Knowledge base Money and extras
Nymbot
An AI assistant built into the app. Free in public channels, paid in a private encrypted chat.
Nymbot in channels
Anything beginning with ? in a channel goes to Nymbot, and it answers in the
channel where everyone can see it. You can also write @Nymbot in an ordinary
message, or quote-reply to one of its answers to keep the conversation going — it
carries up to six messages of the reply chain as context.
It is context-aware: ?ask and ?summarize receive the channel's recent
messages and its active user list, so it can answer questions about the conversation that is
actually happening rather than in the abstract.
A message sent with Send anonymously can ask Nymbot too, in all the same ways. Nymbot is then asked as the message's throwaway nym, not as you, and answers in the channel like any other time. It needs the internet: a channel that is only on the Bluetooth mesh cannot reach Nymbot, and the app says so instead of asking.
The full list of commands is in the command reference.
Nymbot runs on hosted infrastructure, so it only exists on the official site and the official apps. A copy of the web app you serve yourself has every other feature and no bot.
The private chat
You can also have a one-to-one, end-to-end encrypted conversation with Nymbot, exactly like a private message with a person. Nothing you say there is visible in any channel.
The same private assistant is published as a standalone app at nymbot.ai, without the messenger around it. It is the same account: sign in with the same key and your credits, your conversations and your throwaway key are already there.
Private replies are a paid feature. ?help inside that chat is free, handled on
your own device, and explains the tiers, the pricing and the setup.
Credits
Two separate balances, both bought with Bitcoin over Lightning:
| Balance | Price | Spent on |
|---|---|---|
| Standard credits | 10 sats each | Standard replies, auto-routed to whichever model suits the task |
| Pro credits | 100 sats each | Replies from a specific frontier model you have pinned |
?balance— both balances. They are also shown in the chat header.?buy— opens the purchase flow, with a Standard/Pro switch.?gift @nym— gives credits to someone else.?transfer @nym— moves your whole balance, standard and Pro, to another nym.
Anonymous mode
The private chat is end-to-end encrypted, but Nymbot still knows which pubkey is talking to it: the credit balance it charges, the conversation thread it keeps and its own archived copy of the exchange are all filed under your nym. Anyone holding the bot's private key could read that off.
The Anon chip in the chat header — or ?anon — moves
the whole conversation onto a throwaway key generated on your device, the same trick
group chats use for their rotating recipient keys. Nymbot
bills that key, answers it and archives it, and never learns your nym. Replies stay
hybrid post-quantum, and read receipts, typing
indicators, reactions and edits to Nymbot are held back while it is on, since each would
otherwise put your real signature beside the same conversation.
Credits reach the throwaway key as blind vouchers rather than a transfer,
which would rebuild the link the mode exists to break. Your app blinds a random secret,
Nymbot debits your nym and signs what it cannot see, and the throwaway key later presents the
unblinded voucher for Nymbot to verify and credit — with nothing to match it against.
Each signature carries a proof that the published signing key was used, which your app checks
before spending. You can also skip the move and buy credits straight onto the throwaway key
with ?buy.
?gift and ?transfer stay on your real nym, since both are about your
named account. Credits on a throwaway key live and die with that key: it is stored under
identity encryption, syncs to your other
devices, and a panic wipe takes it and any credits
left on it.
Pro models
?model <name> pins every reply to one specific model; ?model off
returns you to standard routing. ?model on its own lists them with their prices.
Available: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Haiku 4.5, GPT-5.6 Sol, GPT-5.4 mini, Gemini 3.1 Pro, Gemini 3.6 Flash, Grok 4.6, Kimi K3, Qwen 3.5 and MiniMax M3.
A Pro reply costs a per-model base of one or two credits and then scales with the length of the reply, up to a per-model maximum. The maximum is reserved when you send the message and only the actual cost is charged, so a short answer costs the base even though a long one was budgeted for.
When a model shows its chain of thought — the standard tier's reasoning route, or a Pro model that exposes it — the reply carries a collapsed 💭 Reasoning section above it that you can tap to read.
You can send Nymbot a picture, too. Every Claude, GPT, Gemini, Grok and Kimi Pro model can see images, as can the creative and translation routes on standard, and will describe one or answer questions about it.
Images and speech
Both are charged per generation rather than by reply length, and nothing is charged if a generation fails.
| Command | Standard | With a Pro model selected |
|---|---|---|
?image <description> | 5 standard credits | 2–3 Pro credits, depending on the generator |
?speak <text> — up to 800 characters | 3 standard credits | 1 Pro credit |
With a Pro model selected you can also choose the generator:
?image --model <name> <description>, picking from Nano Banana Pro,
Nano Banana 2, Imagen 4, FLUX 2 Max, FLUX 2 Pro, Seedream 5 Pro, GPT Image 2, Grok Imagine
and Recraft v4 Pro. ?image models lists them with prices and costs nothing.
Repositories
Working inside a git repository is no longer part of Nymbot in Nymchat. It lives in the Nymbot apps at nymbot.ai.
If you type ?git in Nymchat out of habit, the app catches it on your device and
points you there. Nothing you typed after ?git is sent, so a token pasted by
mistake never reaches Nymbot.