{
  "fixes": {
    "slug": "google-cloud-translation",
    "name": "Google Cloud Translation",
    "listing": "https://www.anchorterminal.com/tools/google-cloud-translation",
    "markdown": "# Fix list: Google Cloud Translation\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/google-cloud-translation, the October 2026 research run, assessed 1 October 2026. Grade B, 68.2 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 Google Cloud Translation: 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. Payments \u0026 pricing, 20 out of 100, up to 10 more on the total\n\nWhy it scored 20: No x402, MPP or L402 (0). Per-million-character and per-page prices for every model published without a login (20). A $10 monthly credit covers 500,000 NMT characters, but a billing account needs a card (0). A person signs up in a browser (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## 2. Maintenance \u0026 community, 38 out of 100, up to 5.4 more on the total\n\nWhy it scored 38: Read as a closed service. The newest release note is Translation LLM fine-tuning with LoRA on 2026-02-24. The SDK changelog shows a later API change, a `mime_type` field on adaptive translation requests in 3.26.0 on 2026-04-09, within 180 days (10). One release in the last 90 days, `google-cloud-translate` 3.28.0 on 2026-10-01, which only declares Python 3.15 support (0). Release notes, Google Cloud support and the public issue tracker exist, but the notes have had one entry in the past year (8 of 15). Official client libraries current, Python for 3.10 to 3.15 (15). Libraries regenerate in the googleapis monorepos, CI not checked (5 of 10).\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## 3. Schema \u0026 documentation, 70 out of 100, up to 4.9 more on the total\n\nWhy it scored 70: A public Discovery document for v3 (revision 20260901) and the protos behind the SDKs form the machine-readable contract (25). No llms.txt at docs.cloud.google.com/translate (0). The docs explain Basic against Advanced and NMT against the Translation LLM and adaptive translation, but not when to avoid each (15 of 20). Types and required fields in the Discovery document, but `model` is a resource path string and `mimeType` a free string rather than enums (10 of 15). REST pages carry examples and the quotas page documents the 403 messages, with errors otherwise in Google's generic error model (10 of 15). Versioned v2 and v3 and a release notes page, but the notes skip changes the SDK changelog shows, such as RefineText in November 2025 and an adaptive `mime_type` field in April 2026 (10 of 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## 4. Agent ergonomics, 74 out of 100, up to 4.2 more on the total\n\nWhy it scored 74: API reading of the checklist. Responses hold the translations and detected language, and a glossary call returns both the glossary and plain translations, which doubles the output (20 of 25). Many strings per request (128 on v2), glossary listing with page size, token and filter, batch jobs to Cloud Storage (18 of 20). Errors use Google's status and message format, but quota errors arrive as 403, so generic 429 retry logic misses them (12 of 20). Stateless translation and long-running batch operations, with no retry guidance on the quotas page (12 of 20). v3 needs a project and location path and treats input as HTML unless `mimeType` says otherwise. Client libraries in seven or more languages (12 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. Security \u0026 auth, 80 out of 100, up to 3.5 more on the total\n\nWhy it scored 80: Model reading of the checklist, with training and retention in place of the least-privilege and injection lines. Advanced (v3) uses OAuth 2.0 from service accounts or Application Default Credentials, with a `cloud-translation` scope and IAM roles (30), less 10 because Basic (v2) documents the API key as a `key` query parameter (20). Google says it doesn't use content sent to the API for training and won't share it with third parties (20). Text is held in memory only for the request. Glossaries are stored in your project, and Basic's global endpoint can't keep processing in one region (15). Cloud Audit Logs cover Google Cloud APIs, Translation-specific log types not checked (10 of 15). google.com's security.txt is valid to 2030 per the 30 September check. Google's reward programme and Cloud compliance reports weren't re-checked in this run (15 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## 6. Reliability, 90 out of 100, up to 2 more on the total\n\nWhy it scored 90: Google Cloud status page with a JSON incident feed (20). No incident in the feed between July and September 2026 names Cloud Translation. The regional ones we saw (europe-west4 on 15 July, us-west1 on 20 August, us-central1 on 1 September) list other products, and the public page shows only broad incidents (30). Quotas published with numbers, 6,000,000 characters a minute per project, 300,000 requests a minute on v2, 6,000 on v3 and 900 for the Translation LLM (15). Quota breaches come back as 403 with Daily Limit Exceeded or User Rate Limit Exceeded rather than 429, and the quotas page gives no retry or backoff advice. Translation is stateless and only successful translations bill, so a retry is safe (5 of 15). 