See the latest features, improvements, and product updates
Our Halloween party has begun and you are invited!
Meet the official guests, bring your own characters, or just come to play.
10 annual I'm All In subscriptions are up for grabs!
The party runs until Nov 2.
Hi everyone,
A new model has arrived on SpicyChat: MiMo V2.6 Pro
MiMo V2.6 Pro is a huge 1 trillion parameters model that has a natural, lively writing voice that brings characters and stories to life. Here's what it's good at:
✍️ Natural dialogue: conversations sound like real people talking, not a script.
😄 Banter and comedy: quick wit and sharp comedic timing that make scenes fun.
🎭 Characters stay true to themselves: it holds onto personalities, quirks and the small details from a character's description.
🚀 Story momentum: it moves the plot forward on its own with new events, reactions and twists, so you don't have to steer every step.
🔁 Fresh phrasing: less repetition and fewer recycled lines, so replies feel new each time.
🌍 Rich worlds: it weaves in lore and setting details well, so fantasy and adventure worlds feel lived-in.
Best for: character-driven roleplay, adventure and fantasy stories, and scenes with multiple characters.
How to try it: open any chat, tap Change Model, and select MiMo V2.6 Pro.
Not on I'm All In yet? Upgrade to unlock MiMo V2.6 Pro along with the rest of our top models.
Upgrade Now
Give it a try and let us know what you think!
Hi everyone,
Here’s what’s new this week.
📚 Lorebooks are now available for Group Chats
You can now attach one Lorebook to any Group you create.
Use your own Public or Private Lorebook, or attach a Public Lorebook created by someone else. The Lorebook is shared across the Group, so every chatbot can use the same world, story, and details during the conversation.
A chatbot’s own Lorebook will still work alongside the Group Lorebook whenever that chatbot is responding.
You can attach, replace, or remove a Group Lorebook anytime from the Group editor.
🔎 Introducing Narrow by Feature
Characters can now use a lot more than just tags, so we’re making it easier to find exactly what you’re looking for.
The new Narrow by Feature filter lets you quickly find characters with features such as:
We’ll keep expanding this as more features become available.
🏷️ Your active filters are easier to see
A small but useful improvement: your selected and excluded tags now stay visible at the top of the results.
No more opening the filter panel just to remember what you selected.
🔍 Search Lorebooks by creator
Looking for Lorebooks from a particular creator?
You can now search using their username and find all of their available Public Lorebooks.
📱 Better Android performance
We’ve also made several performance improvements to the Android app, especially for lower-end devices, for a smoother and more responsive experience.
That’s it for this week. More is already cooking behind the scenes. 💜
We’re excited to finally release Public Lorebooks.
Until now, Lorebooks were private and only available for your own use. Starting today, you can publish them, share them with the community, and use Lorebooks created by other people.
Your character can only keep so much information in active memory at once.
A Lorebook lets you store extra information about your world, characters, locations, relationships, rules, backstory, or anything else you want the AI to know.
Each entry can have its own keywords. When one of those keywords comes up in the conversation, the relevant Lorebook information is automatically added to the context.
So instead of stuffing everything into your character’s persona, you can keep a much larger world in a Lorebook and only bring in the information when it’s actually needed.
Pretty much the same kinds of things you already do with Chatbots:
🌍 Publish and share your Lorebooks
Set a Lorebook to Public, submit it for review, and once approved, anyone can discover and use it. You can still keep any Lorebook Private if it’s just for you.
🔍 Discover Lorebooks made by other creators
Open Lorebooks from the menu to browse what the community has created. You can search, filter by tags, sort through them, and view all of the entries before attaching one.
🔗 Attach them to your Chatbots
You can attach a Lorebook directly from its profile or from the Chatbot editor. Choose from My Lorebooks, Favorites, or Discover.
❤️ Save your favorites
Found one you want to use later? Favorite it and you’ll find it under Favorites → Lorebooks.
👀 See which Lorebook a Chatbot is using
Chatbot profiles now show the attached Lorebook. Public Lorebooks can be opened and explored, while Private Lorebooks only show their name.
📖 Full guide:
Learn More
Public Lorebooks are live now. Go explore what the community has built — or start building your own world. 🗺️💜
Here’s what we’ve been working on the past few weeks.
We’ve upgraded our TTS engine to improve voice quality and make conversations sound smoother and more natural.
Give your favorite voices a try and let us know how they sound!
We’re also actively working on some pretty cool new features. A few of them are already being tested by our incredible Beta Testers, and we’ll have more to share as they get closer to release.
