Skip to content
Support

Frequently Asked Questions

Everything you need to know about Thremark. Can’t find an answer? Contact us →.

Product

Marks are Thremark’s memory. Every fact, preference, and reminder it learns about you becomes a mark — a visible memory card. You can see all of them, search, edit, delete, or add your own. Nothing is hidden. Your AI uses marks silently in future conversations to give you personalized answers without you having to repeat yourself.

How it works
  • Mention any fact in a conversation — «I’m vegetarian», «Mom’s birthday is March 5», «I use React at work»
  • Thremark automatically extracts it and creates a mark — you’ll see it in the Marks tab with a category and timestamp
  • In future chats, your marks are loaded silently — ask for a meal plan and it already knows your diet, no reminder needed
  • Edit, delete, or add marks manually anytime — you’re always in control of what Thremark remembers

Thremark is built around one idea: memory that’s visible, editable, and yours. You see exactly what the AI knows about you—and you control it. Add to that native iPhone integration, Smart Routing across multiple models, and one surface for chat, files, search, images, and voice. It’s a different product for a different kind of user.

ChatGPT vs Thremark
  • Memory — ChatGPT: saved memory is largely opaque; you see hints and summaries, not every fact the model may use. Thremark: what the AI learns becomes visible marks—searchable, editable, deletable—so you always know what context is in play.
  • Platform — ChatGPT: a strong cross-platform chat app. Thremark: native SwiftUI on iPhone with deep Apple integration—Siri, Dynamic Island, widgets, Share Extension, Spotlight, and dozens of system hooks—not a generic wrapper around a single web chat.
  • Models — ChatGPT: you use OpenAI’s model lineup inside OpenAI’s product. Thremark: Smart Routing picks the best available model per turn from your vibe (Fast / Smart / Full) and plan—you don’t micromanage provider APIs.
  • Workflow — ChatGPT: conversation-first; other capabilities are layered on. Thremark: chat, structured Files, web search with citations, image generation, and Imprint voice share the same marks-backed context in one product.
  • Privacy & training — Both send prompts to LLM providers to generate replies. Thremark does not use your content to train its own models and does not sell your data (see the dedicated FAQ on training below).
Other AI apps vs Thremark

Other assistants may remember things too, often as an opaque summary. Thremark is built around marks—every saved fact is visible, searchable, and editable. Typical vendors vary; this table shows our product shape. A dash (—) means rarely or not at the same depth as native Thremark.

Other AI apps
Thremark
Memory you can see and edit (marks)
Full-duplex voice with memory (Imprint)
Vibe Code (Mac · Q4 2026)
Image generation
Web Search (live web in chat)
File analysis & structured files
Siri & Shortcuts
Widgets & Dynamic Island
Cross-device sync
On-device processing where applicable

Files are structured documents your AI creates for you — plans, lists, summaries, trackers. Say «make me a weekly plan» and it’s a file. «Track my expenses» — another file. Everything is named, searchable, and always one tap away. You don’t need a separate planner or note app.

How it works
  • Ask Thremark to create something structured — «make me a weekly workout plan» or «track my monthly expenses»
  • A named file appears in your Files tab — formatted, organized, and ready to use
  • Open it anytime to view or edit — or ask Thremark in chat to update it («add yoga on Fridays»)
  • Because Thremark knows your marks, files are personalized from the start — a meal plan respects your diet, a travel checklist knows your destination

Vibe Code is Thremark’s Mac builder: describe a site, app, or automation in plain language and get real code with a live preview. No coding background required. The experience is intentionally simple and native — fewer surfaces than juggling a full IDE and a chat panel, with UI polish aimed at shipping, not demos. Launching on Mac in Q4 2026.

How it works
  • Describe what you want — «landing page for my studio with booking and pricing»
  • Thremark writes code and shows a live preview — you watch it take shape
  • Refine by talking — «tighter typography», «add a dark mode toggle» — no manual file juggling
  • Deploy when it’s ready — you own the code, no platform lock-in

Yes. Logos, mockups, icons, pitch visuals — and everyday stuff too: a portrait, a card for someone, a picture in a style you like. It generates images right in the chat. Available on all plans.

How it works
  • Describe what you want — professional («app icon, flat, two colors») or personal («portrait, natural light, warm tones»)
  • Thremark generates the image right in the chat
  • Iterate — «softer background», «more contrast», «try black and white» — until it feels right
  • Save to your device, or take the concept to Vibe Code if you’re building something bigger
Technical details
  • Image quality improves with higher plans.
  • Limits — Free: 100/mo. Plus: 600/mo. Pro: 800/mo.

