139 updates in the last 90 days.
New features, improvements and fixes, newest first.
When you uploaded an image and the AI moved it into another folder - for example into public - the image could turn blank, even though the AI said the move had succeeded. Images you upload now keep working wherever the AI moves them, and undoing a move restores them correctly.
Your workspace credits are now one balance for everything Playcode runs for you. Until today only the AI chat and agents drew credits.
keep, and for traffic beyond the included amount. A sleeping computer bills disk only. Each computer's rate is shown next to its hours in Settings > Usage.
their secret key - use credits too, at the model's rate.
Settings > Usage now shows all spending in one place: AI chat + agents, one row per project whose apps used the AI Gateway, Email, and one row per cloud computer, each with quantity × rate = credits. The period buttons at the top drive the whole page - today, this week, this month, all time - and the spending list names the period beside its total. Email alone is shown per billing cycle, because its included sends are a cycle allowance.
If your credits run out, AI requests pause until you add credits. Email beyond your plan's included sends is stored but not delivered until you do; included sends and mail to your own team always go out. Cloud computers keep running: we email you, and only if the balance is still empty 72 hours later do they pause. Nothing is deleted, and the same computers start again as soon as credits are added.
Nothing changes about how you buy credits, and your balance shows the same number in the editor, in Billing and in Usage.
If you published an app, or created a new one, after your workspace moved to a paid plan, turning on Send to anyone in Settings > Email could be refused with a message saying the workspace needed a paid plan, even though it had one. The AI assistant repeated that message and suggested upgrading.
Every affected app is fixed, and new apps now start with email delivery matching your plan. If you saw that refusal, Send to anyone works now: turn it on in Settings > Email, or ask the assistant to do it.
Open a JavaScript, TypeScript, React, Python, SQL or any other language template and the code is the first thing you see: the file tabs on top, the file tree on the left, the AI Chat right under the editor, and the live preview with the console beside them.
Before, every template opened with the chat alone and the code sat a click away in the menu.
Website and business templates keep opening chat-first: describe what you want, and the preview updates as you go.
Google's permission screen lets you continue without ticking the Search Console box. Before, Playcode still showed the account as connected, and every request the agent made on it came back with a permission error.
Now that connection is refused on the spot, and the Connections page says which permission to select before you try again. A connection granted that way earlier is marked as revoked within a couple of hours, with the usual Reconnect button.
Mobile projects get a Phone tab beside Preview (View, then Phone; on the phone it is in the project menu). It shows your app the way a phone sees it, a QR code to scan with your phone's camera, and one line that says whether the phone preview is running. The QR opens the app in your phone's browser: nothing to install, no account. A Browser | Expo Go switch turns it into the native preview for Expo Go when you want that; Expo now asks for the same Expo account on the phone and on the dev machine, and the chat walks you through it. When you are already on the phone, the tab has an Open on this phone button, and the address in a chat card is a link you can tap.
Your dev machine now has its own address. Anyone you give it to can use the app while the machine is on: your phone, a teammate, a client on a call, a webhook you are testing. The machine stays awake while the app is in use from any device.
Only you can turn it on: opening the project in Playcode wakes it, and so does the agent while it works for you. It goes to sleep after a quiet while, and after four hours without you or the agent. When the app on your phone finds the machine asleep, it shows a banner with one button that opens the project and wakes it.
The address is not a public link. Publishing still is: a published app keeps its permanent link that works for everyone, whether your dev machine is awake or not.
Your Profile settings now list every browser you are signed in on - the browser and system, when it signed in, when it was last seen - with Sign out on each row and Sign out everywhere else in one click. Signing out really ends that session on our side, so a lost laptop stays out.
Sensitive actions - buying a domain, changing your sign-in email, creating or revoking a token - now ask you to confirm it's you with the sign-in code when it has been a while since you last did. Everyday work never asks.
In Workspace settings, Developers gained a Signed in as you list: the tools you let act as you through Sign in with Playcode, the workspace each one may act in, what it may do, and Revoke to sign a tool out on every computer at once. The project's Secret key pane replaces API keys: the key your app already has, masked, copied on purpose, rotated when it leaks.
