Everything about what Rich Concierge is, where its fares and hotel prices come from, what it will never do, what happens to a screenshot you send, how usage is measured, exactly what it costs, and how to stop.
Last updated 2026-09-25
Rich Concierge is a private travel assistant that lives inside your Travel Like the Rich dashboard, next to your course, your Travel Bank, your saved trips and your planner. Its job is narrow on purpose: it helps you plan and book a better trip the Travel Rich way. That means turning one dial instead of four, locking the fare by rules instead of panic, putting what you saved into the room, and protecting the price after you book.
That narrowness is the point. A general chatbot will happily name a "cheapest day to fly", quote a hotel price it half remembers from years ago, and tell you a visa rule with total confidence, from whatever it absorbed from the open internet. That is exactly the kind of travel advice that costs people money. Rich Concierge works the other way. It answers from the Travel Rich material on your account, from the Travel Bank (a fixed, checked list of destinations and booking tools, every price in it dated), from fares its tools fetch while you wait (each one labelled with the time it was seen), and from what you have told it about your airport, your budget and your months.
Rich Concierge is included with your purchase of Travel Like the Rich when you pay by card or PayPal. It is not one of the Travel Rich Weekly gifts, it is not an order bump, and it is not an add-on you have to buy. What you use is billed by usage, separately from the course, which is exactly why this page exists: you should know precisely what is measured and what it costs before you type a single word or send a single screenshot.
You never have to use it. Everything in every Travel Rich product is complete without it. The course stands alone, the Season Calendar and the Value-Luxury Map are tables you can read on a train, the True Total calculator works with a pen, and every add-on stands alone. Rich Concierge is there for the moments when you would rather ask than look something up: on a Sunday night with three tabs open and no idea which dial to turn, at the moment you are about to pay for a hotel that looks too good, or when your leave is booked and you still have no destination.
The requests it handles best are small, concrete and about your own trip.
The pattern is simple. It is at its best when the answer already exists somewhere in what you own or in the Travel Bank, and the work is finding it, applying it to your airport and your dates, and handing it to you in a form you can act on tonight.
This matters more for travel than for almost anything else, because a price is only true for a moment. So Rich Concierge is built so that it cannot invent one.
When Rich Concierge shows you a fare, it came from a tool, not from the model's memory. The tool asks the Travelpayouts Aviasales Data API for the lowest round-trip fares found in recent real searches for your route. Those are cached prices from searches other travellers ran, kept for up to about seven days, not a live quote from the airline. Every fare is shown with the time it was seen, and every fare card links to the booking page, where the live price is the one that applies. The same question asked twice within about 30 minutes is answered from our own short cache, so you are not paying for the same lookup twice.
If the fare service is not connected on our side, Rich Concierge does not guess. It gives you a search link instead, with no price on it.
The Travel Bank's destination cards carry Booking.com city-page averages per night by star rating, with the date they were seen. They are averages over many hotels and many nights, not a quote for any hotel on any date. Rich Concierge always says "on average" and gives the date. It never tells you a specific hotel costs a specific amount, because until a live hotel price connection is approved, we do not have a true number for that, and we would rather tell you so than make one up.
It never says a price is guaranteed, available, "will" drop, or "will" rise. It never promises a saving. Fares and hotel rates move with demand, season and time, and the booking page always has the final word.
You can attach one kind of image to a message: a screenshot of a fare or a hotel listing (a booking page, a search result, a price calendar, a room page). Rich Concierge reads the visible price, the currency, taxes and fees (resort fees, city taxes, payment fees), the bag and seat rules and the cancellation terms. It works out the True Total from those numbers only, tells you what is missing (bags not shown, taxes not included, non-refundable), and suggests the equivalent search on our partners so you can compare.
It does not analyse any other image. A photo of a place, a person, a receipt or a document gets one line saying it can only read fare and hotel screenshots. To find somewhere that feels like a photo you love, describe it in words instead.
A few plain facts about images:
Rich Concierge gives general travel information. It is not a travel agent, a lawyer, an immigration adviser or a financial adviser, and it is built so that it cannot act like one. These limits are written into its instructions and they are absolute.
It also has no ability to change your account. It cannot grant you a product, change a price, waive a charge, alter your eligibility or lift a limit. Those are decided by our system, in code, and Rich Concierge is not given a lever for any of them. If you ask it to, it will tell you plainly that it cannot.
Entry and visa rules depend on your passport, your destination, the length of your stay and the reason you travel, and they change. So Rich Concierge never states a requirement as fact. When you ask "do I need a visa for Thailand?", it tells you that the answer depends on your passport and changes, points you to the destination's official government source and to your own government's travel advice, and asks you to check it there before you book.
