Is Lovable Down?

Quickest ways to check the current status of lovable.dev plus recent known issues and working alternatives if it's out.

Last editorial review: 2026-10-15

How to check right now

Step 1 -- Load the site
Open lovable.dev→

The simplest check. If it loads and you can log in, the tool is up for you.

Step 2 -- Crowdsourced reports
DownDetector: Lovable→

User-reported outages aggregated across regions. Good signal for partial or regional outages.

Step 3 -- Live social
Search X for “Lovabledown” →

Live tweets from other users. Fastest signal for a fresh outage -- often beats status pages by 10-20 minutes.

Step 4 -- Official status page
Find Lovable's status page →

Most vendors publish a status page at status.[domain] or on Statuspage.io. Google-search to find the current URL.

Known issues we've tracked

OCTOBER 12-15 CHANGELOG -- GROWTH TOOLS AND ADS, SIGN IN WITH LOVABLE, PROJECT RESTORE, ARGON AND GPT-6.1 SOL IN APPS (vendor changelog): **(1) Growth tools (10/14):** 'Lovable now helps you find customers, from the same chat where you build.' Set a goal and it builds a plan from 'your app, your audience, and your traffic' -- what to fix first, and it 'says so when ads are premature'; recommendations for search and AI-assistant discoverability, landing-page offers, community/directory/creator outreach and Google Business Profiles; **ads launched from Lovable** on Google, YouTube, Facebook and Instagram (create or connect a Google Ads account, use your Facebook account; 'You decide the ad budget and approve when spending can start'); launch videos, demos, ad images and copy; results in a redesigned Analytics view. 'Lovable adds no extra fees for using Growth tools'; normal chat costs apply and Google/Meta bill ad spend directly. **(2) Sign in with Lovable (10/14-10/15):** apps on Lovable Cloud can offer it (default on new login pages from 10/15, next to email/password and Google), and any website can add it with a script tag or standard OpenID Connect; workspaces can register OAuth clients (sensitive scopes need Business/Enterprise plus Lovable verification); sign-ins cost no credits. **(3) Recovery (10/14):** deleted projects restorable for 60 days with code, history and chat; deleted workspaces restorable for 60 days on Free, Pro and Business. **(4) Run-credit investigation (10/14):** ask Lovable what drives run-credit usage and it traces jobs, functions, storage and AI calls to code and proposes fixes. **(5) Models for app AI features:** Gemini 4 Argon (google/gemini-4-argon, 10/13, 'comes at a premium price') and GPT-6.1 Sol (openai/gpt-6.1-sol, 10/15). **(6) Other:** WebMCP browser-agent tools in apps (10/13); 'always allow all tools' per chat connector (10/13); Lovable Cloud now refuses CREATE EXTENSION outside a fixed list (pg_cron, pg_net, vector, postgis...) (10/13); in-app image editing in the Files tab, free-allowance coverage view, Loops connector (10/12); Bing Webmaster Tools connector (10/14); Enterprise audit-log export to S3, GCS, Azure Blob, Splunk or Azure Log Analytics hourly or every 3 hours, past the 13 weeks Lovable keeps (10/15); Lovable MCP in Claude via enterprise SSO (Okta) on Business/Enterprise (10/15).
2026-10-15•Lovable changelog (lovable.dev/changelog, entries dated Oct 12, Oct 13, Oct 14 and Oct 15, 2026) -- fetched 2026-10-15 via curl
CHANGELOG 10/06-10/09 -- SPEND CONTROLS, INVITE-ONLY PUBLISHING, DRIZZLE MIGRATIONS, NINE CONNECTORS (vendor-primary): **10/07 -- usage limits and alerts:** admins and owners on paid plans can set credit thresholds for the workspace, a project or a member (and, on Business/Enterprise, a group or access token) that trigger an alert or a **block that stops building or pauses Lovable Cloud, AI features and metered connector requests in deployed apps**; members can request increases. Also: high-load warnings for Cloud databases with a Resolve flow and credit-priced resize offers, **Cloud schema changes now recorded as Drizzle migration files under drizzle/migrations/** (backward-incompatible changes refused unless allowed), faster inline text edits. **10/08 -- Invite-only publishing on Free and Pro** (workspace members or emailed outsiders, login required; workspace/group publishing still needs Business or Enterprise); app + chat connectors for **Zendesk, Neon, MotherDuck, Oracle Autonomous AI Database, IBM Db2, Qlik Cloud, Omni, Metabase and GoodData**; a **Loom** chat connector; and the three pre-build 'design directions' were removed. **10/09 -- Enterprise publishing domains** (projects publish at your-app.yourdomain.com; old lovable.app addresses keep working), chats can reference or send tasks to other chats, a Generate button for shared secrets, .si domains, and **out-of-credits forecasts on Free, Pro and Business**; Enterprise credit balances shown as numbers. **10/06 --** Klaviyo connector, Excalidraw+ chat connector, Databricks user OAuth, a redesigned model list. **Model retirements inside Lovable's app AI features:** Gemini 3.6 Flash marked deprecated and stops working there on 2026-11-19, Gemini 3.7 Flash on 2027-01-28 (switch to Gemini 3.8 Flash). Those are Lovable's dates for its own built-in AI connector -- Google's Gemini API deprecations page lists no shutdown for gemini-3.6-flash and says gemini-3.7-flash 'is not shutting down' and routes to gemini-3.8-flash.
