend, with adoption highest among high-volume teams—70% of those processing over 10 billion tokens monthly used a decision model. Voice model usage rose 2.6 times since July, reaching 11% of paid teams. OpenAI and Anthropic now serve nearly equal shares of paid teams, but Anthropic gained more new teams (2:1), while OpenAI’s share of gateway spend increased by two-thirds since December. Over half of language-model requests went to models less than two months old, reflecting rapid model turnover with a median half-life of six weeks. In October, Anthropic’s Opus 5.5 became the top model by spend, and image and video model usage reached record levels, with OpenAI’s GPT-Image-2.5 Sunburst leading image spend and ByteDance’s Seedance 2.5 leading video spend.
Vercel introduces json-render, enabling Chat SDK agents to generate and stream interactive UI components as JSON specs, which are converted into platform-native cards (e.g., Block Kit on Slack, Adaptive Cards on Teams). The system uses a typed component catalog covering tables, charts, buttons, and more, eliminating the need for separate tools. It supports streaming updates with real-time edits every 500 ms, validates component specs against schemas, and enforces platform-specific message limits to prevent content degradation.
DeepSeek V4.1 Flash 1017 Ultrafast, offering over 1,000 tokens per second, is now available via Fireworks' accelerated serverless endpoint on Vercel's AI Gateway. The model features a 1M-token context window and is optimized for interactive coding, reasoning, and agentic workflows. It is in public preview with no waitroom or session time limits. Developers can use it by specifying the model name in their code or through tools like Claude Code, Codex, and Cursor after setting up the latest Vercel CLI. AI Gateway provides unified API access, usage tracking, cost management, and performance optimizations without markup or platform fees.
Vercel Schedules is now available in public beta across all plans, enabling users to run tasks on a recurring basis or at a specific time in production, preview, or custom environments. It supports targeting private Vercel Functions, HTTP paths, or Queue topics, with schedules definable in vercel.json or created at runtime. Static schedules use cron expressions and require an experimental trigger to make functions private, while runtime schedules dispatch to Queue topics. Schedules replace Cron Jobs, with billing starting at $5 per 1M runs and $10 per 1M creations on Pro and Enterprise plans, and Hobby plan includes 500 schedule creations and 5,000 runs monthly.
Google's Gemini Omni 1.2 Flash is now accessible via AI Gateway, enabling users to generate 3–15 second videos from text prompts using a single API key without needing a separate Google account. The model supports video generation with native audio, editing clips using up to six reference images, extending videos by 3–10 seconds per call (up to 30 seconds total), and refining outputs via previousInteractionId. Output resolutions include 360p, 720p, 1080p, and 4K in 16:9 or 9:16 aspect ratios. Videos can be retrieved via generateText or streamText in the AI SDK as MP4 files. AI Gateway offers unified API access, usage tracking, cost monitoring, retry configurations, failover, performance optimization, custom reporting, Zero Data Retention, budget controls, and routing rules, reflecting provider pricing with no markup or platform fees, including for BYOK requests.
The Workflow SDK's start() function now allows initiating a workflow run and claiming a hook atomically, eliminating the race condition present in the previous getHookByToken()-then-start() pattern. This change ensures idempotency using a token derived from domain-specific identifiers like order or invoice IDs. Duplicate starts fail safely with a HookConflictError, which includes the conflicting run's ID. The claimed hook is available immediately, enabling early payload buffering and ordered delivery even before execution begins. Inside workflows, createHook with the same token binds to the existing hook without conflict or additional steps. Experimental settings like minRetention prevent late duplicates by keeping tokens reserved after run completion.
Vercel Schedules enables applications and agents to create, modify, or cancel one-time and recurring tasks dynamically through code without redeployment. It supports both static schedules defined in configuration files and dynamic schedules managed via SDK, CLI, or API during runtime. The service integrates with Vercel Queues to trigger tasks at specified times, allowing apps to handle work like data cleanup or AI-driven summaries securely and efficiently. Users can test schedules in preview environments before production, and the feature is now available in Public Beta.
Vercel Security Review is now available in public beta for Pro and Enterprise teams, automatically scanning code pushes to connected GitHub repositories for vulnerabilities. Reviews trigger on every push, including direct and force pushes, and findings are reported in a dashboard with details like project, environment, branch, commit, summary, suggested fix, and AI-generated severity. Findings appear as GitHub checks or review comments, and users can fix issues via Vercel Agent or CLI. Teams can set security policies for context, but the tool does not perform runtime or penetration testing. Pricing follows Vercel Agent rates, with free access until November 10, 2026.
Vercel has partnered with Truffle Security to enhance automated detection and revocation of exposed Vercel tokens across public platforms like GitHub, GitLab, npm, and others. A new scanner also checks monthly Common Crawl data, automatically revoking any found tokens. Revoked tokens trigger an email notification explaining the action.
Project Connections allow applications to evaluate flags from another Vercel project within the same team without managing SDK keys, using deployment identity for authentication. Access is managed via the Connections page or CLI, grants read-only access across all environments, and can be revoked without redeployment. Requires @flags-sdk/vercel 1.6.0 or later, or @vercel/flags-core 1.11.0 or later, and Vercel CLI 63.0.0 or later for CLI management.
Mercor reduced batch job processing time from 12 hours to 2–3 hours by using Vercel AI Gateway, which provided increased inference capacity and failover routing across providers. In its first 10 days on the platform, Mercor routed 18 million requests and 63 billion tokens without hitting rate limits. The company also leveraged Vercel Passport and its internal Audiences product to provision secure access for hundreds of business teams and over 2,000 projects in seconds, enabling rapid deployment of client-specific applications while maintaining strict usage controls and automated offboarding.
