{
  "fixes": {
    "slug": "iloveapi",
    "name": "iLoveAPI",
    "listing": "https://www.anchorterminal.com/tools/iloveapi",
    "markdown": "# Fix list: iLoveAPI\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/iloveapi, the October 2026 research run, assessed 9 October 2026. Grade E, 42 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 iLoveAPI: 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, 26 out of 100, up to 14.8 more on the total\n\nWhy it scored 26: Graded as a hosted API. No status page is linked from the site, the docs or the security page (0), so there is no readable incident history (5). Rate limits are described as tier-dependent and reported in response headers, with no numbers. The open-task cap of 10% of the monthly file limit and two signature reminders a day are the only figures (3). 429 is documented with advice to back off exponentially, and failed files are not charged, but there is no Retry-After and no idempotency key (8). The pricing FAQ says the API guarantees over 99.95% uptime and the functions page says 99.9%+, with no SLA document or remedy, and the terms disclaim availability (0). Generally available (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. Security \u0026 auth, 41 out of 100, up to 10.3 more on the total\n\nWhy it scored 41: Each project has a public and a secret key, requests carry a JWT signed with the secret that expires after one hour, and domain and IP filters exist depending on tier. No scopes (20). No read-only key or confirmation before a task is deleted, and `/auth` issues a token for the public key alone unless a domain filter is set (4). OCR, Markdown and summary output is untrusted text and the docs give no injection guidance (0). `/task` lists processed tasks and signatures have a downloadable audit trail, with no account audit log found (7). ISO/IEC 27001:2022 certificate linked and a signed security policy of 19 June 2025. security.txt answered 403, and no disclosure policy or bounty was found (10).\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## 3. Schema \u0026 documentation, 37 out of 100, up to 10.2 more on the total\n\nWhy it scored 37: No OpenAPI file or other machine-readable contract was found (0). `llms.txt` answered 404 and there are no Markdown docs (0). The single-page reference states what each tool and parameter does, without guidance on when not to use one (10). Parameters carry types, accepted values and defaults, such as rotation 0, 90, 180 or 270 (11). JSON response samples, an error table, and file and task status lists, with request examples mostly in the library guides (10). The path carries `/v1`. No API changelog was found, and the Python and PHP libraries keep their own (6).\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## 4. Payments \u0026 pricing, 30 out of 100, up to 8.8 more on the total\n\nWhy it scored 30: No x402, MPP or L402 (0). The credit cost of every tool is public without a login, but the euro price of a credit is drawn by script and was not read, so this is scored as public plan pricing (10). 2,500 free credits a month, and the sign-up form asks for name, email and password with no card field (20). A person registers in a browser to get keys (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## 5. Agent ergonomics, 61 out of 100, up to 6.3 more on the total\n\nWhy it scored 61: Responses are small JSON and output arrives as a file or ZIP, but every job takes four calls and the start call's server must be reused (12). `/task` lists 50 a page with filters by tool, status and `custom_int`, and the signature list takes page and per-page (14). One error structure with type, message, code and param, plus per-file statuses such as WrongPassword and DamagedFile (14). No idempotency keys. A `debug` parameter echoes a request without processing, and a wrong password leaves the task waiting for a resend (6). Most parameters have defaults, and there are official libraries in five languages (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## 6. Transparency \u0026 trust, 52 out of 100, up to 4.2 more on the total\n\nMade of editorial 37, provenance 66.\n\nWhy it scored 52: Closed service with terms naming iLovePDF S.L., last modified 14 February 2017, and MIT client libraries (15). The reference says files are deleted after an hour depending on tier and elsewhere after two hours, the security page says two hours and the terms say at most 48 hours. The privacy policy is an iubenda document closed to us by robots.txt and was not read (12). No deprecation policy, and the terms allow the API to be discontinued at any time (0). Seven processing regions are selectable per task and Stripe is named for payments. No subprocessor list was read (10).\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: read, states 6 of the 7 things a reader expects (9.1 of 10)\n- Privacy policy: published, but our reader couldn't read it (7 of 10)\n- Status page: not found (0 of 10)\n- Changelog: not found (0 of 10)\n- security.txt: could not be fetched (0 of 10)\n\n## 7. Maintenance \u0026 community, 62 out of 100, up to 3.3 more on the total\n\nWhy it scored 62: The .NET library v1.6.4 was tagged on 3 September 2026, 36 days before this check (20). Three library releases in the last 90 days, PHP v1.4.1 on 22 July, Python v1.1.0 on 28 July and .NET v1.6.4 (20). Closed service with no API changelog. Support is by email and a chat widget, and GitHub issue replies were not read (6). PHP, .NET and Python libraries are current, while Node.js last changed in May 2025 and Ruby in October 2024 (10). CI workflows and tests in the Python, .NET and Node.js repositories (6).