2026-10-09•Lovable changelog (lovable.dev/changelog, entries Oct 6-9, 2026); Google Gemini API deprecations page (ai.google.dev/gemini-api/docs/deprecations) for the Google-side status -- fetched 2026-10-12 (changelog via curl with browser UA, Google page via WebFetch)
LYRIA 3 MUSIC GENERATION IN LOVABLE APPS, BEEHIIV AND RAMP CONNECTORS, GIT-PUSH RESTORE, AND A GITHUB SECRET-SCANNING DETECTOR FOR LOVABLE KEYS (2026-10-05, vendor changelog + GitHub changelog): **Lyria 3 in app AI features (10/05):** 'Your app's AI features can now generate music with two Google models, from a text prompt or an image, with vocals or as an instrumental: **Lyria 3 Clip Preview**, for clips of about 30 seconds; **Lyria 3 Pro Preview**, for full tracks up to 184 seconds.' You can name the model or let Lovable pick; 'Generating music uses credits, charged per finished track and only when a generation succeeds' -- no per-track credit figure is published. **Connectors (10/05):** **beehiiv** (add subscribers, list posts, save drafts -- newsletter signup forms and launch waitlists) and **Ramp** (read transactions, cards, funds and limits, users and business info -- spend dashboards), added from Connectors or by asking Lovable. **Restore after a Git push (10/05):** when a push to the synced repository replaces work Lovable made, Lovable 'saves a backup first and shows a notice in the editor and in Project settings -> Git', where the project owner restores it or keeps the repository's version; restored work syncs back, or to a `lovable-sync` branch when the repository has newer commits -- a fix for the long-standing complaint about two-way sync clobbering edits. **GitHub (10/05):** secret scanning added a `lovable_api_key` detector and Lovable Labs joined GitHub's partner program, so a Lovable API key committed to a public repository is forwarded to Lovable for revocation; detectors for Supabase OAuth and scoped personal access tokens shipped in the same entry, which matters because Lovable Cloud is built on Supabase. The 10/02 entry (a workspace announcement banner for Business and Enterprise admins) is admin UI and not recorded separately. Plan prices remain unverified -- lovable.dev/pricing cards are still client-rendered.
2026-10-05•Lovable changelog (lovable.dev/changelog, entry dated 'Oct 5, 2026') -- fetched 2026-10-06 via curl with browser UA; GitHub Changelog (github.blog/changelog/2026-10-05-secret-scanning-adds-detectors-for-lovable-supabase-and-more/, 'October 5, 2026') -- fetched 2026-10-06
GPT LIVE VOICE IN LOVABLE APPS, EU INFERENCE FOR ENTERPRISE, IP-ALLOWLISTED API KEYS, DATABASE PASSWORD ROTATION AND A MUSE BY META CONNECTOR -- FIVE CHANGELOG ENTRIES IN THREE DAYS (2026-09-29 to 2026-10-01, vendor changelog): **10/01 -- GPT Live:** 'You can now add live voice conversations to your app's AI features with GPT Live. People talk with your app, interrupt it, and have it act on what they say' -- describe the conversation (a voice tutor, a spoken assistant) and Lovable wires it up; **'Live voice works in apps that use TanStack Start and uses credits'** (no per-minute figure given; OpenAI's own GPT-Live-1 API is $0.05/min for the voice layer plus a separately billed backend, so expect credit burn to track minutes). **10/01 -- EU inference:** Enterprise workspace admins and owners can enable EU inference under Privacy & security; while on, 'Lovable runs the workspace's AI model requests on providers in the European Union, both while you build and for the AI features in your published apps' -- with the caveats that **'some models and features are not available in the EU, and your workspace uses more credits while EU inference is enabled'**. **10/01 -- API key IP allowlists:** Business and Enterprise admins can restrict a workspace API key to an allowlist of IP addresses and ranges (CSV upload at creation or from an existing key's menu); other addresses are refused. **9/30 -- database password rotation:** ask Lovable to rotate the project's Cloud database password 'as a routine security measure'; it applies the new password without showing it and the app keeps working. **9/29 -- Muse by Meta:** the Lovable MCP server now works with Muse by Meta -- add Lovable as a connector in Muse settings and build or manage Lovable apps from Muse. Earlier in the window, 9/25 added Discord and Google Business Profile app connectors. None of these changes the plan prices; the credit-cost caveats (GPT Live, EU inference) are the parts that affect bills.