99.9 per cent monthly SLA for Basic, Advanced and AutoML Translation (10). Basic and Advanced are GA (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## 7. Transparency \u0026 trust, 80 out of 100, up to 1.8 more on the total\n\nMade of editorial 60, provenance 100.\n\nWhy it scored 80: Closed service under the Google Cloud terms, client libraries under Apache-2.0 (15). The data usage FAQ agrees with the terms on in-memory processing, no training and no sharing, but doesn't cover the Translation LLM or adaptive translation (25 of 30). The only dated removals in the release notes are from 2017 and 2021, and we found no Translation-specific deprecation policy (5 of 20). Regional endpoints on Advanced for data location, global-only on Basic. Google Cloud's sub-processor list wasn't re-checked (15 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\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- The patch moves `lastRelease` to 2026-04-09, the last API change we found (in the Python client changelog). The release notes page stops at 2026-02-24.\n- Our reader may have seen only part of the status incident feed. Nothing in what it read named Cloud Translation.\n- unchecked: data handling for the Translation LLM and adaptive translation, which the data usage FAQ doesn't cover.\n\n## Weaknesses\n\n- Basic (v2) documents the API key as a URL query parameter\n- Quota errors come back as 403, not 429\n- No formality control, no MCP server and no llms.txt\n- Release notes have one entry in the past year and miss API changes the SDKs show\n- Tags and whitespace count as billed characters\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- Use v2 with an API key for plain text and v3 for glossaries, documents and the Translation LLM\n- Set `mimeType` to text/plain on v3 when the input isn't HTML\n- Back off on 403 User Rate Limit Exceeded as you would on a 429\n- Leave the source language empty rather than calling detect first, since detection with translation is free\n- Keep requests near 5,000 characters. v3 rejects more than 30,000 code points\n\n## What the review panel asked for\n\n- Add a no-card free route\n- complete release notes\n- 429 for quota errors\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": "B",
    "score": 68.2,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 20,
        "maxGain": 10,
        "reason": "No x402, MPP or L402 (0). Per-million-character and per-page prices for every model published without a login (20). A $10 monthly credit covers 500,000 NMT characters, but a billing account needs a card (0). A person signs up in a browser (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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 38,
        "maxGain": 5.4,
        "reason": "Read as a closed service. The newest release note is Translation LLM fine-tuning with LoRA on 2026-02-24. The SDK changelog shows a later API change, a `mime_type` field on adaptive translation requests in 3.26.0 on 2026-04-09, within 180 days (10). One release in the last 90 days, `google-cloud-translate` 3.28.0 on 2026-10-01, which only declares Python 3.15 support (0). Release notes, Google Cloud support and the public issue tracker exist, but the notes have had one entry in the past year (8 of 15). Official client libraries current, Python for 3.10 to 3.15 (15). Libraries regenerate in the googleapis monorepos, CI not checked (5 of 10).",
        "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": "schema",
        "name": "Schema \u0026 documentation",
        "score": 70,
        "maxGain": 4.9,
        "reason": "A public Discovery document for v3 (revision 20260901) and the protos behind the SDKs form the machine-readable contract (25). No llms.txt at docs.cloud.google.com/translate (0). The docs explain Basic against Advanced and NMT against the Translation LLM and adaptive translation, but not when to avoid each (15 of 20). Types and required fields in the Discovery document, but `model` is a resource path string and `mimeType` a free string rather than enums (10 of 15). REST pages carry examples and the quotas page documents the 403 messages, with errors otherwise in Google's generic error model (10 of 15). Versioned v2 and v3 and a release notes page, but the notes skip changes the SDK changelog shows, such as RefineText in November 2025 and an adaptive `mime_type` field in April 2026 (10 of 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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 74,
        "maxGain": 4.2,
