{"id":"src_ybwLQLQFrJY-rVJQeGetN","slug":"vercel","name":"Vercel","type":"scrape","url":"https://vercel.com/changelog","orgId":"org_qsyZSlC_PRGFDYIGsMfzp","productId":null,"productSlug":null,"org":{"id":"org_qsyZSlC_PRGFDYIGsMfzp","slug":"vercel","name":"Vercel"},"isPrimary":false,"isHidden":false,"discovery":"curated","metadata":"{\"noFeedFound\":true,\"pageEtag\":\"\\\"xhk408yvi92rs\\\"\",\"pageContentLength\":\"423514\"}","notice":null,"kind":"platform","stars":null,"starsFetchedAt":null,"releaseCount":54,"releasesLast30Days":33,"avgReleasesPerWeek":3.4,"latestVersion":null,"latestDate":"2026-06-23T00:00:00.000Z","changelogUrl":null,"hasChangelogFile":false,"lastFetchedAt":"2026-06-23T01:02:11.262Z","lastPolledAt":"2026-06-25T11:04:53.926Z","trackingSince":"2026-03-18T00:00:00.000Z","releases":[{"id":"rel_cqnsdrPdzsb4XXxDUMpmj","version":null,"type":"feature","title":"Deploy from Claude Design to Vercel","summary":"Deploy from Claude Design to Vercel","titleGenerated":"Vercel announces Claude Design to Vercel deployment integration","titleShort":null,"content":"Deploy from Claude Design to Vercel","publishedAt":"2026-06-23T00:00:00.000Z","fetchedAt":"2026-06-23T01:02:10.946Z","url":"https://vercel.com/changelog#deploy-from-claude-design-to-vercel","media":[],"coverageCount":0},{"id":"rel_yNUn74KGsQqbJOSpgMBnY","version":null,"type":"feature","title":"WebSocket support is now in Public Beta","summary":"WebSocket support is now in Public Beta","titleGenerated":null,"titleShort":null,"content":"WebSocket support is now in Public Beta","publishedAt":"2026-06-22T00:00:00.000Z","fetchedAt":"2026-06-23T01:02:10.946Z","url":"https://vercel.com/changelog#websocket-support-is-now-in-public-beta","media":[],"coverageCount":0},{"id":"rel_jf8HLNhxqNatu7sVZHY2U","version":null,"type":"feature","title":"Vercel CLI now supports signing blob URLs","summary":"Vercel CLI now supports signing blob URLs","titleGenerated":null,"titleShort":null,"content":"Vercel CLI now supports signing blob URLs","publishedAt":"2026-06-22T00:00:00.000Z","fetchedAt":"2026-06-23T01:02:10.946Z","url":"https://vercel.com/changelog#vercel-cli-now-supports-signing-blob-urls","media":[],"coverageCount":0},{"id":"rel_d2jNSjk4PjM4OFqM0asgf","version":null,"type":"feature","title":"Increased limit for projects per Git repo","summary":"Increased limit for projects per Git repo","titleGenerated":null,"titleShort":null,"content":"Increased limit for projects per Git repo","publishedAt":"2026-06-22T00:00:00.000Z","fetchedAt":"2026-06-23T01:02:10.946Z","url":"https://vercel.com/changelog#increased-limit-for-projects-per-git-repo","media":[],"coverageCount":0},{"id":"rel_L1S61jngBfAVr6TyeYpgn","version":null,"type":"feature","title":"Sakana Fugu Ultra now available on AI Gateway","summary":"Sakana Fugu Ultra now available on AI Gateway","titleGenerated":null,"titleShort":null,"content":"Sakana Fugu Ultra now available on AI Gateway","publishedAt":"2026-06-22T00:00:00.000Z","fetchedAt":"2026-06-23T01:02:10.946Z","url":"https://vercel.com/changelog#sakana-fugu-ultra-now-available-on-ai-gateway","media":[],"coverageCount":0},{"id":"rel_ZqeBfDmNFrNKahLKXY5Xs","version":null,"type":"feature","title":"Vercel Passport is now in Public Beta","summary":"Vercel Passport is now available in Public Beta.","titleGenerated":null,"titleShort":null,"content":"Vercel Passport is now available in Public Beta.","publishedAt":"2026-06-17T00:00:00.000Z","fetchedAt":"2026-06-19T01:01:11.599Z","url":"https://vercel.com/changelog#vercel-passport-is-now-in-public-beta","media":[],"coverageCount":0},{"id":"rel_X7XXTDBQLeY3DYaPz8gGe","version":null,"type":"feature","title":"Introducing eve, an open-source agent framework","summary":"Eve is a new open-source agent framework from Vercel.","titleGenerated":null,"titleShort":null,"content":"Eve is a new open-source agent framework from