As of 13 August 2026, AI can build a multi-city flight itinerary.

This still needs a person who signs their name to it.

Can you do it?

5 minutesto a draft.

30 minutesto something you’d act on.

Cost, all in£0

Skill needednone

Who has to check ityou

What the alternative costsNo priced human or specialist alternative is supplied in the available tool data.

If this goes wrong, you can end up with an invalid connection, an unsuitable airport change or a fare you cannot change.

What to actually do

Hand it to a person
The route this page recommends
A person who owns the outcome does this end to end, worth it when the failure is dear.
Use a tool built for this
Second choice

Do it yourself

The distant third

A chat interface, no skill needed, and roughly 30 minutes until you can act on the result.

How to actually do it

Open a current airline or flight-search site and gather the airports you can use, your possible travel dates, and any direct or connecting flight options for each city pair.
Gather your passport nationality, traveller ages, baggage requirements, cabin preference, date flexibility, budget and any requirement to avoid self-transfers or airport changes.
Paste the prompt into a chatbot and replace every bracketed slot with your details, including the exact order of cities if the order is fixed.
Ask the chatbot to compare the proposed order with sensible alternatives, then identify long layovers, overnight stops, separate-ticket connections and changes of airport.
Open the airline or booking site for every proposed leg and compare the drafted airports, dates, times, operating airlines, baggage rules, fare conditions and live availability against the current results.
Check each destination and transit point on GOV.UK for entry and transit requirements, then confirm the final itinerary directly with the airline or booking site before paying.

Prompt

Build a practical multi-city flight itinerary from the information below. Do not invent flight numbers, schedules, prices, availability, airport facilities, visa rules or baggage allowances. If live data is unavailable, label every such item as needing confirmation rather than guessing. Prefer sensible connections, the same airport where possible, and enough time for immigration, baggage collection, airport changes and delays. Keep the route within my date limits and flag any impossible or risky leg. For each leg, show the date, departure airport and city, arrival airport and city, local departure and arrival times if supplied, duration if supplied, connection time, operating airline if supplied, and what I must verify before booking. Separate confirmed information from suggestions. End with a booking checklist covering passport validity, entry requirements, transit rules, baggage, airport changes, self-transfer risk, cancellation terms and the need to confirm every detail on the airline or booking site. My requirements: Origin: [UK departure airport or city]. Destinations in order or possible order: [cities]. Earliest departure: [date]. Latest return: [date]. Travellers: [number and ages, including children if relevant]. Cabin: [economy, premium economy, business or first]. Baggage: [requirements]. Budget: [budget and currency]. Flexibility: [dates, airports and airlines]. Maximum acceptable connection time: [time]. Other constraints: [mobility, overnight flights, no self-transfers or other requirements].

Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.

What it gets wrong

AI cannot guarantee that a displayed flight still exists or that its price and seats are current.
AI cannot reliably assess whether a connection is safe when it involves immigration, baggage collection, separate tickets or a change of airport.
AI cannot take responsibility for passport, visa, transit, baggage or airline-specific rules.
AI cannot protect you from a non-refundable or otherwise unsuitable fare if you book without checking its conditions.

Even on a YES, the friction has a name: real time truth, verification cost and stakes of error.

How we scored this

Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.

Axis	Score (0–2)
Output	2
Inputs	2
Verification	1
Liability	2
Effort delta	2
Total	9 / 10

The methodology and its thresholds are published in full.

FAQ

Can ChatGPT plan a multi-city trip?: Yes. It can turn your cities, dates and preferences into a route, compare possible orders and present the legs in a usable itinerary. Check every live flight detail and booking condition with the airline before paying.
Can AI find flights for multiple destinations?: It can suggest routes and help you organise flight-search results, but it may not have reliable live availability or fares. Use the suggestions as a shortlist and confirm each leg on a current airline or booking site.
Is it safe to book a flight itinerary made by AI?: It is safe only after you check the itinerary yourself. Confirm airports, connection arrangements, entry and transit rules, baggage, fare conditions and live availability, because a plausible-looking itinerary can still contain an unusable connection.
What information does AI need to plan a multi-city flight?: Give it your departure point, cities, date limits, traveller details, cabin, baggage, budget, flexibility and connection limits. Also state whether you will accept overnight flights, airport changes, self-transfers or separate tickets.

Nearby answers

All Bookings & itineraries rulings

Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.

The newsletter

AI news, new answers and product picks, straight to your inbox.