Sudowrite Release Notes

Barely a week after launching GPT-6 Sol, OpenAI is back with an upgrade: GPT-6.1 Sol is now available, and we've added it to Sudowrite.

OpenAI built this one to be even better at detail-heavy work, and says it makes about a third fewer factual errors than GPT-6 Sol on tricky prompts. For fiction writers, that shows up as better attention to your Story Bible details in longer Drafts. Early reviews of its prose are mixed, with some testers finding GPT-6 Sol's writing a bit more natural. (Try both on the same scene, and see which you prefer!)

GPT-6.1 Sol is available now in Write, Draft, and Plugins. Let us know what you think.

Claude Sonnet 5.5 launched today, and we’ve already made it available in Sudowrite. It's Anthropic's new mid-tier model, and it carries over some of the creative writing improvements we saw in Opus 5.5 (which we added last week). In our testing, it's about 30% faster and 30% cheaper than Opus 5.5.

We've also added several of the most-requested models from our community:

• Gemini 3.7 Flash and 3.8 Flash are Google's latest fast models. These brainy boys can handle a huge amount of text at once, which makes them great in Draft and especially strong in plugins that work across your full manuscript.
• GLM 5.3 is Z.ai's new flagship. It writes consistently solid prose and scores near the top of creative writing benchmarks. It's also one of the least repetitive models in testing, so try it for those long Draft sessions. GLM 5.3 Flash (formerly Ox Alpha) is the lighter, faster version.
• Qwen 3.8 Max is Alibaba's top model. Try it when you want a completely different-sounding voice on the page.
• Grok 4.7 is xAI's latest. Reach for it when you want strong prose that can handle no-holds-barred spice or violence.

Every model has its own strengths and weaknesses. Our goal is to make as many as possible available in Sudowrite, so you can find the right model for whatever it is you're working on. (Different pens for different pages!)

You'll find all these new models in the Prose Mode selector in Write and Draft, and in Plugins too. Let us know what you think, and which ones earn a spot in your regular rotation.

You’ve given your Characters names, aspirations, rich backstories, and probably even some undeserved trauma. Now you can give them faces too.

Character Portraits are now available in Story Bible. Effortlessly generate impressive portraits directly from your character cards or upload images you already have, to maintain a persistent visual reference for each character.

From description to portrait

Portrait generation uses your character’s existing Physical Description, so there’s no need to write a separate image prompt. Open a character card, click the empty Portraits box, choose a style, and click Generate.

We’ve included four default styles: Painterly, Cinematic Realism, Bright Editorial, and Storybook. Pick one, or select all four to generate different variations at once. Your brooding antagonist might look surprisingly charming in Storybook.

A little art direction

Want a particular outfit, expression, or setting? Add instructions in Appearance details to guide the portrait. You can even upload a reference image and explain what you’d like incorporated from that—say, a specific jacket your character should be wearing.

For more control over the art style, deselect the presets altogether and describe your own instead. A black-and-white pencil drawing? A vibrant graphic novel look? Give it a try.

Your cast, at a glance

Every generated portrait is saved to that character’s gallery automatically, so you can keep different looks and compare them later. Already have the perfect image? Use Upload to add it directly to the gallery.

Pick your favorite and click Set thumbnail. That portrait will appear beside the character’s name even when their card is collapsed, making it easier to find a familiar face in a crowded Story Bible. You can change the thumbnail or delete unwanted portraits whenever you like.

So what are you waiting for? Head to your Story Bible’s Character section and start firing off the glamour shots. We can’t wait to see who you make.

It was a big day in AI. Three bleeding-edge models landed today—Anthropic's Claude Opus 5.5 and OpenAI's GPT-6 Sol and GPT-6 Luna. All three are now in Sudowrite.

• Claude Opus 5.5 is the first model in Anthropic's new Claude 5.5 family. Anthropic says it performs at the level of Fable 5.1 on most work, while running more than 30% faster than Opus 5. Anthropic says the writing is clearer, follows instructions more closely, and as one early tester told them, "it writes the way I do."

• GPT-6 Sol and GPT-6 Luna round out OpenAI's GPT-6 family below Astra. Sol is super smart and makes about half as many factual whoopsies as its predecessor—making it great for Story Bible adherence and a solid choice for Plugins. Luna is the quick, inexpensive choice: useful for lots of shots on goal, brainstorming… anything where you want to generate a lot and sort it out afterward.