We’re already getting ready for our Halloween Contest next month.
So start gathering your ideas on Halloween themese characters now — there’ll be yearly subscriptions up for grabs for the winners. More details soon. 👻
We’ve now published 110 help and solution articles covering many of the most common questions, issues, and how-tos on SpicyChat.
You can browse them anytime here:
https://support.spicychat.ai/support/home
That’s it for this week. Thanks as always for your feedback, reports, and for helping us keep making SpicyChat better. 💜
Last week, we introduced 32K context memory for I’m All In users on GLAM Arcturus and Default, with plans to bring it to more models soon.
We’ve since added more capacity, which means we’re now ready to expand 32K support to several more models:
That means you can now enjoy more of your favorite models with double the context, helping them keep track of more of your conversation, story, and character details.
One thing to keep in mind: double the context also means significantly more resources per generation. We’ve added more capacity to support this, but some models may still respond a little slower during peak hours over the next few weeks when dealing with traffic surge.
So if a model feels too slow at peak times, we recommend trying another model and switching back later.
Enjoy the extra memory and enhanced roleplays. 🧠💜
A quick reminder that our new subscription pricing will take effect on September 8 at 10:00 AM EST as announced last week/
If you subscribe before the new pricing goes live, you’ll lock in the current recurring price and continue paying that price for as long as your subscription remains active on the same tier.
If you’re already subscribed, your current price will not change as long as you keep your subscription active.
You can read the full details and FAQ here
And yes — we’re also working on bringing 32K context to more models very soon. 🧠💜
32K context is now available for I’m All In users.
Until now, the maximum context memory on SpicyChat was 16K. We’ve now doubled that to 32K, giving supported models much more room to remember what happened earlier in your conversation.
In simple terms: if a 16K limit could keep roughly 100 previous messages in context, 32K could keep around 200. That is 8x more memory than Get A Taste tier.
That’s just an example — the actual number varies depending on how long your messages are, your character’s persona, user persona, and everything else the model needs to keep in context.
The result? Longer roleplays with more of your story still in memory.
32K is currently available on Default, and Glam Arcturus, and we’ll be bringing it to more models over the next few weeks.
You can learn more about context memory here
One more reminder 💜
Our new subscription pricing goes into effect on September 8.
If you subscribe before September 8, you can lock in the current recurring price and keep it as long as your subscription remains active on the same tier.
So if you’ve been thinking about trying I’m All In and the new 32K context, there are only a few days left to lock in the current price.
Upgrade To 32K Context Memory
32K is live now. Go give it a try. 🔥
Note: if you don't see it: make sure to log out and back in again.
Hi everyone,
Over the past three years, SpicyChat has grown significantly. We've introduced more capable models, longer context, image generation, voices, memory improvements, Group Chat, Lorebooks, creator tools and much more, while keeping a large part of SpicyChat free.
Throughout that growth, our subscription pricing has stayed largely the same. However, the cost of running AI models and the GPU infrastructure behind SpicyChat has increased substantially over the last year.
To keep SpicyChat sustainable and continue investing in better models, larger context (32k is on the way) and new features, we're updating our paid subscription prices on September 8.
The most important part
If you already have an active recurring subscription, your price will not change. As long as your subscription remains active on the same tier, it will continue renewing at the price you pay today.
New monthly pricing from September 8
What this means for you
Until September 8, free users can subscribe at the current price, and existing subscribers can change to another tier at current pricing. The price for the selected tier will remain locked as long as your subscription stays active.
Tier changes made after September 8 will use the new pricing.
For details about annual plans, cancelled subscriptions, non-recurring payment methods and other scenarios, please see our FAQ:
View FAQ
We know a price change isn't welcome news, and we don't take it lightly. We're announcing it in advance so everyone has time to understand their options.
Thank you for supporting SpicyChat and helping us continue improving the experience. 💜
Qwen Plus Character is now available again for I’m All In users.
We temporarily removed the model after identifying issues that were preventing it from running as efficiently and reliably as expected. We’ve now completed the necessary optimizations and brought it back online.
Qwen Plus Character was built for extended roleplays, with a strong focus on character consistency, long-form continuity, and staying true to the tone and personality of your character. It’s especially good at following the direction of a story over longer conversations, handling darker or bolder themes, and keeping dialogue natural and in-character.
We know many of you fell in love with the model and made it your daily driver, so if you’ve been waiting to get back to it, it’s ready to use again.
Thanks for your patience while we worked on it. 💜