Vercel.","publishedAt":"2026-06-17T00:00:00.000Z","fetchedAt":"2026-06-19T01:01:11.599Z","url":"https://vercel.com/changelog#introducing-eve-an-open-source-agent-framework","media":[],"coverageCount":0},{"id":"rel_AMy5mXbxrtUdGzpax8zRN","version":null,"type":"feature","title":"CLI deployment limits removed","summary":"CLI deployment limits have been removed.","titleGenerated":null,"titleShort":null,"content":"CLI deployment limits have been removed.","publishedAt":"2026-06-17T00:00:00.000Z","fetchedAt":"2026-06-19T01:01:11.599Z","url":"https://vercel.com/changelog#cli-deployment-limits-removed","media":[],"coverageCount":0},{"id":"rel_1_q_pX2IxQqqqVpRvJDPJ","version":null,"type":"feature","title":"Vercel Connect: Secure access to external services for your agents","summary":"Vercel Connect enables secure access to external services for your agents.","titleGenerated":null,"titleShort":null,"content":"Vercel Connect enables secure access to external services for your agents.","publishedAt":"2026-06-17T00:00:00.000Z","fetchedAt":"2026-06-19T01:01:11.599Z","url":"https://vercel.com/changelog#vercel-connect-secure-access-to-external-services-for-your-a","media":[],"coverageCount":0},{"id":"rel_Vl-R2nblx-1UdDhrBePS7","version":null,"type":"feature","title":"GLM 5.2 now available on AI Gateway","summary":"GLM 5.2 is now available on AI Gateway. Built for long-horizon tasks, GLM 5.2 carries project-level engineering context across a single task, runs lon...","titleGenerated":null,"titleShort":null,"content":"GLM 5.2 is now available on AI Gateway. Built for long-horizon tasks, GLM 5.2 carries project-level engineering context across a single task, runs long-running tasks more reliably, and follows engineering standards more consistently. The context window has been upgraded to 1M tokens, up from 200K in GLM 5.1. Available via the AI SDK with model ID `zai/glm-5.2`. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations.","publishedAt":"2026-06-16T00:00:00.000Z","fetchedAt":"2026-06-17T01:01:27.409Z","url":"https://vercel.com/changelog#glm-5-2-now-available-on-ai-gateway","media":[],"coverageCount":0},{"id":"rel_PIdr5UCiD5eS4LPcQeRzT","version":null,"type":"feature","title":"Workflow SDK now supports TanStack Start","summary":"Workflow SDK now supports TanStack Start applications on Vercel. TanStack Start is built on Vite and Nitro, so the existing `workflow/vite` plugin wor...","titleGenerated":null,"titleShort":null,"content":"Workflow SDK now supports TanStack Start applications on Vercel. TanStack Start is built on Vite and Nitro, so the existing `workflow/vite` plugin works directly. Add it to `vite.config.ts` alongside `tanstackStart()`.","publishedAt":"2026-06-16T00:00:00.000Z","fetchedAt":"2026-06-17T01:01:27.409Z","url":"https://vercel.com/changelog#workflow-sdk-now-supports-tanstack-start","media":[],"coverageCount":0},{"id":"rel_OIy_I9ivdVXADnn7GqKew","version":null,"type":"feature","title":"Vercel Sandbox can now run for up to 24 hours","summary":"Vercel Sandboxes can run uninterrupted sessions for up to 24 hours (up from 5 hours). This unlocks workloads requiring longer runtimes, such as large-...","titleGenerated":null,"titleShort":null,"content":"Vercel Sandboxes can run uninterrupted sessions for up to 24 hours (up from 5 hours). This unlocks workloads requiring longer runtimes, such as large-scale data processing, end-to-end testing pipelines, and long-lived agentic workflows. The 24 hour max duration is available on all Pro and Enterprise plans. Can be paired with persistent sandboxes to maintain durable state across extended runs.","publishedAt":"2026-06-16T00:00:00.000Z","fetchedAt":"2026-06-17T01:01:27.409Z","url":"https://vercel.com/changelog#vercel-sandbox-can-now-run-for-up-to-24-hours","media":[],"coverageCount":0},{"id":"rel_AomhBGtmTv41iiOnyQTxU","version":null,"type":"feature","title":"Workflow SDK now