• Each of them uses fewer credits than the model it replaces. In early side-by-side runs on the same passage with the same inputs, GPT-6 Sol came in around 40% cheaper than GPT-5.6 Sol, GPT-6 Luna around 10% cheaper than GPT-5.6 Luna, and Opus 5.5 just barely cheaper than Opus 5. There’s a big gap between these models though, with Sol at roughly a third of Opus 5.5's credit cost, and Luna at about a seventh.

That’s a lot of numbers for a site about words though, and what matters is what you think of their prose. **All three are available now in Write, Draft, and Plugins. **Give them a spin and let us know what you think.

We’ve made some big updates to Chat very recently, improving both its speed and performance.

Chat responses are now twice as fast - We moved Chat to faster infrastructure this week, cutting response time in half in the process. You should definitely notice it on bigger tasks.

Chat makes fewer mistakes - We've been working hard to improve Chat’s performance where it’s most likely to stumble. Our most recent fixes have reduced error rates by 30%, meaning it’s now far less likely to drop context, misplace an edit, or give up. We’re not done yet, though, and there are more Chat improvements to come.

Rewrite now runs on our in-house model - Rewrite had been using Anthropic’s Claude Sonnet for a while. We just moved it to Ballad, and the results speak for themselves: authors are now 20% more likely to actually use the resulting Rewrite. If you haven’t tried Rewrite in a while, it’s worth another spin.

Actually print your documents - Hitting Ctrl + P or Command + P while viewing the Sudowrite editor used to pop up a blank page and a message about needing a wider browser. Well, good news, folks: it will now print a clean version of whatever document you're viewing.

OpenAI just released GPT-6 Astra, their newest flagship model, and we've added it to Sudowrite.

OpenAI is calling Astra "a new generation of intelligence"—their most capable model yet. Their launch has focused on how GPT-6 enables complex, technical work, as well as its incredible instruction-following capabilities. For authors, that can mean much stronger continuity across chapters or tighter adherence to the Story Bible. It also makes Astra a great candidate for building and running multistage Plugins on Sudowrite.

As for prose quality, our early tests are promising. It sounds a bit more human than prior GPTs. But we still have a lot to learn about how well it handles long-form fiction—we’re excited to hear what you think of it.

GPT-6 Astra is available now in Write, Draft, and Plugins.

Anthropic just released Claude Fable 5.1, an upgrade to their flagship Fable model. We've added it to Sudowrite.

Fable 5 has been a recent favorite among Sudowrite authors, and 5.1 is a refinement of that same flagship. Anthropic points to performance gains and (notably for authors) fewer false refusals. In plain terms: 5.1 should be even less likely to balk at legitimate story content—dark themes, violence, heat—so your prose can go wherever the story needs to go.

In testing, it was nominally cheaper to use than Fable in the Write button, whereas Draft credit usage is basically identical. We haven't put it through its paces on long-form fiction just yet, so we can’t fully attest to its prose. Maybe you’ll let us know what you think?

Claude Fable 5.1 is available now in Write, Draft, and Plugins.

We just added a batch of formatting improvements that will give you more control over paragraph spacing and make copy/paste more reliable.

Set your own paragraph spacing

There’s a new Paragraph Spacing setting in your account settings (under the gear ⚙️ icon in the upper right). Choose your preferred paragraph spacing, and it applies consistently across your projects—no more hand-inserting blank lines for readability.

Tidy up empty lines in one click

If you (or a prior import) left empty “spacer” lines to provide a visual buffer, a new toolbar button will collapse them for you—either at the document or project level—so you can use the new paragraph spacing settings instead.

Copy and paste that preserves your formatting

Pasting into Sudowrite from Word, Google Docs, ChatGPT, or Claude now preserves formatting far more reliably. And copying out of Sudowrite will no longer double your line breaks. Imports come in cleaner too, without phantom empty paragraphs.

A more polished editor all around

Headings now scale with your text size and match your chosen font. Nested bullets now use proper markers with tighter spacing. And your formatting—bullets included—should now appear in the editor exactly the same as it does in cards in your History section.

Big thanks to everyone in the community who flagged these copy/paste and spacing issues in recent months. This one’s for you.