2026-10-01•Lovable changelog (lovable.dev/changelog, entries dated 'Oct 1, 2026', 'Sep 30, 2026', 'Sep 29, 2026') -- fetched 2026-10-02 via curl with browser UA
CHAT WITH LOVABLE ADDS A FREE THINKING LANE, AND THE APP-AI MODEL MENU NOW INCLUDES OPUS 5.5 AND GPT-6 SOL/LUNA (September 2026 changelog, vendor-primary). **2026-09-21 -- Chat with Lovable**: 'You can now chat with Lovable to think, ask, and plan without changing any code. Chatting is free within a daily chat allowance on Free, Pro, and Business plans.' Chats live outside projects (dashboard prompt box with Chat selected, or lovable.dev/chats) or inside one as Chat mode, with a 'Start building' card when a change is needed; voice conversations are supported; the same day added Lovable in Telegram with your connected tools, per-tool agent permissions (Always allow / Ask each time / Never allow), and default design systems per group on Business and Enterprise. **2026-09-17 -- the Lovable API** (access tokens, a Postman collection on 9/18) automates workspaces, and a Perplexity web-search connector needs no Perplexity key. **Model menu for AI features built into your app**: GPT-6 Astra, Gemini 3.8 Flash and Gemini 3.5 Transcribe (9/08); GPT Image 2.5 Flare and Sunburst (9/15); **Claude Fable 5.1, Claude Opus 5.5, Opus 5, Sonnet 5 and Haiku 4.5 'with no Anthropic account or API key' (9/23)**, for apps on TanStack Start created from 2026-05-13; **GPT-6 Sol and GPT-6 Luna (9/25)**. Also: Bitbucket Cloud sync and Lovable MCP working with Grok (9/10); two-factor enforcement, SCIM-locked membership and connecting other MCP clients to the Lovable MCP server for Enterprise (9/11); Lovable in Slack on Enterprise and buying a domain from chat (9/01); redesigned Security view with deep and quick scans, and image and video generation broken out in usage details (9/23); Discord, Google Business Profile, Storyblok, AWS, Azure, Google Cloud, Looker and Parallel connectors (9/22-9/25). **Pricing note (verified 2026-09-28 on lovable.dev/pricing FAQ):** the free plan is 'a daily grant of 5 build credits (up to 30 a month), plus monthly grants of 20 Cloud credits'; paid plans add a monthly credit balance, Plan Mode costs 1 credit per message and Default Mode varies by task; the FAQ names Pro, Business and Enterprise tiers, but the plan cards are client-rendered and their dollar prices could not be re-verified in this pass, so the tier prices on this page are unchanged from the May check.
2026-09-25•Lovable changelog (lovable.dev/changelog, entries dated 2026-09-01 through 2026-09-25, fetched 2026-09-28); lovable.dev/pricing FAQ (fetched 2026-09-28)
STALENESS CATCH-UP, JULY 21 TO AUGUST 31, 2026 (vendor changelog; this page was last reviewed 2026-07-18 and none of this was recorded). **Lovable works up to 10 hours on a single message** with credit check-ins (8/26, check-ins beta 8/17); **Chat with Lovable in Slack** and adding your app to Slack as an agent (8/26); **a connector for any API** built by workspace admins on any plan (8/31); **design systems on all paid plans** (8/19); the **Lovable plugin for Figma** exports designs into Lovable (8/21) and Figma files can be attached in chat (8/16); **Gemini 3.7 Flash became the default model for AI features inside your app** (8/18; Gemini 3.6 Flash had taken that role on 7/22), with Veo 3.1 video models (8/07), OpenAI image editing (8/13), Gemini Embedding 2 for search (8/20) and 'Chat Latest' (8/24) added to the menu; Microsoft sign-in for your app's users and dashboards from Snowflake semantic views (8/13); a Trust Center for every published app (8/07); older React + Vite projects can upgrade in place to TanStack Start (7/28); the Lovable MCP server became a Codex plugin (7/22) and gained Antigravity support (7/31); an opt-out from AI model training (7/31); GitLab API and Firebase Cloud Messaging connectors (8/28), GitHub API connector sign-in (8/26), Amazon Redshift and Microsoft Fabric (7/29), Google Analytics, Xero and Pipedrive (7/28), PostHog (7/27); leaked API keys are revoked automatically (7/25). Lesson recorded: Lovable ships several changelog entries a day, so this page needs the changelog enumerated every sweep, not the blog alone.
2026-08-31•Lovable changelog (lovable.dev/changelog, entries dated 2026-07-21 through 2026-08-31, fetched 2026-09-28)

