103 updates in the last 90 days.
New features, improvements and fixes, newest first.
The Standard model picker now opens on four models: Claude Opus 5.5 (the default), Gemini 4 Argon, GPT-6.1 Sol and Claude Sonnet 5.5. Grok 4.7, Gemini 3.8 Flash and Kimi K3 are still there: choose More models… at the bottom of the list to see them.
Claude Opus 4.6 and DeepSeek V4.1 Flash have left the picker. If one of them is already your model, it keeps working until you choose another.
A project you create while signed in now starts private on every Playcode plan, Free included. Before, a new project on the Free plan started public, so anyone with its link could open it.
Every Playcode plan can now keep a project private, Free included. Before, making a project private needed a paid plan.
Try it: Make this project private - turn off its public link.
Signing in and creating an account look new, and they work the same everywhere on Playcode.
DeepSeek V4 Pro has left the model picker. DeepSeek has been serving every V4 Pro request with V4.1 Flash since mid-September (until a V4.1 Pro exists), so the picker entry no longer bought anything the Flash entry does not - except a higher price.
If you had V4 Pro selected as a default or on a chat, it now runs on DeepSeek V4.1 Flash automatically, billed at the Flash rate: $0.30 in / $1.20 out per million tokens instead of V4 Pro's $1.32 / $3.96. Same upstream model, about 4x cheaper.
We also moved DeepSeek onto redundant serving infrastructure, so the model no longer depends on a single upstream to stay available.
AI used inside your hosted apps is now priced per model, exactly like the in-chat prices - one price book everywhere. Most models move to the standard rate; the flagship cards keep their premium pricing unchanged.
One less switch to find. When your app's sending domain verifies, Send to anyone now comes on with it - your app can email customers right away, from your own domain, with one-click unsubscribe on every mail to a non-member. Before, verified-domain projects still had to discover the switch in Settings > Email; every one of them turned it on.
The switch stays where it was, as the off lever: turn it off and it stays off - for every app of the project, including ones created later. Nothing else changes: without a verified domain, delivery still goes only to recipients who confirmed their address, and the daily caps, suppression and unsubscribe protections run exactly as before.
We chased down a family of rare but painful loading failures - the kind where Playcode showed a spinner and simply never finished. All fixed today:
If loading ever felt stuck for you before - it wasn't your device, and it's fixed. Thanks to the users whose reports led us straight to it.
When you ask the assistant to add payments, subscriptions, or a checkout to your app, it now follows a Stripe playbook by default:
Claude Opus 5.5 is now the default model on the Quality tier. It is Anthropic's newest Opus, it keeps the 1M-token context window and the 128K maximum answer length of Claude Opus 5, and it costs less per token: $4 in / $20 out per million against Opus 5's $5 / $25, with re-read context dropping from $0.50 to $0.20 per million.
One thing to know about credits. Opus 5.5 thinks for longer before it answers. On our own benchmark it spends roughly 1.8 times as many tokens working through the same task, which more than cancels out the lower price per token - so a typical job costs somewhat more, not less. We chose it as the default anyway, because the work it returns is better.
Claude Opus 5 is still one click away in the model picker, and it is the cheaper of the two per answer. If you would rather trade some quality for a smaller bill, pick it - and anything you have already pinned to it stays exactly as it is.
OpenAI completed the GPT-6 family today, and both new models cost exactly half what their predecessors did. They take over the seats those models held in the picker.
GPT-6 Sol replaces GPT-5.6 Sol on the Quality tier, at $2 in / $10 out per million tokens instead of $4 / $20. OpenAI positions it as the balance of intelligence and cost, and its own testing puts it ahead of GPT-5.6 Sol on professional work, factuality and coding.
GPT-6 Luna replaces GPT-5.6 Luna on the Fast tier, at $0.10 in / $0.50 out instead of $0.20 / $1.20. That makes it the cheapest model we offer - good for simple pages, quick edits and high-volume work.
Both keep the 1M-token context window and the 128K maximum answer length of the models they replace, and we pass the full price cut through, so the same work costs fewer credits.
Nothing you have pinned breaks. GPT-5.6 Sol and Luna stay available to existing chats; chats and preferences set to them move to the GPT-6 equivalent automatically, which is cheaper for the same job.
Every popup in Playcode - confirmations, settings sheets, menus, tooltips - has been rebuilt on one design system, so the whole app now asks questions the same calm way.
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.
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.
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.
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.
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.
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.
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.
On very long builds the agent periodically folds older conversation history into a compact brief to stay fast. That fold used to be lossy: the agent could forget its instructions, lose its place, and re-read files it had just read. The whole handoff was rebuilt:
summary, the model working on your project writes a structured continuation brief for itself - what it was doing, what it decided, what comes next, in its own words.
instructions survive every handoff word-for-word.
next step needs, pre-loaded - resuming costs zero extra reads instead of re-opening file after file.
agent gets more room instead of folding again and again.
approaches, so it finishes the step it is on and writes things down first.
On long builds the agent periodically compacts older conversation history to stay fast. Until now it compacted early enough that big tasks - many files, long sessions - could lose track of files it had just read and re-read them.
context windows the agent keeps roughly 2.5x more of the conversation before compacting, so long builds stay coherent instead of looping over the same files.
now appears only when you raise Context above High (Extra High or Max).
yourself, that choice stays exactly as you set it.
You can still change Context per chat in the build-quality dialog, or set your own default in Settings → You → AI defaults.
When the assistant starts a long job - a build, an app-store submission, a big install - the chat now stays yours.
assistant immediately, mid-work, instead of waiting in silence until the job ends.
long wait - and the assistant stays quiet afterwards until you speak.
a small note appears in the chat and the assistant picks the result up and continues - even if it had already handed the chat back to you. A running job can no longer be forgotten.
longer risks two competing replies.
When something has to reach your phone - opening your app in Expo Go, checking a preview on a real device - the assistant now draws a QR code in the chat instead of asking you to type a long address across two screens.
you can still copy it in one click.
scannable rather than decorative: it sizes itself to the address it holds, and in a column too narrow to scan from it steps aside and leaves you the text.
Only for addresses that genuinely have to cross to another device. A link you can simply tap stays a link.
When you upgrade to Max, every project you already have now moves to the larger Max machines automatically - 8 CPU · 16 GB in the editor and bigger production machines with a 200 GB disk - not only the projects you create after upgrading.
it the next time you open them.
within minutes.
of minutes - while they move to a bigger machine.
And if you ever move back to Pro: CPU and RAM return to Pro sizes, but any disk space you grew into stays yours. We never shrink your disk.
