Search headlines, summaries and articles to connect the dots.
Vercel daemons can now send OpenTelemetry traces to Vercel Tracing via a Unix socket, with automatic export enabled in @vercel/otel version 2.3.0 or later. Developers can initialize tracing using registerOTel and search daemon spans through the Vercel CLI with service name filtering.
Vercel Token Pass now offers $150 in monthly tokens (up from $80) for $30 per team per month, applicable to featured open-weight models via AI Gateway such as Kimi K3, Kimi K3.1 Pro, GLM 5.3, GLM 5.3 Flash, and DeepSeek V4.1 Flash. Credits reset each billing cycle with no rollover; once exhausted, requests using standard keys fall back to the team's AI Gateway balance, while Token Pass-scoped keys cease without overage charges. Available as an Early Access add-on for Pro teams with limited availability and a waitlist. Connect via the Vercel CLI command 'vercel token-pass' or use a Token Pass API key if supported. Subscribe through the AI Gateway dashboard.
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.
Token Pass, Vercel's Early Access subscription for Pro teams, now includes Kimi K3.1 Pro, Moonshot AI's most advanced model for coding and agentic workflows featuring vision, tool use, and a 1M context window. For $30 per team per month, users receive $80 in monthly credit for coding agents via AI Gateway, with zero data retention on requests. The subscription also offers access to other models like GLM 5.3, GLM 5.3 Flash, and DeepSeek V4.1 Flash, with additional models forthcoming.
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 Sandbox startup times have improved significantly outside the Washington, D.C. (iad1) region by leveraging regional caching for reused image data, reducing initialization time by up to 75% in Paris and from 3.5s to 1.05s in Seoul, with smaller gains in regions closer to the origin due to shorter distances.
Gemini 4 Hydrogen, succeeding Gemini 3.8 Flash, is now available on Vercel's AI Gateway, offering improved performance in agentic coding, knowledge work, and tool use with enhanced reliability in following instructions, formatting, and task boundaries. It supports longer engineering tasks, better-researched documents, and stronger grounding to reduce unsupported claims. The model can be used via the 'google/gemini-4-hydrogen' identifier in supported tools after setting up the Vercel CLI. AI Gateway provides a unified API for model access, usage tracking, cost management, and advanced configurations like routing rules and budgets, with no markup or platform fees.
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.
Google's Gemini Decision 1, a multimodal decision model supporting text, images, audio, video, and PDFs, is now accessible via AI Gateway. It provides Boolean probabilities, choices, and scores for tasks like request routing, policy checks, tool filtering, and result ranking without generating output tokens. Supported through the AI SDK, TypeSafe-compatible API, and Decisions API, with PDF, audio, and video inputs available in AI SDK 7. Decision calls are logged and counted toward budgets alongside other model requests.
Gemini 4 Carbon, a model designed for complex software engineering, agentic work, and cybersecurity defense, is now available on Vercel's AI Gateway with a 50% discount through November 30, 2026. It features a 1M-token context window, enhanced capabilities in coding, full-stack development, scientific reasoning, and vulnerability detection, along with improved multi-step planning and collaboration under ambiguous requirements. The model can be accessed using the identifier 'google/gemini-4-carbon' in supported tools after setting up the Vercel CLI. AI Gateway offers unified API access, usage tracking, cost management, and performance optimizations, with no markup or platform fees, including for BYOK requests.
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...
Vercel has increased build disk space from 32 GB to 64 GB on Basic and Standard machines, aligning with Enhanced and Turbo tiers, providing more room for project packages and build-generated files without requiring configuration changes or additional costs.
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.
Token Pass, a $30/month subscription on Pro teams, now includes GLM 5.3 Flash alongside other models like Kimi K3, GLM 5.3, and DeepSeek V4.1 Flash, offering $80 in monthly credit via AI Gateway. GLM 5.3 Flash is Z.ai's native multimodal coding model with a 1M-token context window and features Zero Data Retention by default. It can be added through the team's AI Gateway dashboard or via documentation.
Vercel Container Registry now allows compressed image layers up to 2 GB each, while maintaining a total image size limit of 15 GB. It supports standard Docker workflows like docker push, docker pull, and docker tag, automatically creating repositories on push. Images can be made public or shared with up to 100 teams via the dashboard or CLI. The Vercel CLI v58.3.0 or later enables management of repositories, images, and tags, and GitHub Actions integration uses GitHub OIDC for secure CI logging without long-lived credentials. Failed background optimizations show error statuses in the dashboard, with retry options upon re-push.
The Vercel Workflow SDK has updated to send event writes and stream writes over WebSocket by default starting with version 5.2.0, eliminating the need for one HTTP request per write. This change improves performance, reduces costs, and enables faster AI token streaming—demonstrated by a 4.2× speed improvement in benchmarks. No code changes are required beyond upgrading to workflow@5.2.0 or later. Existing streaming code remains compatible, and in-flight workflows continue on their original deployment. Users should consult the upgrade guide if migrating from version 4.x.
