Flight pricing service

The Flight Shopping API,
built for AI-scale
search.

Flight search at orders of magnitude lower cost — so OTAs and airlines can profitably serve the exploratory traffic from metasearch and AI agents.

  • WHAT Flight prices estimated by an ML model — not queried from a GDS or airline system on every search.
  • WHO IT'S FOR OTAs, airlines, and metasearch absorbing AI-driven exploratory traffic.
  • HOW TO USE Drop-in API or native MCP server — plugs into your stack or any AI travel agent.
Contact us How it works
The problem

Flight pricing was built for humans. AI search breaks the look-to-book math.

Look-to-book — the ratio of searches a pricing system handles to actual bookings — used to be 1:50 in the days of human travel agents. With OTAs it climbed to 1:500. Metasearch pushed it past 1:10,000. AI travel agents and modern comparison tools take it past 1:200,000. At those volumes, computing every fare from scratch on a GDS or airline system stops paying for itself.

1960
Travel agent

Phone, terminal, one query at a time.

1 : 50
look-to-book
1996
OTA

Self-serve. The form moves online; the question stays the same.

1 : 500
look-to-book
2005
Metasearch

Comparison sites fan one query out to many OTAs. Cost climbs.

1 : 10,000
look-to-book
2026 · NOW
AI agents

No form. No constraints. One trip becomes hundreds of thousands of searches.

1 : 216,000+
look-to-book

Use the calculator below to plug in your own traffic and see where you land.

An AI agent planning a flexible Greek-islands week fans out across origins, destinations, and dates in parallel — one trip request becomes hundreds of thousands of searches. Look-to-book was already creaking under human traffic, and the ratio grows exponentially. Calculate yours.

EXAMPLE QUERY

“Show me flights from Milan to Greek islands in June.”

Read the IATA look-to-book white paper →

Look-to-book calculator

One trip request. 216,000 searches.

Origins the agent considers (e.g. LHR, LGW, STN).

Destinations in scope (Greek islands, the Med, etc.).

e.g. 24 possible 7-day trips that fit inside a single 30-day month.

%

Your share of the clicks this trip generates.

%

Trip requests on your channel that turn into bookings.

Your look-to-book
1 : 216,000
2,160 searches per trip request

Look-to-book = (airports × destinations × dates) ÷ share ÷ conversion

How it works

Estimate the answer. Don't recompute it.

Instead of computing every fare combination in real time, our machine-learning model estimates the cheapest options — without sending a query to a GDS or directly to an airline.

01 · MACHINE-LEARNING MODEL
Trained on real fare data

We've trained the model on years of historical fare data. Given a route and dates, it predicts the cheapest itineraries in milliseconds — without computing every combination.

02 · STABLE PATTERNS
Fare rules don't change every minute

Weekend-stay requirements, advance-purchase rules, route restrictions — most fare logic is stable from one day to the next. If an itinerary worked yesterday, it almost certainly works today.

03 · LIVE SAMPLING
Sample. Compare. Correct.

We regularly query real prices and availability and feed the results back into the model. Predictions self-correct continuously as fares move.

Who we serve

Built for OTAs and airlines. Works on any channel — from metasearch, to AI agents.

We help both on the two channels where the look-to-book math has stopped working: metasearch — including the long-tail queries that have always been too expensive to bid on — and AI travel assistants, where one user can generate hundreds of searches in a single conversation.

Online travel agencies

Serve the searches AI agents and metasearch sites send you without your pricing infrastructure scaling with traffic.

Airlines

Show fares on metasearch sites and to AI travel agents without paying GDS fees on every search. Pay full distribution costs only when a customer actually books.

For developers
Building your own travel agent or app?

Get flight search and booking links with a single API call. A generous free quota to build, prototype, and ship — no GDS contract, no enterprise sales cycle.

  • 01 Generous free quota — enough to develop, test, and run a side project without a credit card.
  • 02 Deeplinks to major booking providers — point users straight to checkout on the OTAs and airlines they already trust.
  • 03 REST or MCP — drop into any backend, or plug straight into Claude, ChatGPT, and other agent runtimes.
Booking flow

Search with us. Book the way you already do.

zerolook is a search-and-pricing layer, not a distributor. When a customer commits to a booking, send them through whatever channel makes sense — NDC, GDS, your existing consolidator, a direct connect. Distribution fees apply only with your existing partners.

STEP · 01 · SEARCH & PRICE
You query zerolook

Predicted itineraries, prices, and confidence scores. This is the only step you pay for.

STEP · 02 · CUSTOMER DECIDES
A user commits to a fare

Route the booking by route, fare class, market, or commercial deal — exactly as you do today. zerolook stays out of the booking path.

STEP · 03 · BOOK ANYWHERE
NDC, GDS, consolidator — your call

Distribution fees apply only here, and only with your existing partners. You pay nothing to zerolook.

Talk to us about adding zerolook to your pricing stack.

Sandbox key, integration plan, or partnership conversation — we respond within one business day.

Contact us