The team has been hard at work on fixes and key improvements this week. Here’s what’s new.

Draft won’t charge you more than its estimate

We improved the Draft tool’s estimates recently, and in doing so made that estimated range into a promise. You’ll no longer see credit charges in excess of the estimate’s ceiling in the Draft planning step. Hooray!

One note: While making this update earlier this week, we briefly broke the retired My Voice model options in Draft. My Voice users hit a credit-estimation error and couldn’t generate. The issue lasted about a day, but it’s fully fixed now. Sorry about that!

Chat Improvements

Chat reads and inserts more reliably

We fixed a batch of issues that made it difficult for Chat to read your document or insert its edits. Reading and inserting are more reliable now.

Failed plans shouldn’t use your credits

It was possible for a complex multi-step plan like a complete manuscript review to fail and still charge you credits. We fixed that, and you won’t be charged in those cases.

Reduced internal jargon in your messages

Chat’s own reasoning sometimes includes noisy jargon—document IDs, “tool” references, etc. We tweaked it so it would stop referencing that in conversation.

Other Improvements & Fixes

Write now completes the sentence

The Write button previously prioritized your word count preference over completeness of thought—meaning it could stop mid-sentence. It now runs to the nearest complete sentence, even if that means a few extra words.

Custom Rewrite instructions stick around

The Rewrite button’s “Customize” instructions had quietly become single-use. We made it work like it used to, so they stay put for repeated rewrites.

The highlight toolbar waits to appear

When you select text, the pop-up toolbar now appears after you release the mouse button instead of mid-drag—so it stops obscuring the lines around your selection.

Find and Replace now handles doc switching

We changed Find and Replace so that if you have a term entered when switching documents, it re-runs automatically in the new doc.

New titles stay put

Typing a title too quickly in a brand-new project could sometimes snap the title back to “Untitled.” Your title now sticks.

A cleaner document list

We improved the document list in your left bar—giving a bit more space, improving contrast for accessibility purposes, and making (•••) menus and toggles only show up when you need them.

Undo no longer undoes more than it should

We fixed a bug with undo where it could reverse the past few edits rather than just your most recent edit. Meanwhile, the editor’s Undo button now works on the first click after you insert text from a card. (Did you know there’s an Undo button in the editor toolbar? I didn’t, and I write these!)

It’s also worth calling out a noteworthy fix on the Sudowrite mobile app this week:

We fixed the cursor jump in Story Bible

On mobile, the cursor was jumping to the end of certain Story Bible fields after each character, making them frustratingly difficult to edit. We fixed that!

Some fresh improvements to report: a nice price drop on a couple of our OpenAI models, and another round of Chat improvements based on your feedback.

💸 GPT‑5.6 models just got cheaper

OpenAI recently lowered its prices on some of its models, and we're passing the savings on to you. GPT‑5.6 Luna now uses 70% fewer credits on Sudowrite, while GPT‑5.6 Terra uses 10% fewer. We tweaked GPT‑5.5 while we were at it, and it now uses about 12% fewer credits. You don’t have to change anything to benefit from this—if you write with any of these AI models in Write, Draft, or Plugins, your credits will just go further now.

💬 Chat fixes & improvements

We remain hard at work, making Chat behave the way you expect:

• See Chat's thought process in Chat Only — The “working” box now shows up in Chat Only mode, just like in Allow Edits.
• Narrow questions stay narrow — Asking about one specific thing no longer kicks off a full Feedback sweep across every review type, so you won't burn credits you didn't mean to spend.
• Resend actually resends — If a response stalled, hitting Resend could sometimes throw an error instead of retrying. It now consistently retries.
• More accurate document edits — We made it so when Chat inserts changes into your manuscript, it places them more precisely.
• Fewer false "stuck in a loop" messages — Chat would occasionally claim it was stuck in a loop even after finishing the task. We've cut those way down.
• Story Bible shortcuts in your current chat — Hitting a generate button in Story Bible no longer creates a brand-new chat thread. We made it so the prompt box now pops into your current chat.

