Reverie LogoReverie
KarakterCeritaFiturKreatorBlog
MasukDaftar
Dokumentasi
Dokumentasi

Welcome to Reverie

Thoughtful AI character platform. Chat, write, build, earn.

See what shipped this week →
Reverie documentation

Start here

Getting started
Getting started
Account setup
Your first conversation
Finding characters
Importing your history
Glossary

Chatting

Chatting
The chat screen
Side panel & settings

Steering a reply

Slash commands
Guiding a reply
Reply suggestions
First-response enhancement
Reasoning mode
Comparing two replies

Shaping the conversation

Personas
Scenarios
How memory works
Forking conversations
Group chats
Proactive messages

Managing your chats

Managing conversations
Sharing a conversation
Troubleshooting chat

Voice, images & video

Voice, images & video
Voice, images & video
Voice calls
Reading messages aloud
Voice Studio
Generating images
Image to video
Stickers

Worlds & long-form

Worlds & long-form
Worlds & long-form
World Books

Stories

Story mode
Writing a story

Novels

Novel mode
Directing prose
Writing styles
Chat to novel

Creating characters

Creating characters
Creating characters

Three ways to build

Character quick start
Conversational builder
Visual builder
Importing characters

Making it good

Writing a character
Advanced settings
Prompt fields
Preset personas
Image guidelines

Shipping it

Test drive
Publishing a character
Reviews & creator notes
Plugins
Plugins
Using plugins
Creating plugins

Community

Community
Community
Discovery
Moments
Hashtags
Collections
Following creators
Scene snapshots
Safety & reporting

Earning

Creator hub
Creator hub
Becoming a creator
Revenue streams
Direct support
Withdrawals
Creator analytics
Creator posts
Creator messages
Campaigns
Bounties

Your account

Account
Account
Your profile
Security
Content preferences
Appearance
Notifications
Data & privacy
Reports & appeals
Getting help
Billing
Billing
Subscriptions
Credits
Referrals
Gift cards & codes
Rewards
Rewards
Daily check-in
Lucky draw
Achievements
Titles, frames & themes
Reverie Wrapped

Beyond the app

Integrations
Integrations
Reverie Labs
Discord bot
Telegram bot
Open API
API keys

Reference

Reference
Reference
Models
Choosing a model
Free models
Limits
Keyboard shortcuts
Reverie LogoReverie

Platform obrolan & roleplay karakter AI. Impikan, ciptakan, obrolan dengannya.

Twitter·Discord·Tentang·Kontak

Produk

FiturTemaAI RoleplayIde RoleplayAI RPGChat AI dengan MemoriKarakterCeritaKoleksi pilihanMomenKenanganPembuat Karakter AIPencipta Karakter VisualWorld BooksPlugin AI RoleplayMode CeritaPenulis Novel AIChat ke novelTantangan KarakterPencapaianReverie Wrapped

Jelajahi

Obrolan AI NSFWChat AI Tanpa FilterPacar AIPacar AI (Pria)Teman AIGrup Chat AIPersona AIPanggilan Suara AIKloning Suara AIModel AIPercabangan ObrolanSlash CommandGenerator Cerita AIAI yang Menyapa DuluanPesan Tak TerbatasHashtagKreator

Bandingkan

Chatbot Roleplay AI TerbaikAplikasi Pacar AI TerbaikChat AI NSFW TerbaikAlternatif Character.AIvs Character.AIvs Janitor AIvs Chai AIvs SpicyChatvs Crushon.AIvs Polybuzz.AIvs Chub AIvs SillyTavernvs Talkie AIvs AI Dungeonvs Replikavs Moematevs Figgs AI

Sumber Daya

PanduanGlosariumUntuk KreatorAPI karakter AIImport KarakterPengimpor riwayat chatFAQBlogChangelogStatusHargaBot DiscordBot Telegram

Kategori

  • Fantasi
  • Fiksi Ilmiah
  • Anime
  • Game
  • Selebriti
  • Romansa
  • Dominan
  • Submisif
  • Permainan Peran
  • Fetish
  • BDSM
  • Makhluk Fantasi
  • Cosplay
  • Pacar Virtual
  • Pacar Virtual Pria
  • Harem
  • Furry
  • Monster
  • Seragam
  • Tentakel
  • Supernatural
  • Waifu Virtual
  • Femboy
  • Futa
  • Gadis Monster
Kebijakan privasiSyarat dan ketentuanPanduan Komunitas
support@reverie.im
651 N Broad St, Suite 206, Middletown, DE 19709, USA
© 2026 Reverie. All rights reserved.
Conversations

Reasoning mode

See a model think before it answers, and know which models can.

Some models can work through a reply before writing it — planning a scene, keeping a mystery consistent, deciding what a character would actually do. Reasoning mode turns that step on and shows it to you in a collapsible pane above the reply.

Which models can reason

ModelMultiplierReasoning
DeepSeek V4 Flash0.3×Optional
MiMo V2.50.3×Optional
DeepSeek V3.20.5×None
GLM 5.3 Flash0.5×Always on
DeepSeek V4.1 Flash0.7×Optional
DeepSeek V4 Pro0.7×Optional
DeepSeek R11.0×Always on
GLM 4.71.0×Optional
Gemini 3 Flash Preview1.2×None
GLM 51.3×Optional
Llama 3.1 8BFreeNone

GLM 5.3 Flash and DeepSeek R1 always think before replying and cannot be talked out of it. DeepSeek R1 also has no tool use, so tool-driven plugins won't run on it. GLM 5 and Gemini 3 Flash Preview are advanced models and need a subscription. Full model reference

Turning it on

Side panel → Settings → Replies & Generation → Reasoning Mode, then Enable Reasoning.

The row only exists when the model you're currently on can reason. On an always-on model it's there but locked, reading Reasoning Always On.

The setting is scoped to This device and remembered per model, and it starts off. Switch models and you're back to that model's own setting, not the one you just left.

There is no reasoning toggle in the model picker. The picker has a Reasoning filter chip for narrowing the list and a Reasoning capable badge on the models that qualify. The switch itself lives in chat settings.

Reading the pane

A reasoned reply arrives with a pane headed Reasoning — Reasoning... while it's still coming in — above the reply text. Expand reasoning and Collapse reasoning open and close it.

The pane is collapsed by default. The last message follows your auto-expand setting; older messages keep whatever state you left them in.

Two settings control it, both under Side panel → Settings → Chat Experience, both scoped to This device:

SettingToggleDefault
Reasoning PaneShow AI Thinking ProcessOn
Auto-expand ReasoningAuto-expand for New MessagesOff

Turn Show AI Thinking Process off if the model's analysis spoils the scene for you — the model still reasons, you just don't see it. With auto-expand off, the waiting indicator reads thinking… rather than typing… while the model works.

What it costs

Reasoning tokens are billed as ordinary completion tokens, at the model's own multiplier. There's no separate reasoning rate and no surcharge.

What does change is volume: a model that thinks first writes more tokens and takes longer to start answering than the same model without it. How much more depends entirely on the model and the scene, so watch your credit balance for the first few replies after switching it on rather than budgeting from a fixed number.

Related

  • Choosing a model — which model to reason with in the first place
  • Models — capabilities and multipliers for every model
  • Side panel & settings — where both reasoning settings live
  • Credits — how a reply turns into a charge

On this page

Which models can reason
Turning it on
Reading the pane
What it costs
Related