{
  "fixes": {
    "slug": "booking-demand-api",
    "name": "Booking.com Demand API",
    "listing": "https://www.anchorterminal.com/tools/booking-demand-api",
    "markdown": "# Fix list: Booking.com Demand API\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/booking-demand-api, the October 2026 research run, assessed 1 October 2026. Grade E, 38.1 out of 100.\n\nThis is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.\n\nFor a coding agent working on Booking.com Demand API: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.\n\n## 1. Reliability, 33 out of 100, up to 13.4 more on the total\n\nWhy it scored 33: No public status page found for the Demand API (0). No incident history to read (5). The sandbox is capped at 50 requests a minute and production cars search at 3,000 a minute; every other production limit comes from your account manager, per the 30 September check (8 of 15). The rate-limiting page covers 429 and exponential backoff, per the same check, and we found no idempotency guidance for orders (10 of 15). No SLA published (0). Version 3.2 is the stable release, with 3.2-Beta alongside it (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 2. Payments \u0026 pricing, 5 out of 100, up to 11.9 more on the total\n\nWhy it scored 5: No x402, MPP or L402 (0). No published prices; commission terms are in the affiliate agreement behind Partner Centre (0). The sandbox is free but needs Managed Affiliate Partner status first, and payment tests need a real card (5 of 20). A person registers as a partner (0).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.\n\nOpen-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.\n\n## 3. Security \u0026 auth, 36 out of 100, up to 11.2 more on the total\n\nWhy it scored 36: A Bearer API key plus `X-Affiliate-Id`, generated in Partner Centre, shown once, with guidance to rotate yearly and revoke on compromise. No scopes found (20). The sandbox is the only reduced-privilege mode, and sandbox payment tests use a real card with temporary charges (5 of 20). Responses carry property descriptions and guest content written by third parties, with no injection guidance (5 of 15). No per-call log or audit view documented (3 of 15). developers.booking.com/.well-known/security.txt returned 404 on 30 September, and www.booking.com is closed to our reader, so the wider disclosure programme is unchecked (3 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.\n\n## 4. Agent ergonomics, 53 out of 100, up to 7.6 more on the total\n\nWhy it scored 53: Search takes filters, and the docs name payload size as the main cost and point to filtering, per the 30 September check. We didn't confirm field selection (15 of 25). Pagination and filters on search, per the same check (18 of 20). Error responses not documented on the pages we read (10 of 20). No idempotency key on orders found (5 of 20). Two auth headers on every call, no official SDKs (5 of 15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.\n\n## 5. Schema \u0026 documentation, 57 out of 100, up to 7 more on the total\n\nWhy it scored 57: The API references live under /open-api/ for 3.2, 3.1 and 3.2-Beta, but we found no downloadable OpenAPI or Swagger file (5 of 25). No llms.txt or Markdown docs for agents, per the 30 September check (0). Reference pages state what each endpoint is for and the guides cover the search, look and book flow (15 of 20). Typed request bodies with required fields in the references (12 of 15). Examples in the quickstart and references; error responses weren't documented on the pages we read (10 of 15). Three versions with stated status (3.2 stable, 3.1 supported but frozen, 3.2-Beta experimental) and a dated changelog (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.\n\n## 6. Maintenance \u0026 community, 28 out of 100, up to 6.3 more on the total\n\nWhy it scored 28: The newest changelog entry is August 2026, covering car rental commission estimates, insurance documents and pay-at-pickup car orders in 3.2 and Beta (20). That was the only dated entry since January our reader saw, so fewer than three in 90 days (0). Public changelog and partner account managers; no public support channel (8 of 15). No official SDKs (0). No package to judge (0).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## 7. Transparency \u0026 trust, 49 out of 100, up to 4.5 more on the total\n\nMade of editorial 28, provenance 70.\n\nWhy it scored 49: Closed service. The affiliate terms sit behind Partner Centre sign-in, so the contract can't be read before you sign (5 of 30). The partner privacy statement names Booking.com B.V., Amsterdam, as the responsible entity; the consumer privacy page is closed to our reader and no retention periods or DPA were found (12 of 30). 3.1 is marked \"supported for existing integrations\" with no sunset date, and the changelog carries no deprecation notices (8 of 20). No subprocessor list or data locations found (3 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Terms of service: not found (0 of 10)\n- Status page: not found (0 of 10)\n- security.txt: not found (0 of 10)\n\n## What we couldn't check\n\nWhat we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.\n\n- Whether the changelog has more 2026 entries than the August one our reader saw\n- unchecked: Booking.com's vulnerability disclosure programme and certifications, since www.booking.com blocks our reader\n- Whether the OpenAPI files behind the /open-api/ references can be downloaded by partners\n- Production rate limits other than cars search\n\n## Weaknesses\n\n- Managed Affiliate Partner status required; no self-serve key\n- No published prices, SLA, status page or production rate limits beyond cars search\n- No downloadable OpenAPI file, llms.txt, SDKs or MCP server\n- Sandbox payment tests need a real card with temporary charges, and only accommodation books there\n- One changelog entry in 2026 that we could read\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Send both `Authorization: Bearer` and `X-Affiliate-Id`, or the call fails on auth\n- Stay under 50 requests a minute in the sandbox and back off exponentially on 429\n- Only accommodation flows book in the sandbox; cars and attractions won't\n- Store the key at creation, it's never shown again\n- Use filters and pagination on search to keep payloads small\n\n## What the review panel asked for\n\n- Published eligibility criteria\n- A self-serve sandbox\n- Publish the commission terms\n- Test payments without a real card\n\n## When it's done\n\nSend what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `\"kind\": \"dispute\"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.\n",
    "grade": "E",
    "score": 38.1,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 33,
        "maxGain": 13.4,