Issues here are sourced from our editorial sweeps, not real-time telemetry. Newer issues may exist.

What to use if Lovable is down

Top AIToolTier-ranked alternatives in the same category, ordered by our overall score.

A

GitHub Copilot

8.3

**Oct 15: @GitHub in Slack and Microsoft Teams now works across multiple repositories in a single conversation (issues, pull requests, bug investigations), can be mentioned anywhere in a message, and can use shared Slack messages and threads as context.** **Gemini 4 Argon joined Copilot on 2026-10-13, the day Google made it GA, for Pro+, Max, Business and Enterprise at provider list price; on 10/15 GitHub scheduled Claude Opus 4.8, Claude Opus 5 and GPT-5.6 Terra for removal from every Copilot surface on 2026-11-16 (Opus 4.8 stays for individual annual subscribers), and HydraFusion gained a Max option and a pool of Opus 5.5, GPT-6 Astra, GPT-6.1 Sol and GPT-6 Luna (10/14).** **Claude Haiku 5.5 joined Copilot on 2026-10-07, the day Anthropic launched it, for Pro, Pro+, Max, Business and Enterprise at provider list price; the same day local sandboxing went GA in Copilot CLI, the Copilot app and VS Code Agent Host at no extra cost, the CLI learned to discover local Ollama models, and GitHub announced a purpose-built secret-detection model whose new push-protection and /security-review checks will draw AI Credits.** **GPT-6.1 Sol landed in Copilot on OpenAI's launch day (2026-09-29, Pro+/Max/Business/Enterprise), the fifth day-one frontier add in eight days, and on 2026-10-02 the four-model retirement slate executed on schedule: Gemini 3.5 Flash, Gemini 3.6 Flash, Kimi K2.7 Code and Claude Opus 4.7 are gone from every Copilot surface.** Same week: HydraFusion's multi-model orchestration reached VS Code 1.140 and the Copilot app (9/30), **computer use** let Copilot CLI and the Copilot app drive desktop applications on macOS and Windows in public preview (10/01), dynamic workflows defined in code arrived for CLI, app and SDK (10/01), the September VS Code roundup added automations, agent merge and Dev Container sessions (10/01), and Copilot code review gained REST/GraphQL request support with Balanced as the default effort level (10/02). Still ahead: the six-model slate on 10/19 and the 10/22 default policy for new features for Business and Enterprise. The 9/22 and 9/28 adds (Opus 5.5, GPT-6 Sol/Luna, Sonnet 5.5) all stand, metered at provider list pricing.