🛠️ Other improvements & fixes

• Generate Scenes costs less on long projects — We’ve optimized the Generate Scenes feature. It now pulls less redundant context, which reduces the cost of scene generation on longer projects.
• Clearer Draft limit warning — We reworded the Draft input‑limit warning—occasionally triggered in super large projects—so it's less alarming and easier to address.
• Resizable comment column — We changed the comment column so that it’s fully resizable. Just drag it to your preferred width and it’ll stay that way.

Keep the feedback coming folks! 🫡

Since our last roundup we’ve added a new AI model, made Chat way better at knowing which words you’re talking about, and fixed a batch of bugs you reported. Here’s what’s new.

🆕 New model: Kimi K3

We’ve added Kimi K3 to Write, Draft, and Plugins. Kimi K3 is a new AI model praised for its creative writing chops, sitting at #2 on EQ-Bench’s creative writing leaderboard (second only to Claude Opus 5, which we added last week). It’s apparently quite good at register: ask for hardboiled or lush and it changes its sentence rhythm, rather than just adjectives. Audition it on a scene with a strong voice and let us know how the prose lands.

↩️ Better, safer Undo

We improved the way Undo handles Chat-based edits. If Chat had edited your manuscript earlier in a session, pressing Ctrl/Cmd + Z later could roll the document back to before that Chat edit instead of undoing only more recent manual edits. Undo now reverses the most recent change chronologically, the way it should.

💬 Chat reliability improvements

We’ve been very focused on improving how Chat handles your instructions.

• No more “your manuscript is empty” - It was possible for Chat to write you a useful chapter critique… and then discard it in favor of telling you your manuscript was empty. We fixed that!
• Highlights stick to the correct document - When you highlighted text and asked Chat about it, it was possible for Chat to reference a different file in your sidebar—or claim it couldn’t load your chapter at all. We fixed that too, and it should better understand that highlights are associated with your active document.
• Accurate word and mention counts - Ask how long a document or project is, or how many times a word appears in a document, and Chat now actually counts instead of estimating.
• Pasting editable text into Chat - Pasted text was turning into an uneditable chip instead of dropping into the message box as plain, editable text. We changed that so it remains editable.
• Long requests don’t vanish - A big Chat request that ran for many minutes could end in a bare “Load failed” with nothing saved, forcing you to start over. We made long-running requests like that preserve their work.
• Comment replies are reliable again - Sometimes @Sudowrite replies in document comments could fail with a generic “I wasn’t able to generate a reply” error. We’ve resolved that issue.

🛠️ More improvements & fixes

• Complete sentences from Brainstorm - Long Brainstorm ideas were being truncated, leaving sentences incomplete in some cases. You’ll get a complete idea from now on.
• Worldbuilding trait edits persist - We fixed an issue that caused Worldbuilding traits to overwrite themselves as you typed into them. (Autosave was a little overeager, but it’s tamed now.)
• Smart Dictation (on mobile) preserves nicknames - Inside a project, Smart Dictation was “helpfully” expanding a spoken first name or nickname into a character’s full Character Card name. It now writes the name as you said it.

Thanks as always—and please keep the bug reports coming.

Anthropic just released Claude Opus 5, their newest Opus-class model, and we've added it to Sudowrite.

According to Anthropic, Opus 5 comes close to the intelligence of their flagship Fable 5 model at half the price. It's a big jump over Opus 4.8 on reasoning and instruction-following benchmarks—which, for authors, means better Story Bible adherence and less plot drift. Early testers also report that Opus 5 may be more permissive than other models.

We haven't put Opus 5 through its paces on long-form fiction just yet, so we’re not ready to attest to its prose. The Opus line has historically been a favorite among Sudowrite authors for its warmth and character voice though, and on paper this is the strongest one yet—but you'll be finding out alongside us. Claude Opus 5 is available now in Write, Draft, and Plugins. Give it a spin and let us know what you think.

Since our last update we've focused on speed, reliability, and a few more model options. Here's what's new.

⚡️ A faster, more responsive Sudowrite

This week we made the Sudowrite web app load faster and feel snappier, especially on lower-end devices and slower connections. We optimized things so that both the homepage and the editor start up quicker, and you spend less time staring at a loading screen. Even scrolling now uses 60% less of your computer's processing power than it used to!

🆕 More model options: GPT-5.6 (Sol, Terra & Luna)

We've added OpenAI's newest GPT-5.6 model suite—Sol, Terra, and Luna—to Sudowrite, giving you even more AI model options so you can find the voice and style that fits your story. Try them today in Write, Draft, or your very own Plugins.

