{
  "fixes": {
    "slug": "gemini-api",
    "name": "Gemini Developer API",
    "listing": "https://www.anchorterminal.com/tools/gemini-api",
    "markdown": "# Fix list: Gemini Developer API\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/gemini-api, the October 2026 research run, assessed 1 October 2026. Grade B, 62 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 Gemini Developer 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, 40 out of 100, up to 12 more on the total\n\nWhy it scored 40: Status page at aistudio.google.com/status, but it renders in the browser and we couldn't read any history from it (10 of 20, and 5 for the incident line with no readable record). Per-model limits live in AI Studio, the public page publishes tier rules and batch queue limits only (5 of 15). Troubleshooting guide gives exponential backoff with jitter for 429 RESOURCE_EXHAUSTED and 503, and the Python SDK retries four times (15). No SLA found for the Developer API (0). The default model 3.8 Flash is GA, but the endpoint is `v1beta` and the only Pro model is a preview (5 of 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, 40 out of 100, up to 7.5 more on the total\n\nWhy it scored 40: No machine payment protocol (0). Per-token prices published without a login (20). Free tier on 3.8 Flash and Flash-Lite, and the rate-limits page puts linking a billing account at Tier 1, so the free tier needs no card (20). A Google account and AI Studio are needed for a key (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, 60 out of 100, up to 7 more on the total\n\nWhy it scored 60: Model reading. Keys live in a Cloud project, can be restricted to the Gemini API and by IP or origin, and unrestricted keys are rejected after 28 May 2026. Disable and replace on leak. No permission scopes, so 25 of 30. No query-string key in the key docs. Free-tier prompts and responses are used to improve Google products and human reviewers may read them, paid tier isn't used (10 of 20). Abuse monitoring on paid services is kept 'a limited period' with no number, grounding data 30 days, opt-in logs up to 55 days, and no zero-retention route on this API was found (5 of 15). Opt-in request logs in AI Studio for billed projects (15). security.txt valid per the listing's provenance check. No certification for the Developer API found this run (5 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. Schema \u0026 documentation, 65 out of 100, up to 5.7 more on the total\n\nWhy it scored 65: No OpenAPI document found, and we didn't check for a Discovery document in this run (0). llms.txt at ai.google.dev/gemini-api/docs/llms.txt (10). Reference not read in full this run, and the changelog names the recommended models for new projects (15 of 20). Structured output accepts JSON Schema with enums, `minimum`, `maximum` and `$ref`, but the page asks you to validate and doesn't promise constrained decoding (10 of 15). Examples on every guide and an API errors page with HTTP, blocked and content codes (15). Dated changelog and model versions (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## 5. Agent ergonomics, 85 out of 100, up to 2.4 more on the total\n\nWhy it scored 85: Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Function calling documented, forcing modes not checked this run (15 of 20). Structured output without a stated guarantee (10 of 15). Context caching at 0.1x input, $0.075 per million on 3.8 Flash until 31 December (15). 1,048,576-token context on the default model (15). Batch half price (10). Official SDKs for Python and JavaScript (10). Documented error codes with backoff guidance (10 of 15, because 400, 402 and 403 are flagged as not retryable but recovery advice per code sits on a separate page we only skimmed).\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, 78 out of 100, up to 1.9 more on the total\n\nMade of editorial 55, provenance 100.\n\nWhy it scored 78: Closed service with clear terms, SDKs Apache-2.0 (15). Terms, pricing page and logs policy agree that free-tier data improves Google products and paid data doesn't, but abuse retention on paid services has no number (20 of 30). Deprecations table with earliest shutdown dates, exact dates promised later (15 of 20). Terms say data may be cached in any country where Google has facilities. No subprocessor list checked (5 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## 7. Maintenance \u0026 community, 83 out of 100, up to 1.5 more on the total\n\nWhy it scored 83: Model reading. 3.8 Flash TTS and Flash-Lite TTS went GA on 22 September (30). The deprecations page lists earliest possible shutdown dates and promises advance notice, with no stated minimum (4 of 12). Two shutdown dates in the last 90 days, Imagen 4 on 17 August and Robotics ER 1.6 on 31 August (4 of 8). Dated changelog several times a month (15 of 15). SDK repository replies not sampled (5 of 10). Current official SDKs, `google-genai` 2.25.0 on 22 September (15). Supported runtimes stated, Python 3.10 to 3.14 (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## 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- We couldn't read incident history from the status page, so reliability carries the no-history score\n- Whether a Discovery document for generativelanguage.googleapis.com counts as a public contract. Not checked this run\n- Which certifications cover the Developer API, as distinct from Vertex AI\n- Whether function calling can force a tool on the 3.x models. Not checked this run\n- The listing's `gemini-2.5-flash-image` shutdown on 2026-10-02 didn't appear in the deprecations table we read\n\n## Weaknesses\n\n- Free-tier prompts and responses improve Google products and may be read by human reviewers\n- Per-model rate limits are only visible inside AI Studio\n- No SLA and no zero-retention route found for the Developer API\n- The only Pro model, `gemini-3.1-pro-preview`, is a preview and isn't on the free tier\n- Shutdown dates are 'earliest possible' with no stated minimum notice\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- Never send customer data through a free-tier key. Link billing first\n- Budget 3.8 Flash at $1.50/$7.50 from 2027-01-01, not the introductory price\n- Back off exponentially on 429 RESOURCE_EXHAUSTED and 503, and don't retry 400, 402 or 403\n- Stop sending temperature, top_p and top_k. They've been deprecated since 2026-07-21\n- Validate structured output yourself. The docs don't promise schema-constrained decoding\n\n## What the review panel asked for\n\n- a stated minimum notice period\n- Publish per-model limits\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": 62,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 40,