A

Cursor

8.3

**Oct 16: cloud agents can now build interactive canvases and share them by link, the Environments API entered beta for creating and managing agent environments in code, and cloud agent environments hold up to 300 repositories with large environments loading 5x faster.** **Cursor's own plans closed to new customers on 2026-10-12: Cursor is now sold through The X Subscription (Free, Plus $8, Premium $30, Super $100, Ultra $200) with one usage pool shared with Grok, at least twice the coding usage on SpaceXAI's models -- but Claude, GPT and Gemini are no longer in the allowance, billed at API list price on Premium and up and unavailable on Plus. On 2026-10-06 the Cursor iOS app gained remote control of local agents.** **Cursor launched two bots for the last mile of shipping code on 2026-09-23 (Teams and Enterprise): Rollouts, which attaches a monitor to every pull request and watches the change as it deploys per environment -- verified healthy, regression detected, or inconclusive -- and Security Review, which posts one comment per PR reporting exploitable bugs with severity, attack path and a proposed fix.** Rollouts is the Cursor rebuild of Firetiger's Change Monitors on the Bot Development Kit; it can open a revert PR or hand a regression to a cloud agent but does not merge or roll back on its own. Models: Anthropic's 9/28 Sonnet 5.5 post quotes SpaceXAI's Sualeh Asif on CursorBench 4.0 -- Sonnet 5.5 at 55.5% 'second only to Opus 5.5' (57.8%); Grok 4.7 and its Cursor-only Fast variant arrived 9/21. **Cursor Projects (9/10, beta)** and the 11/12 OpenAI shutoff watch continue.

A

Codex (OpenAI)

8.3

**GPT-6.1 Sol Ultrafast is now on the API rate card -- $12 input / $0.60 cached / $15 cache writes / $60 output per 1M up to 272K tokens, six times Standard, closing the DevDay 'coming days' promise -- and on 2026-10-09 the Codex desktop app gained Composer predictions (beta), which suggests your next message after each response for personal Pro users on GPT-6 Astra and GPT-6.1 Sol.** **OpenAI and Atlassian expanded their partnership on 2026-10-06: GPT-6 family models (GPT-6 Astra and the GPT-5.6 series are named) will power agents across Atlassian's platform and Rovo, more than 3,000 Atlassian developers already use Codex, and the Atlassian and Teamwork Graph CLI plugins connect Codex and ChatGPT to Jira, Confluence, Looms and Bitbucket pull requests.** **Two October notes: EU Codex output will carry OpenAI's invisible textGrain text watermark within weeks (API customers can opt in worldwide from 10/05), and the new Enterprise token rate card prices Codex at API Standard rates, names GPT-5.3-Codex as the code-review model and GPT-5.6 Luna as the auto-review model, and puts Astra Ultrafast at 6x.** GPT-6.1 Sol Ultrafast is still not on the API rate card as of 10/05. **DevDay 2026 (2026-09-29) was mostly a Codex release: GPT-6.1 Sol in Codex and the API at $2/$10 per 1M with cached input cut to $0.10, Codex Cloud (reusable cloud environments, tasks that keep running while your laptop sleeps, on Plus and up), a refreshed CLI with voice steering and an /agents view, Code Review in the desktop app with automatic cloud first passes, Codex Security Cloud with Daybreak Blue models and no separate Daybreak application, and the Agents API gaining computer use** -- plus GPT-6 Astra Ultrafast (300 tokens per second in Codex) on Pro 500 and Enterprise, with GPT-6.1 Sol Ultrafast 'coming soon'. GPT-6.1 Sol nearly matches GPT-6 Astra on DeepSWE at one-fifth of the token price and also landed in GitHub Copilot the same day. Still in place: GPT-6 Sol and Luna (9/22), the Agents API public beta (9/10) and the 8/31 retirement of GPT-5.4 from Codex. On 10/01 OpenAI scheduled GPT-5.3-Codex for API removal on 2027-04-01.