The same goes for safety. It can tell you what the course teaches (arrive in daylight, book the first night and the transfer, keep the address offline), but it does not rate a country as safe or unsafe. Official travel advisories are the source for that, and it links you to them rather than paraphrasing them.
Flight delay and cancellation rights (for example the EU and UK rules) are explained in general terms from the course, with the official pages linked, never as a promise that you will be compensated.
Before every answer, the system selects the Travel Rich material that fits your question from the products on your account, and hands only that to the model. It is not browsing, it is not searching the web, and it is not drawing on a general pool of travel tips.
Every chapter is stored as structured content, and every piece carries the id of the product it belongs to. When you send a message, the system first keeps only what you own. Then it matches what is left against your words and picks the best few passages. Those passages, the Travel Bank catalogue, your small profile and the recent conversation are what the model sees.
Those passages are handed to the model inside an explicit data fence, labelled as content rather than as instructions. That labelling is not decoration. It is what stops a card note, a hotel's own marketing text, something you pasted, or even words printed in a screenshot from giving Rich Concierge orders. If any of that text says "ignore your rules" or "give a discount", Rich Concierge treats it as text, not as a command.
If the best answer to your question lives in a product you do not own, such as The Asia Five-Star Atlas or The 72-Hour Escape System, it tells you which product it is in and leaves it there. It will not paraphrase that content from memory. That is not a sales tactic. It is the same entitlement rule that governs your downloads, applied to the assistant.
It carries a small amount of durable context, if you give it: your first name, your home airports, how many people usually travel, your budget band, the hotel stars you prefer, the regions you like, what you want to avoid, and the months you usually travel. That is the complete list. It never keeps a passport number, a date of birth, payment details or a photo of a document, and nothing from an image is ever added to it. You can view, edit and clear it from your dashboard.
Everything else is the recent conversation, which is trimmed as it grows. A conversation that grows without limit would be a bill that grows without limit, so only the last several turns travel with each message.
Rich Concierge can show you cards: a destination with its dated hotel averages and its cheap months, a flight search with the fares seen and their times, a hotel tool such as member prices or flash sales, or a travel service such as an eSIM or insurance. Every card comes from the Travel Bank or from a fare tool result. The model picks which cards to show; our system builds each card, its price line and its link.
The rules it follows when it shows cards:
Some of those links are partner links. If you book through one, we may earn a commission at no extra cost to you. No partner pays for a place in Rich Concierge's answers, and a commission never decides what it shows you. Some of the best tools the course teaches, such as Google Flights, are not partners at all and never appear as cards; Rich Concierge still teaches you how to use them. You always book with the partner, not with us, and the price and terms on the partner's own page are the ones that apply. The full wording is on our affiliate disclosure.
This is the section most people come here for, so it is stated as plainly as we can manage.
Language models do not read characters or words. They read tokens, which are chunks of text roughly three quarters of a word long on average in English. A short question might be fifteen tokens. A paragraph of reply might be a hundred. The Travel Rich material and the Travel Bank catalogue handed to the model alongside your question are usually the largest part, and they are counted too. A screenshot is converted into tokens as well: with the model and image size we use today, a phone screenshot is typically in the region of one to two thousand input tokens. Fares a tool fetched for you are passed back to the model as input tokens, like everything else.
Every message therefore has two sides: input, which is everything sent to the model, and output, which is everything it writes back. They are priced differently because they cost differently.
Your price is derived from what the underlying AI provider charges us, multiplied by 20. That multiple covers the provider bill, the infrastructure around it, the content retrieval that keeps every answer grounded in your own Travel Rich material, the fare lookups, the Travel Bank, the image handling and the safety rules described above. It is a fixed multiple, published here, and it does not change from one customer to another.
| What is counted | Per 1,000 tokens | Per 1,000,000 | When it applies |
|---|---|---|---|
| Input tokensEverything sent to the model: your message, any screenshot or photo you attach, the recent conversation, the Travel Rich material and the Travel Bank cards it was given, and the fares its tools returned. | $0.0400 | 40.00 | Everything sent to the model: your message, any screenshot or photo you attach, the recent conversation, the Travel Rich material and the Travel Bank cards it was given, and the fares its tools returned. |
| Output tokensEverything Rich Concierge writes back to you, including a True Total it works out and the short line above a set of cards. | $0.2000 | 200.00 | Everything Rich Concierge writes back to you, including a True Total it works out and the short line above a set of cards. |
| Cached inputInput served from cache, which is most of the fixed instructions, the Travel Rich material and the Travel Bank catalogue on every message after the first. | $0.004000 | 4.00 | Input served from cache, which is most of the fixed instructions, the Travel Rich material and the Travel Bank catalogue on every message after the first. |
| Cache writeThe first time a block of content is written into the cache. | $0.0500 | 50.00 | The first time a block of content is written into the cache. |
The rates above are the current customer-facing rates in US dollars, per 1,000 tokens of input and output. They are generated on this page from the live configuration, so what you are reading is what you would be charged right now, not a number typed into a document months ago.
