Frequently asked

ChatGPT only gives you OpenAI models. Claude.ai only gives you Anthropic. Faceb.ai gives you both, plus Gemini, Llama, DeepSeek, Grok, Mistral, Qwen and 100+ more — all from a single subscription, with one consistent UI, history, memory, web search, image generation and a developer API.

Yes — durable facts about you (your role, preferences, ongoing projects) get summarised after each chat and injected into every future conversation. Plus a custom-instructions field every model reads. Both are editable and clearable from your account page.

Toggle the globe icon in the composer and your message goes out with live web-search results prepended to the model. Works on every model in the catalog — even ones that don't support native tool use.

Pick Gemini Flash Image, GPT-Image, or any image-output model from the picker, send a prompt, and you get an image back. Drop in a photo first and you can ask the model to edit it. Same wallet as text — about 250 images/month on the Pro plan.

The paperclip accepts images (8 MB each), PDFs, text and code files. Non-image attachments get extracted to plaintext server-side and inlined into the user message — so even text-only models like DeepSeek or Llama can read your PDFs.

Mic button dictates your message. The 🔊 button on each reply reads it back. Conversation mode chains the loop hands-free. Works in Chrome, Edge, Safari, and Firefox.

Account → Scheduled. Save a prompt with an hourly / daily / weekly cadence in your local timezone. We auto-fire it as a new chat when due — same as ChatGPT's Tasks feature, but you get to pick any model in the catalog.

Faceb.ai talks to each provider's official API on your behalf. Your messages aren't used to train any model and we never see them in plaintext beyond what's needed to route the request.

Click the share icon in any chat and you get a clean read-only link you can hand to anyone — they don't need an account. Or download the chat as Markdown from the conversation menu.

Absolutely. Llama 3.3 70B, Mistral Small 3.1, Gemini 2.0 Flash and DeepSeek V3 are a fraction of the cost of GPT-4o and Claude Opus but get most day-to-day jobs done. Save the heavy models for when you actually need them and your token pool lasts much longer.

A token is one unit of inference. Cheap models like Llama 3.3 70B or DeepSeek V3 burn a few hundred tokens per message; frontier models like Claude Opus or o3 burn tens of thousands. The Pro plan's 15M-credit pool covers about 3,900 GPT-4o messages or 39,000 GPT-4o-mini — pick the right model per turn and the pool stretches further. Every assistant message shows the exact tokens charged.

Pro plan: your monthly pool refills on each renewal — unused tokens do not roll over. Top-up packs do stack and stay until you spend them (or your plan lapses).

The composer tells you before you send a message that's too expensive. Pick a cheaper model, buy a top-up, or wait for your renewal. We never silently fail or downgrade your model.

Open your account page and click “Cancel subscription”. You keep Pro access until the end of your billing period; nothing else is required.

7-day money-back guarantee on your first Pro subscription charge. Top-up packs are non-refundable once tokens have been consumed.

Yes. Your account, chat history, and saved bots stick around. To keep chatting after your Pro tokens run out, top up a token pack or re-subscribe.

Yes — it's OpenAI-compatible (POST /v1/chat/completions) and uses the same token balance as your chat account, so one wallet covers both. See the docs →