Voice AI (Imprint) is a real-time voice conversation on iPhone. Imprint is hands-free duplex audio with your marks. It listens, understands context from your marks, and responds with voice. Audio streams in real time to a low-latency voice model. Your full memory context is available during the conversation. On the web app, you can use the browser microphone for speech-to-text input into chat; full Imprint is iOS-only.

How it works
  • Tap the microphone icon in any chat to start a voice session
  • Talk naturally — Thremark listens in real time and responds with voice, using your full memory context
  • Everything you can do in chat works by voice — save facts, create files, search the web, ask questions
  • End the session anytime — new marks and files created during the conversation are saved automatically
Technical details
  • Providers — Generic assistants: often push-to-talk or text-only. Thremark Imprint (iOS): duplex streaming to Gemini Live or OpenAI Realtime with your marks in the same session context as chat.
  • Web — Browser microphone sends speech-to-text into the chat input; full duplex Imprint with streamed audio is iOS-only.
  • Storage — Voice audio is processed by the provider for the reply and is not stored on Thremark servers as a recording (see Privacy).

You don’t pick AI models in Thremark — you pick a vibe. Fast gives instant answers. Smart thinks deeper. Full uses maximum power. Thremark routes each message to the right model automatically. One simple choice.

How it works
  • Choose a vibe — Fast, Smart, or Full — instead of picking a provider or model name
  • Each message is routed server-side to the best available model based on the task, your vibe, and your plan
  • Your marks and chat context travel with the request — the model choice changes; your memory does not
Technical details
  • Control — Many apps: one vendor, one model. Thremark: one vibe control; routing picks the right engine per request so you never micromanage APIs.
  • Plans — Free emphasizes Fast; Plus unlocks Smart; Pro unlocks Full and the highest routing tier (see next question).

Your plan changes not just how much you can ask, but how the answer gets generated. Fast mode, available on every plan, is optimized for speed — instant, capable, always responsive. Smart mode activates reasoning-capable models that think before answering. Full mode, exclusive to Pro, routes your request to the highest available tier: deeper reasoning, broader creative range, stronger output on complex topics. In practice: the same question will produce a noticeably stronger answer at a higher plan — not more words, but sharper reasoning. It happens automatically. You don’t request it.

What each tier gets
  • Free — Fast mode: speed-optimized, instant answers for everyday tasks
  • Plus — Smart mode: reasoning models activate for analysis, nuanced questions, and multi-step tasks
  • Pro — Full mode: highest available model tier across all task types; Deep Reasoning for extended multi-step work
Technical details
  • Model selection happens server-side per request — no visible delay, no user choice required
  • Higher plan ≠ just faster — it means access to more capable models for demanding tasks
  • Routing considers task type, context, vibe, and plan tier simultaneously

Pricing & Plans

Yes. New users get 7 days of Plus free — Smart mode, higher limits, the full experience. No charge during the trial. You can cancel anytime before it ends through your Apple ID settings. After 7 days it continues as Plus unless you cancel.

Yes. The Free plan includes 1,000 messages, 3 hours of voice, 50 marks, 10 files, 30 web searches a day, and image generation — no credit card required. Plus unlocks smarter models and higher limits. Deep Reasoning is exclusive to Pro.

Free gives you Fast mode with generous limits. Plus is $19.99/mo ($14.99/mo billed annually at $179.99/year) and adds Smart mode — thinking models that analyze deeper. Pro is $39.99/mo ($29.99/mo billed annually at $359.99/year) and unlocks Full mode with the most powerful models, unlimited marks and files, and Deep Reasoning. Annual billing saves 25%.

Yes. Cancel through your Apple ID settings (Settings → Apple ID → Subscriptions). You keep access until the end of your billing period. Your marks, files, and chat history stay — nothing gets deleted when you cancel.

Subscriptions are managed by Apple. To request a refund, visit reportaproblem.apple.com or contact Apple Support. We don’t process payments directly.

Share your referral link from Settings. Both you and the person you invite get 30 days of Plus free. There’s no limit on how many friends you can refer.

Not yet. Subscriptions are currently purchased through the iOS app via Apple’s in-app purchase. If you buy Plus or Pro on iPhone and sign in with Apple on the web, your entitlements carry over automatically. Web billing is planned.

