Skip to content
AI NEWS JOURNAL
AI, IN PERSPECTIVE

Search AI news

Search headlines, summaries and articles to connect the dots.

Newest first

Standard builds move to usage-based billing for new teams

Starting today, new Pro and Enterprise teams no longer receive a Standard build slot, aligning Standard builds with usage-based billing. On Pro, Standard builds cost $0.014 per build minute, with monthly usage credits applying to build usage. Enterprise rates are based on contract terms. Standard builds remain billable after switching from Elastic to Standard for affected teams.

Vercel Blob now supports TTLs for automatic deletion

Vercel Blob now allows automatic deletion of blobs using a time-to-live (TTL) feature, where blobs are deleted automatically between 1 to 730 days after upload. TTL can be set during write operations like put(), copy(), putImage(), multipart uploads, and presigned URLs. The expiresAt timestamp is included in all write results and head() responses. TTL can be modified or removed later using setTtl() without re-uploading. CLI commands support --ttl-days and --clear-ttl flags. Setting a TTL incurs one Advanced Operation per 60 days, with costs scaling up to 13 for the maximum 730-day TTL. Deletion and clearing TTL are free. Usage can be tracked via the Observability tab.

Decision-1.1 now available on AI Gateway

Decision-1.1, an improved version of Microsoft's decision model, is now available on AI Gateway with enhanced accuracy, better calibration, and faster performance. It provides structured outputs—such as Boolean probabilities, choice selections with confidence scores, and numerical ratings—for tasks like routing support requests, selecting models, workflow steps, or grading AI responses. Multiple questions can be processed in a single request, and the model maintains consistent probability tracking to enable threshold-based actions. It uses the same request format as Decision-1 but requires updating the model ID to 'microsoft/decision-1.1'. Accessible via AI SDK, OpenAI-compatible Decisions API, or AI CLI, it supports logging, budget tracking, and fallback mechanisms. Documentation and examples are available for integration.

Hy4 Flash now available on AI Gateway for 50% off

Tencent's Hy4 Flash model is now available on AI Gateway with a 50% discount on input, cached input, and output tokens until November 29, 2026. It offers the full feature set of the Hy4 family—reasoning with preserved thinking across turns, tool calling, structured outputs, prompt caching, image input, and a 1M-token context window—at approximately one-tenth the cost per token. The model can be used with the identifier 'tencent/hy4-flash' in applications and coding agents via Vercel's CLI setup. AI Gateway provides unified API access, usage tracking, cost management, and performance optimizations without markup or platform fees. Additional resources include reference architectures, agent stacks, web application guides, backend options, and a prompt library.

Introducing eve 1.0

Vercel announces the general availability of eve 1.0, an open-source framework for building production-ready agents. The release includes performance improvements, expanded integrations, enhanced observability via OpenTelemetry, and new features like multi-tenant support, persistent memory, multiplayer sessions, and lower workflow costs. eve enables developers to build agents with customizable workflows, native UI integrations with frameworks like Next.js, and secure, scalable deployments on Vercel. Early adopters report significant gains in development speed, reduced codebases, and lower AI costs.

Native lint and typecheck Deployment Checks are being deprecated

Vercel is deprecating native lint and typecheck Deployment Checks, which will no longer be available for new projects. Existing checks will continue until November 30, 2026. Users are advised to migrate these tasks to Vercel CI or their own CI workflows. Affected checks can be found in the Build and Deployment settings with Vercel as the provider. Instructions include using a coding agent prompt to set up Vercel CI and configuring tasks via pull requests. Running these checks in the build command is an alternative but may increase build time and cause deployment failures on errors.

Pull-request-only preset now available for preview builds

A new Ignored Build Step preset in Vercel allows skipping preview builds for branches without an open pull request, while maintaining production deployments and previews for branches with open pull requests. Skipped preview deployments are canceled before consuming Build CPU Minutes on GitHub and GitLab projects. Users can enable this feature via Deployments > Configuration by selecting 'Only build previews for pull requests' under the Ignored Build Step behavior menu.