supports inflight cancellation","summary":"The Workflow SDK 5 beta now supports the standard `AbortController` and `AbortSignal` APIs across workflow and step boundaries. Create a controller in...","titleGenerated":null,"titleShort":null,"content":"The Workflow SDK 5 beta now supports the standard `AbortController` and `AbortSignal` APIs across workflow and step boundaries. Create a controller inside a workflow, pass its signal into steps, and cancel in-flight operations using the same API `fetch` already uses. The signal stays durable across suspensions and deterministic replay. Cancellation is cooperative; steps have to inspect the signal or pass it to an API that supports `AbortSignal`. Use cases include stopping slow steps on timeout, cancelling remaining requests after first success, threading signals through pipelines, or cancelling parallel work on external condition changes.","publishedAt":"2026-06-16T00:00:00.000Z","fetchedAt":"2026-06-17T01:01:27.409Z","url":"https://vercel.com/changelog#workflow-sdk-now-supports-inflight-cancellation","media":[],"coverageCount":0},{"id":"rel_CGZeLjNzOHrp6WLDbjOxk","version":null,"type":"feature","title":"Increased Blob store limit for Hobby users","summary":"Hobby users can now create up to 100 Blob stores, up from 5, allowing teams to organize data by project, environment, or region as applications grow. Storage, operations, and transfer limits remain unchanged.","titleGenerated":"Vercel increases Blob store limit for Hobby users to 100","titleShort":"Hobby users: 100 Blob stores now available","content":"Hobby users can now create up to 100 Blob stores, up from 5. This gives teams more flexibility to organize data by project, environment, or region as applications grow. Storage, operations, and transfer limits still apply.\n\nLearn more in the [Blob documentation](https://vercel.com/docs/vercel-blob/usage-and-pricing).","publishedAt":"2026-06-15T00:00:00.000Z","fetchedAt":"2026-06-15T01:01:01.740Z","url":"https://vercel.com/changelog#increased-blob-store-limit-for-hobby-users","media":[],"coverageCount":0},{"id":"rel_k_P5niuFY9yzwbJJRjOc0","version":null,"type":"feature","title":"Workflow SDK now runs natively in Nitro v3","summary":"Workflow SDK's native Nitro v3 integration is now in beta, with steps running inside the same bundled runtime as the rest of your app. Steps can now use Nitro's server-side APIs like useStorage() directly, and the Nitro dev server serves a workflow web UI at /_workflow for inspecting, monitoring, and debugging runs. Workflow routes are bundled by Nitro with dependency tracing and tree-shaking for faster builds and smaller bundles.","titleGenerated":"Vercel Workflow SDK now runs natively in Nitro v3","titleShort":"Workflow SDK integrates natively with Nitro v3; dev server UI added","content":"Workflow SDK's native Nitro v3 integration is now in beta. Steps run inside the same bundled runtime as the rest of your app, instead of a separate bundle. Nitro's `useStorage()` and other server-side APIs work directly inside `\"use step\"` functions.\n\nThe Nitro dev server also serves the workflow web UI at `/_workflow`. Open it in your browser to inspect, monitor, and debug workflow runs.\n\nWorkflow routes are now bundled by Nitro as part of the app build. Dependencies are traced, and unused code is tree-shaken, so the output includes only what runs, with faster builds and smaller bundles.","publishedAt":"2026-06-13T00:00:00.000Z","fetchedAt":"2026-06-13T01:00:54.029Z","url":"https://vercel.com/changelog#workflow-sdk-now-runs-natively-in-nitro-v3","media":[],"coverageCount":0},{"id":"rel_wU9-v81RogoUVOmxoL45b","version":null,"type":"feature","title":"Claude Fable 5 access suspended on AI Gateway","summary":"In compliance with the US Government's directive, access to Claude Fable 5 is now suspended on AI Gateway for all users. We do not know if or when acc...","titleGenerated":null,"titleShort":null,"content":"In compliance with the US Government's directive, access to Claude Fable 5 is now suspended on AI Gateway for all users. We do not know if or when access to the model will be restored.