{
  "fixes": {
    "slug": "ideogram",
    "name": "Ideogram API",
    "listing": "https://www.anchorterminal.com/tools/ideogram",
    "markdown": "# Fix list: Ideogram API\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/ideogram, the October 2026 research run, assessed 1 October 2026. Grade D, 50.3 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 Ideogram 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. Security \u0026 auth, 35 out of 100, up to 11.4 more on the total\n\nWhy it scored 35: Plain API keys, shown once, no scopes. The hosted MCP server uses OAuth with an Ideogram account (20). The $300 balance cap limits what a leaked key can spend, no read-only mode (5). Returns generated images only (10). No per-call log or audit trail found (0). No security.txt, no bug bounty and no SOC 2 or ISO 27001 statement found (0).\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## 2. 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-image prices published without a login, though the pricing page loads them with JavaScript (20). No free tier. Requests return 402 until the account has a payment method and credit (0). Browser sign-up (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. Maintenance \u0026 community, 18 out of 100, up to 7.2 more on the total\n\nWhy it scored 18: Ideogram 4.0 on 3 June 2026 is the last release we could date, 120 days ago (10). For models we look at churn and notice. Ideogram 3.0 stays on for inpainting and custom models, but there's no notice policy (5). No public changelog, support channel not tested (3). No official SDK, and the official MCP server isn't in the MCP registry (0). No packages to assess (0).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## 4. Reliability, 65 out of 100, up to 7 more on the total\n\nWhy it scored 65: Atlassian Statuspage at status.ideogram.ai with the API as its own component (20). Six API incidents in the last 90 days, all under an hour. A complete outage of 3.1 and its variants for 47 minutes on 27 July, v4 latency for 11 minutes on 16 July, v3 outages of 43, 17, 18 and 10 minutes on 4, 23, 24 and 29 September. Minor only by our line, though three in one week is a pattern to watch (20). 10 in-flight requests by default per the docs (15). We found no 429, Retry-After or backoff guidance (0). No SLA (0). Ideogram 4.0 is 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## 5. Agent ergonomics, 63 out of 100, up to 6 more on the total\n\nWhy it scored 63: Responses carry image URLs, not bytes, with a count control (20). Resolution, aspect ratio and image count controls (15). 402 for no credit, 422 for unsafe prompts and an `is_image_safe` flag per image (14). No idempotency key. Async variants with signed webhooks avoid holding calls open (6). Only the prompt is required, but there's no official SDK and requests are multipart (8).\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 32, provenance 72.\n\nWhy it scored 52: Closed API under a Developer API Agreement last revised on 14 August 2024. Ideogram 4.0 weights are public under a non-commercial licence, which doesn't change the API terms (15). The agreement says Ideogram won't train on API inputs or outputs unless they're flagged under the usage policies, but states no retention period (12). The agreement promises commercially reasonable efforts to give prior notice of changes that need developer work, and we found no dated notices (5). No subprocessor list or data locations found (0).\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- Domain age: ideogram.ai, registered 2023-02-28 (3 years) (7 of 15)\n- Changelog: not found (0 of 10)\n- security.txt: not found (0 of 10)\n\n## 7. Schema \u0026 documentation, 76 out of 100, up to 3.9 more on the total\n\nWhy it scored 76: OpenAPI spec at developer.ideogram.ai/openapi.json (25). llms.txt index, every page available as Markdown, and an MCP server for the docs themselves (10). Endpoint pages state what each does, little on when not to use one (12). Typed form fields with enums such as rendering speed, but requests are multipart form data rather than JSON (12). Examples per endpoint and a 422 for safety failures, no full error catalogue found (10). Versioned paths per model generation but no changelog (7).\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## 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 fetch budget ran out before we could re-read the pricing page, the v4 API reference and the privacy policy, so rate limits and prices rest on the listing's 2026-09-30 research.\n- Status incidents on 27 July name a '3.1' model family that the listing doesn't mention.\n- The listing said top-ups start at $1. The API setup page says one-time credits run from $10 to $300. Corrected in patch.pricingNotes.\n\n## Weaknesses\n\n- Six API incidents in 90 days, three on v3 endpoints between 23 and 29 September\n- No changelog, so model and endpoint changes aren't dated anywhere public\n- No security.txt, bug bounty or certification found, and the API agreement dates from August 2024\n- No official SDK, and requests are multipart form data\n- Inpainting and custom model training are still on Ideogram 3.0\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Send multipart form data, not JSON\n- Treat 402 as no credit or no payment method, and 422 as an unsafe prompt to rewrite, not retry\n- Check `is_image_safe`. When it's false the `url` is empty\n- Download images straight away, the links expire\n- Use the `/async/` variants with `webhook_url` for batches and verify the Ed25519 signature\n\n## What the review panel asked for\n\n- One billing balance\n- Document 429 handling\n- state whether 422 rejections bill\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": "D",