Agents are users, so your software needs evals

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 tests run multiple trials, score outcomes, and help identify failures across steps like searching cafes, checking budgets, and placing orders. Using frameworks like Harbor, teams can define tasks with specific instructions, environments, verifiers, and known-good solutions. Metrics such as success rate, Pass@k, and Pass^k reveal how reliably agents perform, while trace analysis uncovers root causes of failure. The process includes setting a goal based on observability, customer feedback, or roadmap needs; defining measurable metrics; designing task sets covering common and edge cases; running evaluations at scale using tools like Vercel Sandbox and AI Gateway; and analyzing traces to iterate improvements. Automated trace analysis enables scaling, and repeated evaluation supports continuous improvement, regression detection, and product optimization.

Qwen4-Max now available on AI Gateway

Qwen4-Max, the first model in Alibaba's Qwen4 series, is now available on AI Gateway. It features a 1M-token context window, native vision capabilities, and excels in coding, professional tasks, and long-running agent workflows. The model can generate and test 3D scenes in Blender and games in Unity, Unreal Engine, and Godot, while also handling complex document analysis for finance, legal, and healthcare use cases. It produces cited reports, spreadsheets, and slide decks, and supports iterative improvements via a Live Delivery plugin. Compared to previous models, it uses fewer tokens, writes more secure code, and integrates with tools like Claude Code, Codex, and Cursor through Vercel CLI setup. AI Gateway offers unified API access, cost tracking, Zero Data Retention, budget controls, and no markup pricing, including for BYOK requests.

Seedance 2.5 Flash now available on AI Gateway

Seedance 2.5 Flash, a faster and lower-cost variant of Seedance 2.5, is now accessible via AI Gateway. It delivers output comparable to the standard model in human realism, reference-based editing, and prompt adherence. Users can generate videos with synchronized audio from text prompts or references, supporting clips between 4 to 30 seconds at up to 720p and 24 fps in various aspect ratios. The model supports editing or extending existing videos and using images to define start and end frames. Integration is available through AI SDK 7 with example code for text-to-video generation and reference-guided creation using image and video URLs.

Set budgets for projects and products in Spend Management

Spend Management now allows individual project and product budgets, enabling users to track spending and automatically pause production deployments when thresholds are reached. Only team and project budgets support automatic pausing. Users can manage budgets via the Vercel dashboard or CLI, with notifications at 50%, 75%, and 100% of budget limits. The feature is included at no extra cost for Pro and Enterprise teams on Flexible Commitment plans, and is available to organizations in the private beta.

Single-second static deployments now support more assets

Vercel now enables instant deployments of static sites in about one second, supporting CSS, images, fonts, and various other assets without a build step. The feature works automatically for eligible projects up to 100 files and 25 MB, including HTML, Markdown, JSON, XML, SVG, PNG, JPEG, WebP, WOFF, PDF, MP4, and more. Deployments exceeding limits or containing unsupported files still follow the standard build process. The update is available across all Vercel plans.

Daemons can now send traces to Vercel Tracing

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.

Token Pass now includes $150 in tokens for $30/month

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.

Gemini 4 Hydrogen now available on AI Gateway

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 now available on AI Gateway

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.

Workflow SDK 5: built for production

Vercel's Workflow SDK 5 introduces end-to-end encryption for workflow payloads, regional data residency for improved latency and reliability, and significant performance enhancements including fewer queue hops, incremental replay, and WebSocket streaming. The update supports secure, durable workflows across multiple regions, enables zero-configuration encryption on Vercel, and delivers up to 25× faster execution in benchmarks. It also adds features like searchable run attributes, in-flight cancellation, and expanded framework integrations, with a Python SDK now in beta.

WTF are evals? How to test agents and the software they use

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.