\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## 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- unchecked: plan and package prices in euros. The pricing page draws them by script, so only the credit cost of each tool was read\n- unchecked: the iLoveAPI privacy policy. It is an iubenda document under a path iubenda's robots.txt disallows\n- unchecked: security.txt. The request answered 403\n- unchecked: rate-limit numbers per tier and the names of the rate-limit headers. No request was sent to the API\n- unchecked: maximum file size per plan, and GitHub issue response times on the library repositories\n- unchecked: whether a status page exists. None is linked from the pages read\n- Translate PDF is commented out of the API reference and the product page but ships in the PHP and Python libraries\n- The lead's 250 free files a month comes from the API reference. The pricing page says 2,500 credits a month\n\n## Weaknesses\n\n- No OpenAPI file, llms.txt or Markdown docs. The reference is one HTML page\n- No status page is linked from the site or docs, and rate limits are described as tier-dependent with no numbers\n- The API terms were last modified on 14 February 2017 and let iLovePDF discontinue the API at any time without liability\n- Uptime is stated as over 99.95% on the pricing page and 99.9%+ on the functions page, while the terms disclaim availability\n- The reference still says a free account has a 250-file monthly limit, while the pricing page says 2,500 credits\n- No idempotency keys, no scoped or read-only keys, and no guidance on untrusted text returned by OCR, Markdown or summary tools\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- Run four calls per job. `GET /v1/start/{tool}/{region}` returns a `server` and a `task`, then send upload, process and download to that server\n- Sign a JWT with the project secret key and send it as `Authorization: Bearer`. Tokens expire after one hour\n- Download results promptly. The reference says files are deleted one to two hours after processing, depending on tier\n- Back off exponentially on 429 and read the rate-limit headers on each response. No limit numbers are published\n- Add `debug=true` to any request to have the server echo the parameters without processing or spending credits\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": 42,
    "assessed": "2026-10-09",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 26,
        "maxGain": 14.8,
        "reason": "Graded as a hosted API. No status page is linked from the site, the docs or the security page (0), so there is no readable incident history (5). Rate limits are described as tier-dependent and reported in response headers, with no numbers. The open-task cap of 10% of the monthly file limit and two signature reminders a day are the only figures (3). 429 is documented with advice to back off exponentially, and failed files are not charged, but there is no Retry-After and no idempotency key (8). The pricing FAQ says the API guarantees over 99.95% uptime and the functions page says 99.9%+, with no SLA document or remedy, and the terms disclaim availability (0). Generally available (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": "security",
        "name": "Security \u0026 auth",
        "score": 41,
        "maxGain": 10.3,
        "reason": "Each project has a public and a secret key, requests carry a JWT signed with the secret that expires after one hour, and domain and IP filters exist depending on tier. No scopes (20). No read-only key or confirmation before a task is deleted, and `/auth` issues a token for the public key alone unless a domain filter is set (4). OCR, Markdown and summary output is untrusted text and the docs give no injection guidance (0). `/task` lists processed tasks and signatures have a downloadable audit trail, with no account audit log found (7). ISO/IEC 27001:2022 certificate linked and a signed security policy of 19 June 2025. security.txt answered 403, and no disclosure policy or bounty was found (10).",
        "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": "schema",
        "name": "Schema \u0026 documentation",
        "score": 37,
        "maxGain": 10.2,
        "reason": "No OpenAPI file or other machine-readable contract was found (0). `llms.txt` answered 404 and there are no Markdown docs (0). The single-page reference states what each tool and parameter does, without guidance on when not to use one (10). Parameters carry types, accepted values and defaults, such as rotation 0, 90, 180 or 270 (11). JSON response samples, an error table, and file and task status lists, with request examples mostly in the library guides (10). The path carries `/v1`. No API changelog was found, and the Python and PHP libraries keep their own (6).",
        "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": "payments",
        "name": "Payments \u0026 pricing",
        "score": 30,
        "maxGain": 8.8,