\n\nYou can still access and use other Anthropic models through AI Gateway.","publishedAt":"2026-06-12T00:00:00.000Z","fetchedAt":"2026-06-15T01:01:01.740Z","url":"https://vercel.com/changelog#claude-fable-5-access-suspended-on-ai-gateway","media":[],"coverageCount":0},{"id":"rel_ybUCJsOn9n5l6Lc9dvgWM","version":null,"type":"feature","title":"Kimi K2.7 Code now available on AI Gateway","summary":"Kimi K2.7 Code from Moonshot AI is now available on AI Gateway. K2.7 Code is a coding model built for long-horizon programming tasks, generalizing acr...","titleGenerated":null,"titleShort":null,"content":"Kimi K2.7 Code from Moonshot AI is now available on AI Gateway. K2.7 Code is a coding model built for long-horizon programming tasks, generalizing across scenarios including frontend development, DevOps, and performance optimization. The model has a native multimodal architecture that supports text and vision input, and always runs in thinking mode.\n\nTo use K2.7 Code, set model to `moonshotai/kimi-k2.7-code` in the AI SDK. The model supports both text and image inputs for multimodal capabilities.","publishedAt":"2026-06-12T00:00:00.000Z","fetchedAt":"2026-06-13T01:00:54.029Z","url":"https://vercel.com/changelog#kimi-k2-7-code-now-available-on-ai-gateway","media":[],"coverageCount":0},{"id":"rel_qi3tcD8qBnrrdL0XEBk9v","version":null,"type":"feature","title":"Program Claude Code, Codex, Pi and other agent harnesses with AI SDK","summary":"AI SDK 7 introduces `HarnessAgent`, a single API for running established agent harnesses, including Claude Code, Codex, and Pi. Write the agent once a...","titleGenerated":null,"titleShort":null,"content":"AI SDK 7 introduces `HarnessAgent`, a single API for running established agent harnesses, including Claude Code, Codex, and Pi. Write the agent once and use the best harness available. Harnesses manage components including skills, sandboxes, sessions, permission flows, compaction, runtime configuration, and sub-agents. The AI SDK normalizes access to these capabilities through a unified harness abstraction. Initial harness adapters for this experimental release include Claude Code, Codex, and Pi, with more coming soon.","publishedAt":"2026-06-12T00:00:00.000Z","fetchedAt":"2026-06-13T01:00:54.029Z","url":"https://vercel.com/changelog#program-claude-code-codex-pi-and-other-agent-harnesses-with-","media":[],"coverageCount":0},{"id":"rel_ryIImivIymOjbuRR6t_Tb","version":null,"type":"feature","title":"Budgets for API keys on AI Gateway","summary":"Set spend caps on API keys for AI Gateway to control AI costs. Once a budget limit is exceeded, AI Gateway rejects further requests on that key until ...","titleGenerated":null,"titleShort":null,"content":"Set spend caps on API keys for AI Gateway to control AI costs. Once a budget limit is exceeded, AI Gateway rejects further requests on that key until the budget resets or is raised. The cap applies to all AI Gateway providers and models running through the key.\n\nCreate budgeted API keys in the Vercel Dashboard via the AI Gateway API Keys page, or programmatically through the Vercel CLI:\n\n```\nvercel ai-gateway api-keys create --name <NAME> --budget <DOLLARS> --refresh-period <PERIOD>\n```\n\nRefresh periods can be `daily`, `weekly`, `monthly`, or `none`. Each period resets at the start of its window in UTC.","publishedAt":"2026-06-09T00:00:00.000Z","fetchedAt":"2026-06-10T01:02:13.022Z","url":"https://vercel.com/changelog#budgets-for-api-keys-on-ai-gateway","media":[{"type":"image","url":"https://assets.vercel.com/image/upload/contentful/image/e5382hct74si/3U04IHbBLkYtm0R5UEgbaS/31c8b86982886a713b60b7005526df1e/CleanShot_2026-06-05_at_18.03.28_2x.png","alt":"AI