💬 Smoother, more reliable Chat & editing

We resolved a handful of issues you reported with Chat to help make it a better writing partner.

• Edits insert more reliably - We reworked the flow that applies AI rewrites into your document, so approved changes land where they should far more consistently.
• No more code or "thinking" text - Chat will no longer blurt out its internal reasoning or stray code in its replies.
• Streamlined conversations - Prose analysis and change descriptions now read naturally in the conversation instead of showing up as boxes in the chat. Chat will no longer derail a planning discussion just because you mention a chapter number.

✍️ Draft improvements

We fixed an issue where chapter prose could stop generating after the first scene (or in some cases, after 8+ scenes), and improved how Draft handles longer scene instructions so generations consistently complete as expected with all Prose Modes. If you do encounter an issue with Draft when using an experimental AI model (like the new GPT-5.6 suite), please submit a bug report so we can fix that.

🛠️ Even more improvements & fixes

• Story Bible now stays put - We tweaked Story Bible so that it stays open or closed based on your preference, rather than popping open on hover.
• Clearer sidebar icons - We’ve added more descriptive icons for the collapsible columns on either side of the editor, making it easier to restore your documents, history, or chat from a collapsed state. We also fixed a bug with resizing the editor when those are collapsed.
• Dark theme chat toggle visibility - We fixed an issue where the Chat Only / Allow Edits toggle in Chat was hard to read in dark themes.
• Selection menu clipping - We fixed a longstanding issue with the menu that appears when you highlight text, where if it was too long (or your screen was too small) it was clipped by the editor’s frame. It will now extend beyond the edge of the editor if necessary.
• Unpublish shared documents - We resolved a document sharing issue that prevented the ••• (more) menu from opening. That means you can once again unpublish a previously shared link.
• Trait text entry fix - We fixed an issue that was causing lag or text deletion while typing in Character and Worldbuilding trait fields.

We’ve got even more on the way. Keep the feedback coming!

Hey folks! The team has been busy, and we’ve got a whole bunch of exciting new features and fixes to share with you.

🆕 Claude Sonnet 5 is Here!

Anthropic just released Claude Sonnet 5, their most powerful Sonnet-class AI model yet, and we just added it to Sudowrite.

Sonnet 5 delivers quality approaching Anthropic's flagship Opus 4.8—with notably sharper instruction-following—at a much more reasonable credit cost. That makes it a strong everyday choice for authors looking for great prose and strong instruction-following. Try it now in Write, Draft, or Plugins, and be sure to let us know what you think!

**🆕 **Export an Entire Folder at Once

We just added an option to export a whole document folder in one click. Now when you click on a folder’s three dot (•••) more menu inside of a project, you have the option of exporting all of the documents in that folder as a .zip or as a single (merged) .docx file. This makes it easier than ever to export just what you need—a single file exclusively containing your entire final manuscript, or a .zip file of the supporting research you’d compiled with help from Chat.

🆕 Accessible Document Reordering

We made it so that you can reorder your document list using your keyboard. While holding Alt (Windows) or Option (Mac) use Up/Down to reorder, Right to nest an item inside a folder, and Left to move it back out. It’s faster than dragging and fully screen-reader friendly, with each move announced as you go.

Recent fixes

Use the Sudowrite mobile app on either iOS or Android?We just released an update that resolves some widely reported loading issues and persistent crashes. Please update your app to the latest version: 2026.26.16.

Other fixes include:

