AI BriefingVercel Blog news
The latest AI and developer news from Vercel Blog, with short summaries.
Visit website →NEWVercel Token Pass increases monthly token allowance to $150
The credit applies to featured open-weight models on AI Gateway, including Kimi K3, Kimi K3.1 Pro, GLM 5.3, GLM 5.3 Flash, and DeepSeek V4.1 Flash.
NEWVercel Daemons Support OpenTelemetry Traces via Vercel Tracing
Upgrading @vercel/otel to 2.3.0 enables automatic trace export for Node.js daemons using a provided Unix socket.
NEWVercel Security Review now scans unlinked GitHub repositories
The feature automatically triggers vulnerability checks on code pushes in repositories not yet linked to a Vercel project.
NEWVercel increases build cache size limit to 5 GB on all build machines
Vercel has increased the build cache size limit to 5 GB on all build machines, allowing projects to save more dependencies and framework files for reuse.
NEWVercel Sandbox initialization up to 4x faster with regional caching
Regional caching of image data reduces startup latency for sandboxes outside the Washington, D.C. region, with measured improvements up to 75% in Paris.
NEWParallel Decisions Fast available on AI Gateway free through November 23, 2026
The model searches the live web to answer questions about companies and policies, returning probabilities and cited evidence for automated decision-making.
NEWVercel Sandbox Adds Support for Managed npm Credentials and Custom Registries
The feature keeps tokens outside the sandbox while allowing coding agents to install dependencies from private registries like GitHub Packages and JFrog Artifactory.
NEWToken Pass adds Kimi K3.1 Pro with 1M context window
The subscription provides $80 in monthly credit for coding agents with zero data retention.
NEWVercel Adds Python 3.15 Managed Image for Sandbox
The default universal image will switch from Python 3.14 to 3.15 on December 16, 2026.
NEWVercel CLI enables agents to update project compute settings non-interactively
The update applies all settings supported by vercel project update without a confirmation prompt, requiring a Pro or Enterprise plan.
NEWVercel Workflow SDK 5 Delivers 1.6x to 25x Latency Improvements and End-to-End Encryption
The update introduces AES-256-GCM encryption, regional deployment for reduced cross-region latency, and a rewritten engine that reduces step-to-step overhead from 618 ms to 109 ms.
NEWInkling 2 Small from Thinking Machines Available on AI Gateway
The model supports text and image inputs for coding, visual understanding, and professional knowledge work.
NEWVercel AI Gateway adds Google Gemini 4 Hydrogen with improved agentic coding and tool use
The model succeeds Gemini 3.8 Flash, handling longer engineering tasks and producing better-researched documents in fewer agent steps.
NEWVercel demonstrates how to build end-to-end agent evals using Harbor and AI Gateway
The guide uses a coffee-ordering API example to show how to define tasks, run trials in Vercel Sandboxes, and analyze traces to fix agent failures.
Google Gemini Decision 1 Available on AI Gateway for Multimodal Routing
The multimodal model processes text, images, audio, video, and PDFs to return Boolean probabilities, choices, and scores for policy checks and ranking.
MiniMax H3 Image and Highspeed models added to AI Gateway
The new models support custom dimensions and aspect ratios, with the Highspeed variant offering faster generation using the same API key.
Gemini 4 Carbon available on AI Gateway with 50% discount through November 2026
The model features a 1M-token context window for complex software engineering and cybersecurity tasks, with a 50% price reduction ending November 30, 2026.
Speed Insights and Web Analytics now support custom environments
Data from custom deployments is now attributed to the specific environment rather than Preview, enabling separate tracking for staging, QA, or canary setups.
Token Pass adds GLM 5.3 Flash with 1M-token context
The $30/month subscription now includes Z.ai's native multimodal coding model, which features a 1M-token context window.
Vercel Sandbox snapshot creation speeds up 10x to under 0.4 seconds
Snapshot restore speed also improved by 50% to 250ms at p50 through a more efficient VHS format that enables parallel operations.