        "maxGain": 12,
        "reason": "Status page at aistudio.google.com/status, but it renders in the browser and we couldn't read any history from it (10 of 20, and 5 for the incident line with no readable record). Per-model limits live in AI Studio, the public page publishes tier rules and batch queue limits only (5 of 15). Troubleshooting guide gives exponential backoff with jitter for 429 RESOURCE_EXHAUSTED and 503, and the Python SDK retries four times (15). No SLA found for the Developer API (0). The default model 3.8 Flash is GA, but the endpoint is `v1beta` and the only Pro model is a preview (5 of 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": 40,
        "maxGain": 7.5,
        "reason": "No machine payment protocol (0). Per-token prices published without a login (20). Free tier on 3.8 Flash and Flash-Lite, and the rate-limits page puts linking a billing account at Tier 1, so the free tier needs no card (20). A Google account and AI Studio are needed for a key (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": 60,
        "maxGain": 7,
        "reason": "Model reading. Keys live in a Cloud project, can be restricted to the Gemini API and by IP or origin, and unrestricted keys are rejected after 28 May 2026. Disable and replace on leak. No permission scopes, so 25 of 30. No query-string key in the key docs. Free-tier prompts and responses are used to improve Google products and human reviewers may read them, paid tier isn't used (10 of 20). Abuse monitoring on paid services is kept 'a limited period' with no number, grounding data 30 days, opt-in logs up to 55 days, and no zero-retention route on this API was found (5 of 15). Opt-in request logs in AI Studio for billed projects (15). security.txt valid per the listing's provenance check. No certification for the Developer API found this run (5 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": "schema",
        "name": "Schema \u0026 documentation",
        "score": 65,
        "maxGain": 5.7,
        "reason": "No OpenAPI document found, and we didn't check for a Discovery document in this run (0). llms.txt at ai.google.dev/gemini-api/docs/llms.txt (10). Reference not read in full this run, and the changelog names the recommended models for new projects (15 of 20). Structured output accepts JSON Schema with enums, `minimum`, `maximum` and `$ref`, but the page asks you to validate and doesn't promise constrained decoding (10 of 15). Examples on every guide and an API errors page with HTTP, blocked and content codes (15). Dated changelog and model versions (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": 85,
        "maxGain": 2.4,
        "reason": "Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Function calling documented, forcing modes not checked this run (15 of 20). Structured output without a stated guarantee (10 of 15). Context caching at 0.1x input, $0.075 per million on 3.8 Flash until 31 December (15). 1,048,576-token context on the default model (15). Batch half price (10). Official SDKs for Python and JavaScript (10). Documented error codes with backoff guidance (10 of 15, because 400, 402 and 403 are flagged as not retryable but recovery advice per code sits on a separate page we only skimmed).",
        "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": 78,
        "maxGain": 1.9,
        "reason": "Closed service with clear terms, SDKs Apache-2.0 (15). Terms, pricing page and logs policy agree that free-tier data improves Google products and paid data doesn't, but abuse retention on paid services has no number (20 of 30). Deprecations table with earliest shutdown dates, exact dates promised later (15 of 20). Terms say data may be cached in any country where Google has facilities. No subprocessor list checked (5 of 20).",
        "blend": "editorial 55, 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"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 83,
        "maxGain": 1.5,
        "reason": "Model reading. 3.8 Flash TTS and Flash-Lite TTS went GA on 22 September (30). The deprecations page lists earliest possible shutdown dates and promises advance notice, with no stated minimum (4 of 12). Two shutdown dates in the last 90 days, Imagen 4 on 17 August and Robotics ER 1.6 on 31 August (4 of 8). Dated changelog several times a month (15 of 15). SDK repository replies not sampled (5 of 10). Current official SDKs, `google-genai` 2.25.0 on 22 September (15). Supported runtimes stated, Python 3.10 to 3.14 (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"
      }
    ],
    "unchecked": [
      "We couldn't read incident history from the status page, so reliability carries the no-history score",
      "Whether a Discovery document for generativelanguage.googleapis.com counts as a public contract. Not checked this run",
      "Which certifications cover the Developer API, as distinct from Vertex AI",
      "Whether function calling can force a tool on the 3.x models. Not checked this run",
      "The listing's `gemini-2.5-flash-image` shutdown on 2026-10-02 didn't appear in the deprecations table we read"
    ],
    "weaknesses": [
      "Free-tier prompts and responses improve Google products and may be read by human reviewers",
      "Per-model rate limits are only visible inside AI Studio",
      "No SLA and no zero-retention route found for the Developer API",
      "The only Pro model, `gemini-3.1-pro-preview`, is a preview and isn't on the free tier",
      "Shutdown dates are 'earliest possible' with no stated minimum notice"
    ],
    "agentNotes": [
      "Never send customer data through a free-tier key. Link billing first",
      "Budget 3.8 Flash at $1.50/$7.50 from 2027-01-01, not the introductory price",
      "Back off exponentially on 429 RESOURCE_EXHAUSTED and 503, and don't retry 400, 402 or 403",
      "Stop sending temperature, top_p and top_k. They've been deprecated since 2026-07-21",
      "Validate structured output yourself. The docs don't promise schema-constrained decoding"
    ],
    "requests": [
      {
        "text": "a stated minimum notice period",
        "reviews": 1
      },
      {
        "text": "Publish per-model limits",
        "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"
  }
}