When you add your own sending domain in Settings > Email, the DNS records now show every field in full: Name, Value and, for the MX record, Priority, each with its own copy button. Before, the name was cut off on screen and only the value could be copied, so the long DKIM names had to be retyped.
Copy all records puts the whole set on the clipboard as labelled text, for a note or for whoever runs your DNS.
If your domain's DNS runs at GoDaddy or Namecheap, the names are shown the way those providers' Name field expects them, without your domain at the end.
When you move a domain's DNS to Playcode, the certificate for the bare name now follows the nameserver change as soon as it lands, instead of up to an hour later. The check that decides it reads the registry itself on every pass.
Settings > Domains tells you exactly what that check saw: which nameservers answer today, which ones they must be, and when we last looked. The old sentence that promised a fix "within minutes" is gone.
"Finish setup" on a domain whose DNS moved here opens the same three-step switch the connect flow shows: the values to paste, what the world reports while the change spreads, and the done card once everything serves.
Moving DNS to Playcode keeps a www that already points at your Playcode site, and the review list says plainly when an unchecked record would leave a name unanswered after the switch.
Turning on Send to anyone in Settings > Email now applies to your Development and Production computers at once. Before, only the published app was switched on, so a test send from the editor could still be held while the page said delivery was live.
Mail that was held before you switched it on no longer sits there: every held address now shows a Deliver button as soon as your domain is verified and Send to anyone is on, including addresses that were never added to your verified recipients.
Your sending domain verifies within seconds of the records going live, with nothing to click. The assistant can check a domain for you too, and reads each email under the computer it came from.
Adding a customer's address to Verified recipients now warns you first: that list is for your own inboxes, and each add sends the person a permission request. Customers are reached through your own domain.
A cloud computer keeps up to 20 checkpoints you own. When the assistant reached that number it used to refuse to take a new one, and a schema migration could go in without a rollback point. Now, at the cap, the assistant replaces its own oldest checkpoint and tells you which one it replaced. The checkpoints you saved yourself are never the ones replaced.
If the Checkpoint history dialog cannot open, it now says why instead of staying blank.
Giving your site an address you already own used to start with four tabs named after mechanisms. It now starts with the name. Type it, and Playcode looks up where it is managed and recommends the best way first:
your email keeps working, and you make one small change at your provider. Then never again.
lands.
for providers that cannot do the one above.
Each card carries a ? that says in one sentence what the setting is. On Cloudflare, the one setting leads and nothing pushes you off it. Moving the whole registration to Playcode is a quiet line under the first card, not a tab.
The setting card shows a live chip - *Not seen yet*, *Found*, *Live* - and turning on Also answer at www adds its one extra setting right there, same visit. The same flow runs for Playcode Cloud and Playcode Pages projects, and the workspace's Domains list now keeps watch on its own while anything is still setting up.
DeepSeek V4.1 Flash is now the DeepSeek Flash option on the cheap-and-fast tier, in place of DeepSeek V4 Flash. DeepSeek retired V4 Flash today and shipped V4.1 Flash on a new architecture that its own tests place ahead of DeepSeek V4 Pro - and it can now see images (V4 Flash was text-only), so screenshots and reference designs work on this model too.
It is also cheaper: $0.30 in / $1.20 out per million tokens, down from $0.44 / $1.32. We pass the cut straight through, so the same work costs fewer credits.
If you had DeepSeek V4 Flash selected as a default or on a chat, it now runs on V4.1 Flash automatically - nothing to change on your side.
Gemini 3 Flash remains the tier default.
Attach a document to the chat and the agent can work from it - no more re-saving a spreadsheet as CSV so it can be read.
the same way it sees an attached image.
Export a table from your project, edit the prices in Excel or Google Sheets, attach it back, and the agent updates the site from it.
This works in browser and Cloud projects, and for files you attached before today. Very large PDFs (over 100 pages) are not shown to the agent; it will ask you for the relevant pages instead. Legacy formats (.xls, .doc, .pptx) are not supported yet - save as .xlsx, .docx or .pdf.