        "reason": "API reading of the checklist. Responses hold the translations and detected language, and a glossary call returns both the glossary and plain translations, which doubles the output (20 of 25). Many strings per request (128 on v2), glossary listing with page size, token and filter, batch jobs to Cloud Storage (18 of 20). Errors use Google's status and message format, but quota errors arrive as 403, so generic 429 retry logic misses them (12 of 20). Stateless translation and long-running batch operations, with no retry guidance on the quotas page (12 of 20). v3 needs a project and location path and treats input as HTML unless `mimeType` says otherwise. Client libraries in seven or more languages (12 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": "security",
        "name": "Security \u0026 auth",
        "score": 80,
        "maxGain": 3.5,
        "reason": "Model reading of the checklist, with training and retention in place of the least-privilege and injection lines. Advanced (v3) uses OAuth 2.0 from service accounts or Application Default Credentials, with a `cloud-translation` scope and IAM roles (30), less 10 because Basic (v2) documents the API key as a `key` query parameter (20). Google says it doesn't use content sent to the API for training and won't share it with third parties (20). Text is held in memory only for the request. Glossaries are stored in your project, and Basic's global endpoint can't keep processing in one region (15). Cloud Audit Logs cover Google Cloud APIs, Translation-specific log types not checked (10 of 15). google.com's security.txt is valid to 2030 per the 30 September check. Google's reward programme and Cloud compliance reports weren't re-checked in this run (15 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": "reliability",
        "name": "Reliability",
        "score": 90,
        "maxGain": 2,
        "reason": "Google Cloud status page with a JSON incident feed (20). No incident in the feed between July and September 2026 names Cloud Translation. The regional ones we saw (europe-west4 on 15 July, us-west1 on 20 August, us-central1 on 1 September) list other products, and the public page shows only broad incidents (30). Quotas published with numbers, 6,000,000 characters a minute per project, 300,000 requests a minute on v2, 6,000 on v3 and 900 for the Translation LLM (15). Quota breaches come back as 403 with Daily Limit Exceeded or User Rate Limit Exceeded rather than 429, and the quotas page gives no retry or backoff advice. Translation is stateless and only successful translations bill, so a retry is safe (5 of 15). 99.9 per cent monthly SLA for Basic, Advanced and AutoML Translation (10). Basic and Advanced are GA (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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 80,
        "maxGain": 1.8,
        "reason": "Closed service under the Google Cloud terms, client libraries under Apache-2.0 (15). The data usage FAQ agrees with the terms on in-memory processing, no training and no sharing, but doesn't cover the Translation LLM or adaptive translation (25 of 30). The only dated removals in the release notes are from 2017 and 2021, and we found no Translation-specific deprecation policy (5 of 20). Regional endpoints on Advanced for data location, global-only on Basic. Google Cloud's sub-processor list wasn't re-checked (15 of 20).",
        "blend": "editorial 60, provenance 100",
        "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"
      }
    ],
    "unchecked": [
      "The patch moves `lastRelease` to 2026-04-09, the last API change we found (in the Python client changelog). The release notes page stops at 2026-02-24.",
      "Our reader may have seen only part of the status incident feed. Nothing in what it read named Cloud Translation.",
      "unchecked: data handling for the Translation LLM and adaptive translation, which the data usage FAQ doesn't cover."
    ],
    "weaknesses": [
      "Basic (v2) documents the API key as a URL query parameter",
      "Quota errors come back as 403, not 429",
      "No formality control, no MCP server and no llms.txt",
      "Release notes have one entry in the past year and miss API changes the SDKs show",
      "Tags and whitespace count as billed characters"
    ],
    "agentNotes": [
      "Use v2 with an API key for plain text and v3 for glossaries, documents and the Translation LLM",
      "Set `mimeType` to text/plain on v3 when the input isn't HTML",
      "Back off on 403 User Rate Limit Exceeded as you would on a 429",
      "Leave the source language empty rather than calling detect first, since detection with translation is free",
      "Keep requests near 5,000 characters. v3 rejects more than 30,000 code points"
    ],
    "requests": [
      {
        "text": "Add a no-card free route",
        "reviews": 1
      },
      {
        "text": "complete release notes",
        "reviews": 1
      },
      {
        "text": "429 for quota errors",
        "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"
  }
}