Gateway API key creation with spend quota","r2Key":"releases/62f712ee38ba0090c29dc7d3006b8be41de92976217cee1a51a5787ee471bccb.png","r2Url":"https://media.releases.sh/releases/62f712ee38ba0090c29dc7d3006b8be41de92976217cee1a51a5787ee471bccb.png"},{"type":"image","url":"https://assets.vercel.com/image/upload/contentful/image/e5382hct74si/vlWZLTOqpjM9fjsZtbjiR/d03c7fd99aa830a669dfe6ef2f716947/CleanShot_2026-06-05_at_18.02.03_2x.png","alt":"API key editing interface","r2Key":"releases/a95d423e0f19b6249d92d2a52fb312381a7fb9675dc3a0fbd5015508f8055e95.png","r2Url":"https://media.releases.sh/releases/a95d423e0f19b6249d92d2a52fb312381a7fb9675dc3a0fbd5015508f8055e95.png"}],"coverageCount":0},{"id":"rel_r9ejeZ4TeWa9FwClr-dnM","version":null,"type":"feature","title":"Claude Fable 5 now available on AI Gateway","summary":"Claude Fable 5 from Anthropic is now available on AI Gateway. A Mythos-class model, Fable 5 is a notable step up over prior Claude models on long-runn...","titleGenerated":null,"titleShort":null,"content":"Claude Fable 5 from Anthropic is now available on AI Gateway. A Mythos-class model, Fable 5 is a notable step up over prior Claude models on long-running, ambiguous, multi-step tasks. The model sustains productive output across multi-day runs and dependably dispatches parallel sub-agents. Code review, bug-finding, and repository investigation are stronger, and first-shot correctness on complex problems is noticeably higher.\n\nFable 5 ships with blocking classifiers that refuse offensive cybersecurity, biology, and summarized-thinking extraction. Anthropic does not support Zero Data Retention; prompts and completions are retained for 30 days and are not used to train Claude.\n\nTo use Fable 5, set the model to `anthropic/claude-fable-5` in the AI SDK.","publishedAt":"2026-06-09T00:00:00.000Z","fetchedAt":"2026-06-10T01:02:13.022Z","url":"https://vercel.com/changelog#claude-fable-5-now-available-on-ai-gateway","media":[],"coverageCount":0}],"pagination":{"nextCursor":"2026-06-09T00:00:00.000Z|2026-06-10T01:02:13.022Z|rel_r9ejeZ4TeWa9FwClr-dnM","limit":20},"summaries":{"rolling":{"windowDays":90,"summary":"Vercel's platform moved toward tighter control and flexibility across execution, caching, and feature management. The company graduated Vercel Flags to general availability, adding framework-native flag definitions for Next.js and SvelteKit while supporting the OpenFeature standard for other stacks. The AI Gateway expanded significantly—Claude Opus 4.7 arrived with task budgets and improved agentic execution, and Seedance 2.0 brought multimodal video generation (text-to-video, image-to-video, video editing) without requiring separate provider accounts. On the infrastructure side, new projects now respect upstream cache-control headers by default, Sandbox persistence moved to beta for automatic filesystem snapshots, and elastic build machines entered beta to right-size compute per project.","releaseCount":14,"generatedAt":"2026-04-16T15:07:02.626Z"},"monthly":[{"year":2026,"month":3,"summary":"Vercel shipped infrastructure improvements and security responses across caching, build machines, and sandbox persistence. The Axios supply chain attack on March 31st prompted immediate remediation—blocking malicious versions and C&C access from build infrastructure—while new projects defaulted to respecting upstream cache headers starting April 6th. The SDK layer expanded with Sandbox automatic persistence (saving filesystem state on stop and restoring on resume), Chat SDK concurrent message handling and Slack scheduling, file permission control in sandbox writes, and Activity Log integration into the CLI, while elastic build machine assignment moved to beta to right-size compute per project.","releaseCount":11,"generatedAt":"2026-04-16T15:07:05.545Z"}]}}