The status chip next to a custom domain in Publish and in Workspace > Domains used to say only *Verifying* or *Action needed*. It now tells you why:
yet. This takes minutes, sometimes up to a day.
is on its way.
issued. Fix the records and we retry on our own.
Nothing to do.
The same reading applies to every domain, however it is connected, so two screens never disagree about the same address.
Two fixes for custom domains on Playcode Cloud.
Root domains now go live. A root domain (example.com, not www.example.com) needs one extra verification record at the edge before it can serve over HTTPS. When Playcode runs your DNS - a domain bought here, or one you moved to Playcode nameservers - that record is now added for you the moment you connect, and the edge is asked to check it right away. If your DNS stays at another provider, the connect dialog shows the record beside the routing record, and the assistant lists both.
Connections no longer get lost while you set up DNS. A connection made before a nameserver change had finished could be dropped as abandoned. Playcode now keeps every connection you make, checks it against the edge every few minutes, and restores it automatically while your domain points at Playcode. If a domain never points at Playcode for a week, you get one email and can reconnect any time.
The Domains settings and the assistant's domain status now say what the edge actually serves, not only whether DNS has landed.
In the editor's Preview, a link that opens a file in a new tab - a PDF from your public folder, an image, a download - now opens that file, the same way it does on your published site.
a correct link look like a bug in your site.
the editor) now say what they are: the preview only runs inside the Playcode editor. Use Open preview in a new window from the preview toolbar to view your project in its own tab.
Search Workspace > Domains and the list just got a lot longer: 615 new extensions are now searchable and buyable, priced at what the registries actually charge today.
and .zone are in, alongside hundreds of others spanning tech, business, and lifestyle endings.
.dev, and .io stay at the price they have always been - this expansion only adds, it never repriced what you already use.
a handful of membership-only names - need something extra from their own registry before anyone can register them through us. Search still tells you what is missing instead of a dead end; we are working through that list one registry at a time.
Apple shipped a major Expo Go update this week, which broke the phone preview for mobile projects: scanning the QR code showed an SDK-compatibility error on iPhone. Fixed on both sides - new mobile projects target the Expo version the App Store actually ships, and the AI now checks your project against the current Expo Go before handing you a QR code, upgrading the project first if it is out of date.
The QR code itself also got more reliable: it now always carries the secure exps:// link, so it opens in Expo Go on the first scan.
GPT-6 Astra - OpenAI's most capable model, built for the hardest end-to-end work - is now available on the Ultra tier, next to Claude Fable 5.1. OpenAI launched it yesterday behind a limited-access program; our access opened this morning and it went through our full verification the same hour: live tool-calling, prompt caching, and token accounting all confirmed on the real wire before it reached the picker.
Astra is priced identically to Claude Fable 5.1 ($10 / $50 per million tokens at the provider), and because its tokenizer encodes the same work to roughly a third fewer tokens, the same build tends to cost fewer credits. Claude Fable 5.1 remains the Ultra default.
Background agents (the tasks your AI delegates work to) can now look at images, capture page screenshots, and understand videos, just like the main agent. Visual work delegates reliably: captioning a photo gallery, writing honest alt text, matching a reference design, picking a video poster frame, or reviewing a page's layout no longer fails partway because the helper agent could not see what it was working with.
Available on vision-capable models across all task roles - explorer, coder, auditor, and researcher.
Gemini 3.8 Flash is now the Gemini option on the Pro quality tier. It launched today at the same price as its predecessors, and Google's own launch numbers put it ahead of 3.7 Flash on every published axis - software engineering, terminal coding, and multi-step reasoning. In our own SVG drawing benchmark it is measurably the strongest Gemini Flash yet.
It also costs you fewer credits than 3.6 Flash did. Google discounted this rate card after we first added 3.6 Flash, and our pricing had not caught up, so 3.6 Flash was charging roughly double what it should have. That is corrected: every Gemini Flash model now bills at the real rate.
If you had 3.6 Flash selected on a chat, it keeps working and stays on that chat - nothing you pinned has moved. It is simply no longer offered in the picker for new selections.