Privacy & Security

Your marks, files, and chat history sync to Cloudflare’s edge network using an anonymous device ID — not your Apple ID or email. Voice audio streams to LLM providers (Google, OpenAI, Anthropic) for processing and is not stored by Thremark. Cross-device sync requires Sign in with Apple; without it, data stays local to the device.

No. Thremark works without email, name, or Apple ID sign-in. Your device generates a random anonymous ID — that’s what identifies your data. If you sign in with Apple, it enables cross-device sync and links your subscription entitlements. Apple provides only an opaque unique ID, not your name or email unless you choose to share them. We still can’t see who you are.

Yes. In the iOS app: Profile → Delete Account removes everything permanently — marks, files, chats, and your anonymous ID — from all servers. On web: Settings → Erase Everything removes all local data and server data tied to your device. There is no recovery after deletion.

No. Your conversations are sent to LLM providers (Google, OpenAI, Anthropic) to generate responses, but Thremark does not use your data for any model training. We don’t sell, share, or aggregate user data.

Technical details
  • Providers — Third-party LLMs: each vendor has its own terms for API traffic; Thremark does not add your chats to a proprietary training dataset on our side.
  • Product — Marks and messages are for your product experience only — not sold, not used to train a separate «Thremark model.»

Sign in with Apple enables cross-device sync — your marks, files, and chats become available on all your devices (iPhone, iPad, web). Without it, your data stays on the current device. Apple sign-in is also how subscription management works: if you buy Plus or Pro on iPhone, signing in on web links your entitlements. We still can’t see who you are — Apple provides only a unique opaque ID, not your name or email unless you choose to share it.

Platforms

The web app at thremark.com/app brings Thremark to your browser — no install needed. You get chat with Smart Routing (Fast / Smart / Full), marks, files, live web search with citations, image generation, and speech-to-text — within the same monthly limits as on iOS. Everything syncs between web and iPhone. The only iOS-exclusive features are Imprint real-time voice, Siri, widgets, Dynamic Island, and other native Apple integrations. Paid plans (Plus / Pro) are currently purchased through the iOS app via Apple; web billing is coming soon.

Technical details
  • Stack — Web: Next.js client to the same Worker API as iOS; full cloud sync for marks, files, and chats. Native-only features (Imprint duplex, Siri, widgets, Dynamic Island, etc.) are not available in the browser.
  • Billing — Subscriptions for Plus/Pro currently go through Apple on iPhone; the web app respects the entitlements tied to your account. Web billing is planned.

iPhone and iPad (native SwiftUI app) and Web (thremark.com). A Mac app is in development. The web app works on any device with a browser.

Yes, with Sign in with Apple. Once signed in, your marks, files, and chat history sync automatically across iPhone, iPad, and web — changes appear within seconds. Without Apple sign-in, data is local to the current device. The Mac app will join sync when it launches.

Yes. With Plus or Pro, you can export your chat history as text or PDF from Settings. Your marks can be exported as well.

Thremark’s interface is available in 39 languages. The AI responds in whatever language you write in.

30 native Apple technologies: Siri & App Intents, Dynamic Island & Live Activities, Home Screen Widgets, Share Extension, StoreKit 2, Spotlight, StandBy mode, Focus Filters, Handoff, Alternate App Icons, and more. These aren’t checkboxes — they’re deeply integrated into how the app works with iOS.

Sign in with Apple once on any device. After that, your marks, files, and chat history sync automatically via Cloudflare’s edge network. Changes made on iPhone appear on web and iPad within seconds — no manual export or import needed. The sync happens in the background whenever you’re connected. Voice audio from Imprint sessions is not stored and does not sync.

Not much — the web app has nearly full feature parity with iOS for the core experience: chat, marks, files, web search, image generation, and speech-to-text. The iOS app has exclusive features the browser cannot replicate: Imprint real-time voice (duplex streaming), Siri & Shortcuts, widgets, Dynamic Island, and other native Apple integrations. Think of the web app as Thremark anywhere, iOS as Thremark at its deepest.

Not currently. Thremark is built as a native SwiftUI app, deeply integrated with Apple’s ecosystem — Siri, Dynamic Island, and 30+ native APIs. An Android port would mean a fundamentally different product. The web app at thremark.com works on any browser including Android Chrome, giving you chat, marks, files, search, and image generation on any device.

Still have questions?

We usually respond within a few hours.

← Back to Thremark·Roadmap·About·Contact →·Security·