Changelog

When you ask the assistant to add payments, subscriptions, or a checkout to your app, it now follows a Stripe playbook by default:

• Stripe Checkout over custom card forms. The hosted payment page converts better - Apple Pay, Google Pay, one-click Link, and local payment methods appear automatically - and Stripe's own card-testing defenses stand in front of it. Playcode sells its own plans the same way.
• Fraud protection armed from day one. Stripe.js loads on every page of your site so Stripe Radar can tell real customers from bots, and the assistant reminds you to keep Radar on. An unprotected payment form gets found by card-testing bots within days, and the disputes that follow can get a Stripe account blocked.
• Keys handled safely. Secret keys stay on the server, never in page code. On browser-only projects the assistant uses Payment Links, which need no keys at all.
• Real fulfillment. Purchases unlock through verified Stripe webhooks, not just "the buyer landed on the success page".

If your domain was connected with an A record - the way most DNS providers connect a root domain - turning on "Also answer at www" failed with a confusing error about Cloudflare, no matter what you changed at your provider. The www setting now follows how your root domain is served: flip the switch, add the one record it shows you, and www goes live on the same address as your root.

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.

Very rarely, the AI provider's safety filter refuses a request outright and returns nothing. Until now the chat showed an empty reply with no explanation, and the turn was still charged. Both are fixed:

• You are told. The chat now shows a notice that the provider declined the request, and that the cause is usually something earlier in the conversation rather than your last message. The action offered is Undo & rephrase, because sending the same thing again gets the same refusal.
• You are not charged for a refused turn that produced nothing.

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.

• Destructive actions ask properly. Deleting a chat, folder, project, domain or token states what happens in one plain sentence, and the most dangerous ones wake their button only when you type the exact name.
• Clearer questions everywhere. Renames open with your current name ready to edit, the resize dialog shows the price before you switch, and the unlock-for-transfer flow hands you the code with a plain way to lock it back.
• Menus and pickers cleaned up. The project, workspace and attachment menus render as one crisp panel, and the build-quality picker opens right by its button instead of covering your work.
• Phone-friendly sheets. Top up and Share now open as bottom sheets on phones, with the main action in thumb reach.

Pro includes 100 GB of Playcode Cloud bandwidth a month and Max includes 1 TB. Until today those numbers were enforced as a hard limit: when a workspace crossed it, its published apps were suspended until the next month - with no warning. That was wrong, and it is fixed.

• Your site keeps running. Past the included amount, Playcode Cloud keeps serving your visitors and the extra traffic is simply metered at $0.05 per GB (0.2 credits), on the same balance as everything else. Nothing is charged for it before September 29, 2026, as announced.
• You set your own ceiling. Spending controls in Settings → Billing are the only cap - yours, not ours.
• The pricing page now says exactly this, instead of "100 GB / month", which read like a wall.

If your published apps were suspended by this limit today, they have been restored.

Two ways the sign-in window could leave you with nothing to press are fixed:

• When the Google button cannot load. Some browser extensions, security tools, and office networks stop Google's sign-in button from loading. The window used to show an empty box and stay that way. Now it tells you within a few seconds that Google sign-in is unavailable, and that you can continue with your email instead - your Google address opens the same account.
• When your browser fills in your email. If your browser or password manager filled in the email field for you, Continue could stay greyed out. It now always works, and if something is wrong with the address, Playcode says what.

If a file you attached to the AI chat could not be uploaded, pressing Send used to do nothing - no message, no explanation. That is fixed:

• Attach a file before you sign up. A file added to your first prompt now travels with it. Before, the message could fail to send right after you created your account.
• You are told at once, by name. When a file cannot be uploaded, Playcode says which file and why - it could not be read from your device (common with files still syncing in OneDrive, iCloud, or Dropbox), your storage is full, the connection dropped, or it is not an image your browser can open - and what to do next.
• Send never goes quiet. If a message cannot go because of a failed file, Playcode tells you so. Your text and your other files stay exactly where they were.
• Nothing gets dropped. When one file in a batch failed, the files that did upload used to disappear from your draft. They stay now.

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.