The cheap-and-fast tier is unchanged. Gemini 3 Flash is still the default there, and still the cheapest way to build.
Grok 4.6 is now the Grok option on the Pro quality tier, in place of Grok 4.5. xAI prices the two identically and calls 4.6 "the most intelligent and fastest model we've built" - and in our own SVG drawing benchmark the difference is visible: where 4.5 famously spent 668 tokens barely attempting the task, 4.6 actually engages with it.
If you had Grok 4.5 selected on a chat, it keeps working and stays on that chat - nothing you pinned has moved. It is simply no longer offered in the picker for new selections.
GLM 5.3 is now the GLM option on the cheap-and-fast tier, in place of GLM 5.2. Z.ai prices the two identically, and 5.3 is the newer and stronger model - Z.ai's own measurements show it doing markedly better agentic coding work while spending *fewer* output tokens than 5.2 at every reasoning-effort level, which on a reasoning model means the same work tends to cost you less.
It also brings a real reasoning-effort dial (low / high / max), which the Intelligence setting now drives.
If you had GLM 5.2 selected on a chat, it keeps working and stays on that chat - nothing you pinned has moved. It is simply no longer offered in the picker for new selections.
GPT-5.6 Luna is now available on the cheap-and-fast tier. OpenAI cut its price fivefold today - to $0.20 in / $1.20 out per million tokens - which makes Luna the cheapest model in the picker, below even Gemini 3 Flash. In our SVG drawing benchmark it lands right beside Gemini 3 Flash in capability, with a reasoning-effort dial that responds cleanly to the Intelligence setting.
We also passed today's OpenAI price cuts for GPT-5.6 Sol and GPT-5.6 Terra straight through - the same work now costs you fewer credits on all three.
Gemini 3 Flash remains the tier default.
You can now connect email services like MailerLite, SendGrid, Mailchimp, Klaviyo, and Postmark to a domain managed by Playcode.
These services verify your domain with DKIM records: CNAME records whose target contains an underscore, such as litesrv._domainkey.mlsend.com. Playcode's DNS editor rejected those targets as invalid, which blocked email authentication. Underscores are now accepted in CNAME, ALIAS, NS, and MX targets, so you can add the records exactly as your email service shows them.
The app now opens in your browser's language on your first visit - all ten languages, including the sign-in page. On the website, the language switcher now also lives in the top menu (next to Pricing on desktop, inside the menu on phones), and if the site isn't in your language, a small note offers the switch in your own language.
Also fixed on phones: on some Android screens the page could grow slightly wider than the display, which pushed the menu button half off the edge. The menu stays put now, and a new account button next to it takes you straight to sign-in - or to your projects if you're already signed in.
Claude Fable 5.1 is now the default model on the Ultra tier, replacing Claude Fable 5. It is Anthropic's most capable model, tuned for the hardest reasoning and long agent sessions - and it comes with a real cost improvement: reading cached context is 4x cheaper than on Fable 5. In practice that is most of what a long coding session pays for, so the deeper into a project you are, the more you save.
Token prices are unchanged. Claude Fable 5 remains available in the model picker if you have it selected.
Attaching files used to mean hitting a small target inside the chat box. Now the whole editor catches your files:
the file attaches to your message.
the element under your cursor highlights - release, and the image lands in the composer aimed at that exact spot. Press Enter and the AI places it there.
can also drop a file straight into a folder.
Every drop answers visibly: the file flies to where it landed, and if you drop somewhere that can't take files, a short note points you to the chat or the file tree. A missed drop never navigates the page away or loses what you typed.
Publishing asked the wrong question about who you are. If you were a workspace admin opening a project a teammate had created, the Publish button appeared and looked ready - but pressing it did nothing at all. No progress, no message, no explanation. Only the person who originally created the project could publish it.
The button was reading your team permissions, while the publish action behind it was still checking whether you personally created the project. Both now read the same rule: if you can manage the project, you can publish it. Unpublish was affected in the same way and is fixed too.
Nothing changes for personal projects, and nobody gained access they did not already have - editors and viewers are unchanged.
