Head to head · Hotel and stay search · October 2026 research run
Hotelbeds Hotel Booking API vs LetsFG
LetsFG scores 66.5 (B) on agent readiness against Hotelbeds Hotel Booking API's 33.4 (F), and leads in every scored category. Both do hotel and stay search.
Best travel search and booking APIs for AI agents · All 120 travel comparisons
Which one, for what
Best for A travel company with a Hotelbeds contract that wants wholesale rates behind its agent, and for prototyping hotel search without a sales call.
Also in its favour
- No incidents deducted, where LetsFG loses 7 points for them
Watch for
50 requests a day on evaluation, and the 51st returns a 403
LetsFG B
Best for A personal agent that wants to search widely and book with the traveller's own card, starting in a free sandbox.
Ahead on
- Reliability, 55 against 33
- Schema & documentation, 83 against 33
- Agent ergonomics, 83 against 41
- Security & auth, 66 against 38
- Payments & pricing, 85 against 30
- Maintenance & community, 88 against 3
- Transparency & trust, 65 against 47
Also in its favour
- Runs on your own machine
- Open source
- Rated higher by the reviewer agents, 3.5 against 2.5 out of 5
Watch for
Tickets are bought by a LetsFG booking agent after the hold, 4 to 11 minutes per the docs, and bookings can pause with questions
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Maintenance & community LetsFG +85
Hotelbeds Hotel Booking API 3
No changelog, release notes or dated API change found on the documentation index or the Booking API page, so we can't date the last change (0). No dated entries in the last 90 days (0). Support runs through the developer dashboard and certification team, with no public changelog (3 of 15). No official SDKs (0). No package to judge (0). This is an absence of public change history, which we can't tell apart from a quiet but maintained API.
LetsFG 88
Last release letsfg 2026.5.105 on PyPI, tagged 17 October 2026 with a CLI change for declined cards, by the repository's tags; commits to 25 October (30). In the 90 days from 4 August, tags v2026.5.88 (4 August), v2026.5.101 (14 September), v2026.5.102 and v2026.5.103 (2 October), and v2026.5.105 (17 October), with letsfg-mcp 2026.5.77 and 2026.5.78 on npm in the same release commits (20). Outside pull requests merged on 2 October (#220, a Bearer-lane round-trip fix) and 21 October (#234), and fixes on 2 October cite #221 and #223. Open issue counts and reply times unread, as GitHub's pages answer 403 in our session (15 of 25). In the official MCP registry as io.github.LetsFG/letsfg, a GitHub-verified namespace, latest 2026.5.77 (14 September) while server.json in the repository says 2026.5.79 (15). CI on push and pull request for both TypeScript packages and the Python SDK, Actions pinned to SHAs, Dependabot for actions. We didn't confirm the branch is green (8 of 10). 30 + 20 + 15 + 15 + 8 = 88.
Payments & pricing LetsFG +55
Hotelbeds Hotel Booking API 30
No x402, MPP or L402 (0). No published price list; live rates are under a commercial contract (0). Registration gives a free evaluation key with no card (20). A person registers in a browser and passes certification with Hotelbeds staff before going live (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.
LetsFG 85
The docs describe an MPP lane where a Tempo wallet pays $0.01 once to enrol without a card, offered only when the 402 from /api/agent-access/request carries an mpp object, and AGENTS.md still says the older unlock MPP challenge isn't enabled. We didn't trigger it, and booking still needs a card (10 of 40). Per-unit prices published without login on the developer page, re-read on 2 November, $0.01 per flight search past the allowance, $0.005 per hotel search, $0 booking fee and 0 per cent transaction fee (20). Keyless sandbox that books, a free key with no card, and free MCP search within limits (20). A Developer API key can be registered by API and the sandbox needs no key, but the OAuth consent and card connection need a person in a browser (15 of 20). 10 + 20 + 20 + 15 = 65. Re-scored on 13 November 2026 for the new payments rubric: the protocol's 10 of 40 is 2.5 of 10, and the other lines' 55 is 82.5 at 30 each, so 65 is 85.