        "reason": "No public status page found for the Demand API (0). No incident history to read (5). The sandbox is capped at 50 requests a minute and production cars search at 3,000 a minute; every other production limit comes from your account manager, per the 30 September check (8 of 15). The rate-limiting page covers 429 and exponential backoff, per the same check, and we found no idempotency guidance for orders (10 of 15). No SLA published (0). Version 3.2 is the stable release, with 3.2-Beta alongside it (10).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.",
          "Local packages, SDKs, frameworks and stdio MCP servers.",
          "- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.",
          "Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 5,
        "maxGain": 11.9,
        "reason": "No x402, MPP or L402 (0). No published prices; commission terms are in the affiliate agreement behind Partner Centre (0). The sandbox is free but needs Managed Affiliate Partner status first, and payment tests need a real card (5 of 20). A person registers as a partner (0).",
        "checklist": [
          "The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).",
          "- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).",
          "Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.",
          "Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 36,
        "maxGain": 11.2,
        "reason": "A Bearer API key plus `X-Affiliate-Id`, generated in Partner Centre, shown once, with guidance to rotate yearly and revoke on compromise. No scopes found (20). The sandbox is the only reduced-privilege mode, and sandbox payment tests use a real card with temporary charges (5 of 20). Responses carry property descriptions and guest content written by third parties, with no injection guidance (5 of 15). No per-call log or audit view documented (3 of 15). developers.booking.com/.well-known/security.txt returned 404 on 30 September, and www.booking.com is closed to our reader, so the wider disclosure programme is unchecked (3 of 20).",
        "checklist": [
          "- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.",
          "Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 53,
        "maxGain": 7.6,
        "reason": "Search takes filters, and the docs name payload size as the main cost and point to filtering, per the 30 September check. We didn't confirm field selection (15 of 25). Pagination and filters on search, per the same check (18 of 20). Error responses not documented on the pages we read (10 of 20). No idempotency key on orders found (5 of 20). Two auth headers on every call, no official SDKs (5 of 15).",
        "checklist": [
          "- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.",
          "Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 57,
        "maxGain": 7,
        "reason": "The API references live under /open-api/ for 3.2, 3.1 and 3.2-Beta, but we found no downloadable OpenAPI or Swagger file (5 of 25). No llms.txt or Markdown docs for agents, per the 30 September check (0). Reference pages state what each endpoint is for and the guides cover the search, look and book flow (15 of 20). Typed request bodies with required fields in the references (12 of 15). Examples in the quickstart and references; error responses weren't documented on the pages we read (10 of 15). Three versions with stated status (3.2 stable, 3.1 supported but frozen, 3.2-Beta experimental) and a dated changelog (15).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.",
          "Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 28,
        "maxGain": 6.3,
        "reason": "The newest changelog entry is August 2026, covering car rental commission estimates, insurance documents and pay-at-pickup car orders in 3.2 and Beta (20). That was the only dated entry since January our reader saw, so fewer than three in 90 days (0). Public changelog and partner account managers; no public support channel (8 of 15). No official SDKs (0). No package to judge (0).",
        "checklist": [
          "- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 49,
        "maxGain": 4.5,
        "reason": "Closed service. The affiliate terms sit behind Partner Centre sign-in, so the contract can't be read before you sign (5 of 30). The partner privacy statement names Booking.com B.V., Amsterdam, as the responsible entity; the consumer privacy page is closed to our reader and no retention periods or DPA were found (12 of 30). 3.1 is marked \"supported for existing integrations\" with no sunset date, and the changelog carries no deprecation notices (8 of 20). No subprocessor list or data locations found (3 of 20).",
        "blend": "editorial 28, provenance 70",
        "checklist": [
          "- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).",
          "The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      }
    ],
    "provenance": [
      {
        "label": "Terms of service",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "Status page",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "Whether the changelog has more 2026 entries than the August one our reader saw",
      "unchecked: Booking.com's vulnerability disclosure programme and certifications, since www.booking.com blocks our reader",
      "Whether the OpenAPI files behind the /open-api/ references can be downloaded by partners",
      "Production rate limits other than cars search"
    ],
    "weaknesses": [
      "Managed Affiliate Partner status required; no self-serve key",
      "No published prices, SLA, status page or production rate limits beyond cars search",
      "No downloadable OpenAPI file, llms.txt, SDKs or MCP server",
      "Sandbox payment tests need a real card with temporary charges, and only accommodation books there",
      "One changelog entry in 2026 that we could read"
    ],
    "agentNotes": [
      "Send both `Authorization: Bearer` and `X-Affiliate-Id`, or the call fails on auth",
      "Stay under 50 requests a minute in the sandbox and back off exponentially on 429",
      "Only accommodation flows book in the sandbox; cars and attractions won't",
      "Store the key at creation, it's never shown again",
      "Use filters and pagination on search to keep payloads small"
    ],
    "requests": [
      {
        "text": "Published eligibility criteria",
        "reviews": 1
      },
      {
        "text": "A self-serve sandbox",
        "reviews": 1
      },
      {
        "text": "Publish the commission terms",
        "reviews": 1
      },
      {
        "text": "Test payments without a real card",
        "reviews": 1
      }
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-04",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}