        "reason": "No x402, MPP or L402 (0). The credit cost of every tool is public without a login, but the euro price of a credit is drawn by script and was not read, so this is scored as public plan pricing (10). 2,500 free credits a month, and the sign-up form asks for name, email and password with no card field (20). A person registers in a browser to get keys (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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 61,
        "maxGain": 6.3,
        "reason": "Responses are small JSON and output arrives as a file or ZIP, but every job takes four calls and the start call's server must be reused (12). `/task` lists 50 a page with filters by tool, status and `custom_int`, and the signature list takes page and per-page (14). One error structure with type, message, code and param, plus per-file statuses such as WrongPassword and DamagedFile (14). No idempotency keys. A `debug` parameter echoes a request without processing, and a wrong password leaves the task waiting for a resend (6). Most parameters have defaults, and there are official libraries in five languages (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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 52,
        "maxGain": 4.2,
        "reason": "Closed service with terms naming iLovePDF S.L., last modified 14 February 2017, and MIT client libraries (15). The reference says files are deleted after an hour depending on tier and elsewhere after two hours, the security page says two hours and the terms say at most 48 hours. The privacy policy is an iubenda document closed to us by robots.txt and was not read (12). No deprecation policy, and the terms allow the API to be discontinued at any time (0). Seven processing regions are selectable per task and Stripe is named for payments. No subprocessor list was read (10).",
        "blend": "editorial 37, provenance 66",
        "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"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 62,
        "maxGain": 3.3,
        "reason": "The .NET library v1.6.4 was tagged on 3 September 2026, 36 days before this check (20). Three library releases in the last 90 days, PHP v1.4.1 on 22 July, Python v1.1.0 on 28 July and .NET v1.6.4 (20). Closed service with no API changelog. Support is by email and a chat widget, and GitHub issue replies were not read (6). PHP, .NET and Python libraries are current, while Node.js last changed in May 2025 and Ruby in October 2024 (10). CI workflows and tests in the Python, .NET and Node.js repositories (6).",
        "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"
      }
    ],
    "provenance": [
      {
        "label": "Terms of service",
        "value": "read, states 6 of the 7 things a reader expects",
        "points": 9.1,
        "max": 10
      },
      {
        "label": "Privacy policy",
        "value": "published, but our reader couldn't read it",
        "points": 7,
        "max": 10
      },
      {
        "label": "Status page",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "Changelog",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "could not be fetched",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "unchecked: plan and package prices in euros. The pricing page draws them by script, so only the credit cost of each tool was read",
      "unchecked: the iLoveAPI privacy policy. It is an iubenda document under a path iubenda's robots.txt disallows",
      "unchecked: security.txt. The request answered 403",
      "unchecked: rate-limit numbers per tier and the names of the rate-limit headers. No request was sent to the API",
      "unchecked: maximum file size per plan, and GitHub issue response times on the library repositories",
      "unchecked: whether a status page exists. None is linked from the pages read",
      "Translate PDF is commented out of the API reference and the product page but ships in the PHP and Python libraries",
      "The lead's 250 free files a month comes from the API reference. The pricing page says 2,500 credits a month"
    ],
    "weaknesses": [
      "No OpenAPI file, llms.txt or Markdown docs. The reference is one HTML page",
      "No status page is linked from the site or docs, and rate limits are described as tier-dependent with no numbers",
      "The API terms were last modified on 14 February 2017 and let iLovePDF discontinue the API at any time without liability",
      "Uptime is stated as over 99.95% on the pricing page and 99.9%+ on the functions page, while the terms disclaim availability",
      "The reference still says a free account has a 250-file monthly limit, while the pricing page says 2,500 credits",
      "No idempotency keys, no scoped or read-only keys, and no guidance on untrusted text returned by OCR, Markdown or summary tools"
    ],
    "agentNotes": [
      "Run four calls per job. `GET /v1/start/{tool}/{region}` returns a `server` and a `task`, then send upload, process and download to that server",
      "Sign a JWT with the project secret key and send it as `Authorization: Bearer`. Tokens expire after one hour",
      "Download results promptly. The reference says files are deleted one to two hours after processing, depending on tier",
      "Back off exponentially on 429 and read the rate-limit headers on each response. No limit numbers are published",
      "Add `debug=true` to any request to have the server echo the parameters without processing or spending credits"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-10",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}