    "score": 50.3,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 35,
        "maxGain": 11.4,
        "reason": "Plain API keys, shown once, no scopes. The hosted MCP server uses OAuth with an Ideogram account (20). The $300 balance cap limits what a leaked key can spend, no read-only mode (5). Returns generated images only (10). No per-call log or audit trail found (0). No security.txt, no bug bounty and no SOC 2 or ISO 27001 statement found (0).",
        "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": "payments",
        "name": "Payments \u0026 pricing",
        "score": 20,
        "maxGain": 10,
        "reason": "No x402, MPP or L402 (0). Per-image prices published without a login, though the pricing page loads them with JavaScript (20). No free tier. Requests return 402 until the account has a payment method and credit (0). Browser sign-up (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": 18,
        "maxGain": 7.2,
        "reason": "Ideogram 4.0 on 3 June 2026 is the last release we could date, 120 days ago (10). For models we look at churn and notice. Ideogram 3.0 stays on for inpainting and custom models, but there's no notice policy (5). No public changelog, support channel not tested (3). No official SDK, and the official MCP server isn't in the MCP registry (0). No packages to assess (0).",
        "checklist": [
          "- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      },
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 65,
        "maxGain": 7,
        "reason": "Atlassian Statuspage at status.ideogram.ai with the API as its own component (20). Six API incidents in the last 90 days, all under an hour. A complete outage of 3.1 and its variants for 47 minutes on 27 July, v4 latency for 11 minutes on 16 July, v3 outages of 43, 17, 18 and 10 minutes on 4, 23, 24 and 29 September. Minor only by our line, though three in one week is a pattern to watch (20). 10 in-flight requests by default per the docs (15). We found no 429, Retry-After or backoff guidance (0). No SLA (0). Ideogram 4.0 is 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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 63,
        "maxGain": 6,
        "reason": "Responses carry image URLs, not bytes, with a count control (20). Resolution, aspect ratio and image count controls (15). 402 for no credit, 422 for unsafe prompts and an `is_image_safe` flag per image (14). No idempotency key. Async variants with signed webhooks avoid holding calls open (6). Only the prompt is required, but there's no official SDK and requests are multipart (8).",
        "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 API under a Developer API Agreement last revised on 14 August 2024. Ideogram 4.0 weights are public under a non-commercial licence, which doesn't change the API terms (15). The agreement says Ideogram won't train on API inputs or outputs unless they're flagged under the usage policies, but states no retention period (12). The agreement promises commercially reasonable efforts to give prior notice of changes that need developer work, and we found no dated notices (5). No subprocessor list or data locations found (0).",
        "blend": "editorial 32, provenance 72",
        "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": "schema",
        "name": "Schema \u0026 documentation",
        "score": 76,
        "maxGain": 3.9,
        "reason": "OpenAPI spec at developer.ideogram.ai/openapi.json (25). llms.txt index, every page available as Markdown, and an MCP server for the docs themselves (10). Endpoint pages state what each does, little on when not to use one (12). Typed form fields with enums such as rendering speed, but requests are multipart form data rather than JSON (12). Examples per endpoint and a 422 for safety failures, no full error catalogue found (10). Versioned paths per model generation but no changelog (7).",
        "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"
      }
    ],
    "provenance": [
      {
        "label": "Domain age",
        "value": "ideogram.ai, registered 2023-02-28 (3 years)",
        "points": 7,
        "max": 15
      },
      {
        "label": "Changelog",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "The fetch budget ran out before we could re-read the pricing page, the v4 API reference and the privacy policy, so rate limits and prices rest on the listing's 2026-09-30 research.",
      "Status incidents on 27 July name a '3.1' model family that the listing doesn't mention.",
      "The listing said top-ups start at $1. The API setup page says one-time credits run from $10 to $300. Corrected in patch.pricingNotes."
    ],
    "weaknesses": [
      "Six API incidents in 90 days, three on v3 endpoints between 23 and 29 September",
      "No changelog, so model and endpoint changes aren't dated anywhere public",
      "No security.txt, bug bounty or certification found, and the API agreement dates from August 2024",
      "No official SDK, and requests are multipart form data",
      "Inpainting and custom model training are still on Ideogram 3.0"
    ],
    "agentNotes": [
      "Send multipart form data, not JSON",
      "Treat 402 as no credit or no payment method, and 422 as an unsafe prompt to rewrite, not retry",
      "Check `is_image_safe`. When it's false the `url` is empty",
      "Download images straight away, the links expire",
      "Use the `/async/` variants with `webhook_url` for batches and verify the Ed25519 signature"
    ],
    "requests": [
      {
        "text": "One billing balance",
        "reviews": 1
      },
      {
        "text": "Document 429 handling",
        "reviews": 1
      },
      {
        "text": "state whether 422 rejections bill",
        "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"
  }
}