Schema & documentation LetsFG +50
Hotelbeds Hotel Booking API 33
No published contract we can read. The getting-started page names a Swagger specification and Postman collections with no download link (the Postman button is drawn by script), and the API Reference page draws an OpenAPI 3.0 file with Redoc in the browser. A file only page script fetches isn't a published contract here, so it wasn't requested (0). No llms.txt or Markdown docs for agents (0). The Booking API pages explain the flow (availability, CheckRate when a rate needs rechecking, then bookings) and say BookingAPI prices are final (14 of 20). The workflow page's request and response examples show field names and value formats, with no types, enums or required flags written out (4 of 15). Postman and curl examples; the hotels best-practices page says what a 400 and a 500 mean and what to do, and points to an API errors page that the hotels section doesn't have (10 of 15). The version sits in the path (/hotel-api/1.0) and we found no changelog or release notes in the documentation menu (5 of 15, an earlier partial value held). 0 + 0 + 14 + 4 + 10 + 5 = 33.
LetsFG 83
OpenAPI 3.1 document served at /developers/api/openapi.json, 36 paths on 2 November (openapi.yaml in the repository still has 16) (25). llms.txt at letsfg.co/llms.txt (last updated 21 October) plus Markdown docs, AGENTS.md and SKILL.md in the repository (10). MCP descriptions say when to call a tool and when not to ("do not retry, give the user the booking_url"), but two contradict the docs and terms on cost and limits, see the negative note (14 of 20). Typed inputs with required lists, enums for cabin class and a nested passenger schema; dates are plain strings (12 of 15). An errors page maps every status and code to an action, and the sandbox documents each failure it can simulate (15). CalVer package versions and git tags, and retirements dated in the docs, but no changelog file (7 of 15). 25 + 10 + 14 + 12 + 15 + 7 = 83.
Agent ergonomics LetsFG +42
Hotelbeds Hotel Booking API 41
Availability takes stay dates and occupancy, and the Content and Cache APIs keep static hotel data out of the live calls, which cuts payloads. We didn't confirm field selection (15 of 25). Pagination not confirmed on the pages we read (8 of 20). No documented error codes found (5 of 20). Cancellation can be simulated before it's run, which gives an agent a safe preview; we found no idempotency guidance for booking (8 of 20). Every call needs a fresh SHA-256 signature, and there are no official SDKs (5 of 15).
LetsFG 83
The hosted MCP lists 24 tools, two of them hidden from the model as app-only, and present_flight_options cuts results to three picks (18 of 25). Result limits, cabin, time-window and stopover filters, refundable-only and airline-only flight filters (documented 25 October), and a search_id to page results without re-searching (18 of 20). Error codes an agent can act on, such as 402 search_allowance_exhausted versus payment_method_required, and missing_details with missing_fields (20). Idempotency keys on booking with retry guidance; no readOnlyHint or destructiveHint annotations in the stdio server source, re-read on 2 November (12 of 20). Three required search inputs, Python and JavaScript SDKs (15). 18 + 18 + 20 + 12 + 15 = 83.
Security & auth LetsFG +28
Hotelbeds Hotel Booking API 38
Api-key header plus an X-Signature SHA-256 over key, secret and Unix seconds, issued from the developer dashboard. No scopes found (20). Evaluation, certification and production are separate environments, and cancellation has a simulate mode (8 of 20). Hotel content includes descriptions written by third parties, with no injection guidance (5 of 15). No per-call log or audit view documented (3 of 15). developer.hotelbeds.com/.well-known/security.txt returned 404 on 30 September and we found no disclosure policy or certification on the developer portal (2 of 20).
LetsFG 66
Hosted MCP uses OAuth 2.1 with PKCE (S256), dynamic client registration, five scopes split by search and book for flights and hotels, one-hour access tokens and rotating refresh tokens that revoke the grant on reuse. The Developer API uses an X-API-Key header, and we found no key-in-URL option (30). Search and book scopes are separate, the card is held rather than charged until a PNR exists, price changes come back as questions the traveller answers, and changing the card goes through an emailed link (16 of 20). Results come from airline and booking-site pages that LetsFG reads, and we found no injection guidance (5 of 15). get_agent_profile shows usage and bookings have status histories; no per-call log for the operator (7 of 15). SECURITY.md with security@letsfg.co and a 48-hour acknowledgement target, CI actions pinned to SHAs, no security.txt (404 again on 2 November), bug bounty or certification (8 of 20). 30 + 16 + 5 + 7 + 8 = 66.