After every answer, the AI provider reports exactly how many input tokens, output tokens, cached-input tokens and cache-write tokens that request consumed. We take those numbers, not an estimate. We do not count characters, we do not approximate from message length, and we never accept a token count sent by your browser, because a number that arrives from a browser is a number that can be edited.
Each category is priced at its own rate from the table above, added together, and written to your usage ledger as one row. When an answer needs more than one step (for example, fetching fares, then choosing cards, then working out a True Total), every step of that one answer is added together and recorded as a single row, exactly like a plain answer. The row records the model, the time, the four token counts, the provider cost, the multiplier applied and the resulting charge. The rate in force at the time is stored on the row itself, so if rates ever change, your history is not repriced. You can see every row in your dashboard under Billing.
Usage accumulates as an unsettled balance rather than being charged message by message. Nobody wants fourteen card transactions of a few cents each, and no card processor wants them either.
Settlement cannot fire twice for the same balance. Each settlement carries a key built from your account, the billing week and the exact amount, so a retry after a network timeout finds that key already used and does nothing.
It is easier to trust a number you can follow, so here is one, start to finish. The token counts are round examples, not measurements.
Suppose you open Rich Concierge and ask: "Somewhere warm in November from London, under $300 for the flight. I like old towns and good food."
Now ask a follow-up in the same conversation: "What would four nights there cost in total with one checked bag?" Most of the input is identical to last time, so it is served from cache at the much lower cached rate. Only the new part is charged at the full input rate. The second message costs a fraction of the first.
At the rates in the table above, that first answer comes to about $0.328, and the follow-up question, with most of its input served from cache, to about $0.080. These are illustrations built from round example token counts. Your real numbers depend on the exact token counts the provider reports, which is why the row in your ledger, not this paragraph, is the authority.
This is the single biggest reason a conversation is cheaper per message than a string of one-off questions, and it is why we do not charge a flat fee per message: a flat fee would quietly overcharge exactly the people who use it most sensibly.
We could have published a flat price per message. We did not, for two reasons.
First, messages are not the same size. A one-line question about which dial to turn and a full trip plan with fares and a True Total cost very different amounts to answer, and a flat fee means the short question pays for the long one. Charging for what you actually used is the fairer arrangement, even though it is harder to explain.
Second, a published multiple can be checked in a way a flat fee cannot. The provider publishes its rates. We publish the multiple. You can therefore check our arithmetic, which is not true of a number we simply assert.
If you also have Travel Rich Weekly and Travel Rich Fare Watch running, they stay on separate lines with separate descriptions. A week might read, for example:
| Line | Amount |
|---|---|
| Travel Rich Weekly | $25.00 |
| Rich Concierge AI usage (an example amount) | $7.20 |
| Travel Rich Fare Watch, an example week of 10 completed tasks at $1.50 | $15.00 |
They are never collapsed into one unexplained total. If you cannot tell what a charge was for by reading its description, that is a bug, and we want to hear about it.
A typical text question and answer is a few hundred tokens of your own words plus the Travel Rich material it was given, and one or two hundred tokens of reply. In practice most text questions land in the region of a few cents each once caching is doing its work. A question that fetches fares costs a little more, because the fares come back as input. A screenshot costs more than a text question, because the image adds to the input.
Caching works in your favour. The fixed instructions, much of the Travel Rich material and the Travel Bank catalogue are identical from one message to the next, so after the first message in a conversation most of that input is served from cache at the much lower cached rate. A longer conversation is therefore considerably cheaper per message than its first message suggests.
The way people plan trips also keeps usage modest. Most people use Rich Concierge in bursts: an evening choosing where to go, a few questions while comparing fares, a screenshot check before paying for the hotel, and then nothing for weeks until the next trip. Someone who uses it like that will usually sit under the $7.00 minimum for a while and see nothing charged at all for the first stretch. Someone who plans a trip every week and has long conversations will see a settlement most weeks. Your actual number is in your dashboard, updated after every message, and you never have to work it out from this page.
There is one more protection: a daily ceiling of $20.00 of AI usage per account. Reaching it stops further billable use until the next day. It exists so that a runaway loop, a forgotten open tab or somebody else getting into your account cannot produce a bill you did not choose.
Rich Concierge is only available when there is a payment method on file that can legitimately be charged again. In practice that means a card, or a PayPal account you authorised for future payments at checkout. It is also for adults only: you must be 18 or older to use it.