A

Google Antigravity

8.0

**Gemini 4 Argon reached Antigravity on 2026-10-13 for Google AI Ultra subscribers and enterprises, and Google is offering 10,000 scientists Antigravity's highest usage tier free for six months.** Google's agent-first AI IDE -- deploys up to 5 autonomous coding agents in parallel on a VS Code fork. Antigravity 2.0 (I/O 2026) is the runtime substrate for Gemini Spark, and the Antigravity CLI is now the official successor to Gemini CLI, which stopped serving consumer tiers on 2026-06-18

A

Roblox Assistant

8.0

Roblox Studio's agentic AI that plans, builds, and playtests games. Planning Mode (2026-04-16) + Mesh Generation + Procedural Models brings 3D-native creation to 70M+ daily creators

About Lovable

Tier B (7.8/10). **Lovable launched Growth tools on 2026-10-14: set a goal such as your first 100 signups and it builds a plan from your app and traffic, prepares SEO, listings and creative, and launches Google, YouTube, Facebook and Instagram ad campaigns you approve, with no extra Lovable fee. Same week: Sign in with Lovable for any website, 60-day restore for deleted projects, Gemini 4 Argon (10/13) and GPT-6.1 Sol (10/15) for app AI features, and Enterprise audit-log export to SIEMs.** **Lovable shipped credit usage limits and alerts for workspaces (10/07), invite-only publishing on Free and Pro (10/08), nine new app connectors plus a Loom chat connector, Drizzle migration files for Cloud database changes, chat-to-chat task handoff and Enterprise workspace publishing domains (10/09).** Describe the app you want in plain English and watch it build itself. **New this week: apps built on Lovable can generate music with Google's Lyria 3 Clip Preview (about 30-second clips) and Lyria 3 Pro Preview (tracks up to 184 seconds) from a prompt or an image (2026-10-05, credits charged per finished track), beehiiv and Ramp connectors arrived, Lovable can restore its own work after a Git push overwrites it, and GitHub secret scanning now detects leaked Lovable API keys (10/05). Earlier: live voice conversations through GPT Live (2026-10-01, TanStack Start apps, uses credits), Enterprise workspaces can pin AI processing to EU providers (10/01, costs more credits), Business and Enterprise API keys can be IP-allowlisted (10/01), Lovable can rotate a Cloud database password from chat (9/30), and the Lovable MCP server works inside Muse by Meta (9/29).** **Chat with Lovable (2026-09-21)** adds a free daily chat allowance for thinking, asking and planning without changing code, plus voice conversations and a Telegram surface; apps built on Lovable can now call **Claude Opus 5.5 (9/23)** and **GPT-6 Sol and Luna (9/25)** for their own AI features, and the **Lovable API (9/17)** automates workspaces. $500M ARR (June 2026) and ~1M new projects a week

Read the full Lovablereview →