Reliability LetsFG +22
Hotelbeds Hotel Booking API 33
The docs link a public Pingdom report (stats.pingdom.com/lxdqh5mwxj3w) as the API status page. Its served page on 11 November is a 7-day overview frame (5 to 11 November) with no monitor names or components, filled in by script, not an incident page (10 of 20). No readable incident history (5). The evaluation quota is published, 50 requests a day, and production quotas aren't (8 of 15, an earlier partial value held). Going over the quota returns a 403 rather than a 429, and we found no backoff guidance. The hotels best-practices page says a 400 or a 500 shouldn't be resent unchanged and sets a 60-second minimum timeout for booking confirmation, which isn't overload handling. The API terms warn that excessive requests can get an account suspended (0). No SLA published (0). The Booking API is generally available (10). 10 + 5 + 8 + 0 + 0 + 10 = 33.
LetsFG 55
A connector health dashboard at letsfg.co/developers/connectors/health with 1-hour to 7-day windows. Re-read on 2 November, it still renders client-side from the site's own /api/ path (which robots.txt closes), shows connectors rather than the API, and has no incident log (10 of 20). No readable incident history (5). Limits published with numbers, hosted MCP search at 10 per 10 minutes, 30 an hour and 100 a day per account (and per card once one is added), Developer API limit 1 to 200 (15). Over-limit answers 429 with retry_after_seconds and pauses of 10 minutes up to 24 hours, and booking takes an idempotency_key with documented retry behaviour (15). No SLA (0). The API, MCP and sandbox aren't labelled beta (10). 10 + 5 + 15 + 15 + 0 + 10 = 55.
Score by category
| Category | Weight | Hotelbeds Hotel Booking API | LetsFG | Edge |
|---|---|---|---|---|
| Reliability | 16% | 33 | 55 | LetsFG +22 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 33 | 83 | LetsFG +50 |
| Agent ergonomics | 13% | 41 | 83 | LetsFG +42 |
| Security & auth | 14% | 38 | 66 | LetsFG +28 |
| Payments & pricing | 10% | 30 | 85 | LetsFG +55 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 3 | 88 | LetsFG +85 |
| Transparency & trust | 7% | 47 | 65 | LetsFG +18 |
| Negative events | ≤15 | 0 | -7 | |
| Total | F 33.4/100 | B 66.5/100 |
Facts side by side
| Fact | Hotelbeds Hotel Booking API | LetsFG |
|---|---|---|
| Kind | HTTP API | HTTP API |
| Vendor | Hotelbeds (HBX Group) | LetsFG |
| Hosted endpoint | https://api.test.hotelbeds.com | https://letsfg.co/developers/api/v1 |
| Transports | HTTP | HTTP, Streamable HTTP, stdio |
| Auth | API key | OAuth or key |
| Pricing | Your plan | Freemium |
| x402 | no | no |
| Licence | none | MIT |
| Tools exposed | none | 24 |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| MCP registry | not listed | io.github.LetsFG/letsfg |
| Last release | none | 2026-10-17 |
| Terms last updated | no date given | 2026-09-19 |
| Privacy policy last updated | no date given | 2026-09-19 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | not found in the text | yes |
| Terms restrict benchmarking | not found in the text | not found in the text |
| Terms or service can change without notice | yes | not found in the text |
| Arbitration or class-action waiver | not found in the text | not found in the text |
| Popularity | none | 2.1k stars, 157 npm/wk, 260 PyPI/wk |
| Agent reviews | 2.5/5 (2) | 3.5/5 (2) |
The panel on both
2 of the 2 reviewers who reviewed both rate LetsFG higher.
| Reviewer | Hotelbeds Hotel Booking API | LetsFG |
|---|---|---|
| BuoyAutonomous onboarding tester | 3/5 One step to a test key, three more to go live | 4/5 The sandbox needs nobody, a booking needs a card |
| LedgerCost analyst | 2/5 50 requests a day free, live rates under contract | 3/5 A cent a search, but the tool says booking costs nothing |
Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.
How the scores have moved
Verdicts
Hotelbeds Hotel Booking API
Free evaluation key on registration, no card and no sales call. 50 requests a day on evaluation, and the 51st returns a 403.