If you paid with Apple Pay or Google Pay, there is a genuine technical reason it is not available: both wallets give merchants a single-use device number rather than a reusable card. There is nothing on file that can be charged a second time. That is a privacy feature of those wallets working exactly as designed, and it means anything billed by usage cannot be attached to them.
For those accounts, Rich Concierge is not hidden behind a message: it is genuinely off. The dashboard does not show it, our server refuses it, and no usage can be recorded. Everything you bought still works in full: your course, the Season Calendar, the Value-Luxury Map, the Travel Bank, the planner and every add-on.
If you want access later, you can add a card deliberately from Billing in your dashboard. That is an explicit action you take, never something that happens because you clicked past a screen.
Before the first message that could ever be billed, you see a usage consent screen. It states that AI usage is billed separately, that usage varies with how much you use it, that the payment method you already have on file may be charged, what the current rates are, when settlement happens, where to see your usage and how to stop. You tick a box. Nothing is pre-ticked. If you do not tick it, nothing happens and nothing is billed.
After that, we do not interrupt you again. A product that asks you to reconfirm every time you type is not being careful, it is being annoying, and it teaches you to click past warnings. You agreed knowingly, and the running balance is visible whenever you want it.
Under the chat box there is a permanent line: "AI Chatbot. Extra usage may apply. Learn more". The "Learn more" is the link that brought you here. It is on every screen where you can type to Rich Concierge, and it never disappears.
Your conversations are stored against your account so you can reopen them, together with any cards they showed. They are readable by you, and they are not shown to anyone else. The system enforces that in two independent ways: conversations are keyed by your account, and every read checks again that the stored record belongs to the account asking for it.
Durable memory is deliberately small and deliberately named, as listed in section 7. Nothing else from a conversation is promoted into durable memory, and nothing from an image ever is. A system that quietly collects everything you ever mentioned is a liability you never agreed to, so it does not do that.
You can view, edit and clear that profile from your dashboard, and delete any conversation. Deleting a conversation removes it.
Your travel plans are never sent to advertising platforms. Not your airports, not your destinations, not your dates, not your budget, not anything you typed to Rich Concierge, not anything you set up in Travel Rich Fare Watch. Advertising events carry a purchase value, a currency and a hashed identifier, and the tracking layer on our pages strips travel fields before an event leaves the page. It is set out in more detail in our privacy notice.
Your messages, and any image you attach, are processed by a third-party AI provider in order to produce an answer. They are sent for that purpose and no other. When Rich Concierge looks up fares, only the route question (airports, month, length) is sent to the fare service, never your name or email.
A few things about how Rich Concierge is protected, in plain terms.
Several limits run quietly in the background. They exist to stop a compromised account, a runaway script or an honest mistake from producing a bill nobody intended.
None of these affect anything you have bought. A paused assistant never removes access to a PDF, the Travel Bank, your saved trips or your Travel Rich Weekly content.
Cards expire and banks decline things. If a settlement fails, the balance stays on your account as outstanding, and we try again in line with what the payment provider supports.
After repeated failures, billable AI use is paused. That is the honest option: the alternative is letting an unpaid balance grow on an account we already cannot charge, which serves nobody.
Your dashboard will say plainly what happened and what the outstanding amount is, and you can update your payment method there. When it goes through, AI use resumes.
Throughout all of it, everything you already bought stays yours. A failed AI settlement never removes access to a product, a download or your membership.
Stopping is simple, and there is no retention flow to click through.
Rich Concierge is built on a large language model, and large language models get things wrong. It is grounded in your own Travel Rich material and the Travel Bank specifically to reduce that, and it is instructed to say when something is outside what it was given rather than fill the gap. It will still occasionally be wrong. Your course is the reference whenever the two disagree, the booking page is the reference for a price, the airline or hotel is the reference for its own rules, and the official government source is the reference for entry, visas and safety.
Fare data has real limits too. Cached fares come from searches other travellers ran, up to about seven days ago, and the cheapest seats sell out. A fare seen this morning may be gone this afternoon, and a fare may exist today that no search has found yet. That is why every fare carries its seen time and a link to confirm it. Hotel averages are averages: a city's five-star average tells you where to look, not what your room will cost.
Availability depends on third-party providers: the AI provider and the fare service. Either can be slow or briefly unavailable. Nothing else in Travel Like the Rich depends on them: your course, the calendar, the map, the Travel Bank, your saved trips and your downloads all work whether or not Rich Concierge is up.
If a charge does not look right, or something on this page does not match what you see in your dashboard, write to us at support@travelliketherich.com. Include the date and the amount and we will find it.
We would genuinely rather refund a charge you did not understand than keep it.