• Write Guidance Persistence - We fixed a Write (Guided) bug where dismissing the custom prompt menu by clicking outside the field could delete your guidance. Your in-progress prompt will now persist until you choose to change or submit it.
• Stale Browser Bug - We fixed an issue where the editor might display an unusual “Cannot Get” error in a stale browser tab. Refreshing fixed it—but now you don’t have to.
• Too Many Comments Fix - Feedback made it possible to receive hundreds of comments on a single document, which could result in performance issues such as freezing. We’ve resolved this issue by changing how comments load. They now appear in batches as you scroll.
• Feedback Text Preservation - We fixed a Feedback bug where leaving the page or switching chapters could make manuscript text appear missing when you came back. Your chapter text will now remain visible.
• Comment Allow Edit Bug - When asking @Sudowrite for help in comment replies, the response would sometimes mistakenly suggest you need to toggle your Chat mode to Allow Edits. We’ve fixed that, and you can tag away to get help without interruption now.
• Series Chat History - We fixed a bug where your Chat history from books later in a large Series folder could be missing. Series-level chat retrieval will now include books beyond the first 16.
• Quick Edit Usability - We fixed Quick Edit layout and readability issues where buttons could overlap and highlighted text could be hard to read in some themes. Quick Edit suggestions should now be easier to review and accept.
• Draft Generation Fix - We fixed a Draft generation bug where failed or partially completed scene output could still charge estimated credit amounts. Partial or failed scene generations will no longer cost the same as successful complete generations.
• Import Novel Character Detection - We fixed an import issue where Sudowrite could detect Worldbuilding but silently miss Characters in some cases. The Import Novel flow will now retry rather than producing zero Character cards.
• …and a whole bunch more!

Most of these fixes and improvements are a direct result of your feedback. Thank you—and please keep it coming!

Still reading? You must love Sudowrite. We love you too, so here’s a chance to be among the first to try our new Style Guide feature.

We’ve got a huge update for you this week, with a few headline items below you definitely don’t want to miss.

Excellent Credit Efficiency

Earlier this week we launched Ballad 1.1, Sudowrite’s very own new AI model powering the Excellent Prose Mode. The response has been incredible, with many of you saying it has quickly become your daily driver. There was constructive feedback too, however—primarily that the credit cost of generating multiple Write cards could really add up (especially with big Story Bibles or longer chapters linked in continuity).

Based on that feedback, we made some key changes to how Excellent works. The result? You’ll now save up to 70% on credit costs when generating multiple Write cards with Excellent. The more cards at once, the bigger the savings.

Improved Plugin Editor

If you’ve ever clicked “Create Plugin” in the More Tools menu, you know how simple that first step is—say what you need, and Sudowrite builds it for you. Finalizing your custom writing tool in the editor was less intuitive though, so we just launched an improved Plugin editor that dramatically simplifies the process.

We’ve done away with a complex table of variables, and made it easy to pick from a selector which story inputs you want your plugin to use. New input fields will appear below the Plugin Instructions only for the story inputs you want your plugin to use—so you can force someone to select at least a hundred words to use it, or increase the limit so your Plugin can read a complete manuscript.

Updates to our documentation, including a video walkthrough of this new Plugin creation flow, are coming very soon!

Other Improvements

Claude Opus 4.8 - We’ve added Anthropic’s latest, “greatest” AI model to Sudowrite. Early reviews suggest improvements in prose quality, instruction-following, and consistency across longer outputs—but feedback differs based on genre. Try it out now in Write, Draft or Plugins.

Model Context on History Cards - Can’t remember if you used Opus 4.7 or 4.8 on that last Write click? We just added a new Model chiclet to the Write and Draft cards that appear in your History column, so you’ll always know which AI model wrote the card in question.

Chat Web Research - We heard your feedback that Chat being able to search the web would be a game changer, so we gave it the ability to do so. You can now ask Chat to go research and synthesize things from the internet. Try it with genre conventions or trope data.

Fixes

Rewrite Error Fix - We fixed an issue earlier this week that caused some of you to get a “Something went wrong” error when trying to use Rewrite.

Word Count While Drafting - The word count was not updating consistently while the Draft tool was generating chapter prose. We fixed that and it now gives you a much better real-time picture of your document length during generation.

POV Persistence - We fixed an issue where, after manually setting the chapter POVs in your Story Bible’s Outline, refreshing the page or navigating away could result in those being reset. Your POV will now persist as intended.

Chat History Cutoff - We fixed a bug that was preventing people with very long chat exchanges from scrolling all the way back to the beginning of their chat thread.

More Menu Dismissal - Clicking the three-dot (•••) More menu on a History card would expand a menu with a delete option that could not be dismissed. We fixed that and made it easier to dismiss that menu if you didn’t want to delete your History card.

Large Project Duplication - Projects with over 150 documents could get stuck during the duplication process, but still display a “success” message. We fixed that so large projects work as expected now, but also, if a duplication fails the message is now correct.

Thanks as always for bringing these issues to our attention. Keep the great feedback coming!