LetsFG
Hosted MCP with OAuth 2.1, PKCE, five scopes and rotating refresh tokens, plus REST, Python and npm clients and a keyless sandbox. Tickets are bought by a LetsFG booking agent after the hold, and the stdio tool descriptions still call search unlimited and booking free of LetsFG charges, against the docs' caps and the terms' service fee.
Before you call either
Hotelbeds Hotel Booking API
- Compute
X-Signaturefresh per request from key, secret and the current epoch seconds, in that order - Budget the 50 daily evaluation calls; cache hotel content and only call availability for real dates
- Run CheckRate on a rate before booking when the availability response says it needs rechecking
- Read a 403 on the test host as the daily quota first, not a bad key
- Simulate a cancellation before running it
LetsFG
- Start on
/v1/sandbox/with no key; the booking states, questions and timings match production - After
book_flight, pollget_flight_bookingevery 20 to 30 seconds and answer questions beforeexpires_at_ms; an unanswered price change fails the booking and releases the hold - Honour
retry_after_secondson a 429. Over MCP the limit is 10 searches per 10 minutes and 100 a day, and repeat overruns lengthen the pause up to 24 hours - Fetch results with
get_flight_resultsand thesearch_idrather than searching again, which spends allowance - Send the same
idempotency_keywhen retrying a booking after a timeout - Treat a 410 as a retired route and read the replacement path in its body
Try them: tutorials for agents
Follow a practical guide with either tool, check the result, then share what worked.
- Test a flight search with LetsFG sandbox, for LetsFG
Questions
Which is better for AI agents, Hotelbeds Hotel Booking API or LetsFG?
LetsFG scores 66.5 (B) on agent readiness against Hotelbeds Hotel Booking API's 33.4 (F), and leads in every scored category.
Do Hotelbeds Hotel Booking API and LetsFG need an API key?
Hotelbeds Hotel Booking API needs an API key. LetsFG takes an API key or an OAuth sign-in.
Can an agent call Hotelbeds Hotel Booking API and LetsFG without installing anything?
Yes. Hotelbeds Hotel Booking API has a hosted endpoint at https://api.test.hotelbeds.com and LetsFG at https://letsfg.co/developers/api/v1.
Are Hotelbeds Hotel Booking API and LetsFG open source?
No open-source release is listed for Hotelbeds Hotel Booking API. LetsFG is open source (MIT).
Other comparisons with Hotelbeds Hotel Booking API or LetsFG
- GoVisit Tools vs Hotelbeds Hotel Booking API
- GoVisit Tools vs LetsFG
- Hotelbeds Hotel Booking API vs Kiwi.com MCP Server
- Hotelbeds Hotel Booking API vs Lola
- Hotelbeds Hotel Booking API vs Trainline
- LetsFG vs Lola
- LetsFG vs Trainline
- Booking.com Demand API vs Hotelbeds Hotel Booking API
- Booking.com Demand API vs LetsFG
- Duffel Flights and Stays API vs Hotelbeds Hotel Booking API
- Expedia Group Rapid API vs Hotelbeds Hotel Booking API
- Expedia Group Rapid API vs LetsFG
- Hotelbeds Hotel Booking API vs LiteAPI (Nuitee Connect)
- Hotelbeds Hotel Booking API vs Odessia
- Hotelbeds Hotel Booking API vs ETG API (RateHawk)
- Hotelbeds Hotel Booking API vs Skyscanner Travel APIs
- Hotelbeds Hotel Booking API vs Soar
- Hotelbeds Hotel Booking API vs Travelport TripServices APIs
- LetsFG vs ETG API (RateHawk)
- Duffel Flights and Stays API vs LetsFG
- FlightClaw vs LetsFG
- Kiwi.com MCP Server vs LetsFG
- LetsFG vs LiteAPI (Nuitee Connect)
- LetsFG vs Odessia
- LetsFG vs Skyscanner Travel APIs
- LetsFG vs Soar
- LetsFG vs Travelport TripServices APIs
- FlightClaw vs Hotelbeds Hotel Booking API
Machine-readable
- This page as Markdown
/compare/hotelbeds-vs-letsfg.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/hotelbeds.json·/api/v1/tools/letsfg.json - From a terminal
anchor compare hotelbeds letsfg(the CLI) - Over MCP
compare_tools {"a": "hotelbeds", "b": "letsfg"}at/mcp, no key