{
  "fixes": {
    "slug": "meta-model-api",
    "name": "Meta Model API",
    "listing": "https://www.anchorterminal.com/tools/meta-model-api",
    "markdown": "# Fix list: Meta Model API\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/meta-model-api, the October 2026 research run, assessed 12 October 2026. Grade D, 52.2 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 Meta Model 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: No status page with component history. The error guide's link to dev.meta.ai/status redirects to the home page, and `GET /v1/status` reports only the current state, `operational` when we called it on 12 October (0). No readable incident history (5). Rate limits published per team and per model, 3,000 RPM and 4,000,000 TPM for muse-wonder-1.0, 150 RPM for the contributor variants, 600 background submissions a minute (15). 429 and 503 carry Retry-After (60 seconds for `service_overloaded` and `backend_unavailable`), with backoff-with-jitter guidance, rate-limit headers on every token response and a documented mid-stream `server_shutting_down` event to retry (15). No SLA found, and the terms let Meta throttle or suspend access without notice (0). Muse Wonder is labelled a preview. Muse Spark 1.3 carries no preview label, but the API opened on 8 July 2026 as a public preview and we found no general-availability notice, so half (5 of 10, a departure from the all-or-nothing line).\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, 20 out of 100, up to 10 more on the total\n\nWhy it scored 20: No machine payment protocol (0). Per-token prices for Muse Wonder and Muse Spark, and per-image, per-hour and per-frame prices for the other models, published without a login (20). No free API allowance found. Billing needs a card, and Playground requests count towards usage (0). Browser sign-up with email, phone, Facebook, Google or GitHub (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. Schema \u0026 documentation, 60 out of 100, up to 6.5 more on the total\n\nWhy it scored 60: No OpenAPI or similar machine-readable contract found. The reference is Markdown pages with schema sections, and /openapi.json paths on dev.meta.ai return 404 (0). llms.txt at dev.meta.ai/llms.txt, and every docs page has a Markdown copy (10). The models page says when to choose Muse Wonder and when Muse Spark, and the tool-calling and structured-output guides state their limits, such as `tool_choice` only accepting `auto` and which schema keywords `strict` allows (16 of 20). JSON Schema tools and output, `reasoning_effort` an enum from minimal to max, a strict subset that returns 400 when violated, though `tool_choice` has one value (12 of 15). Curl, Python and TypeScript examples on each page and an error guide covering 400 to 504 with the error envelope, codes and a fix for each (15). Versioned model IDs (muse-spark-1.1 to 1.3, muse-wonder-1.0) and dated launch posts on the developer blog, but no API changelog (7 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. Security \u0026 auth, 64 out of 100, up to 6.3 more on the total\n\nWhy it scored 64: Model reading. Bearer keys per team, named, shown once and revoked by deletion, with rotation advice. No scopes, read-only keys or per-key limits found (20 of 30). The terms say Meta will not use Content submitted to the Standard Services to train Meta Models, and training applies only to the `-contributor` model IDs a caller picks. Content may still be used to develop and improve safety and security systems (17 of 20). Retention is 'as needed' for the service, the law, flagged violations and safety review, with no period stated. Zero data retention for qualified accounts through sales, with flagged content kept up to 2 years (10 of 15). The usage dashboard shows tokens and requests per day by model, with no per-key or per-call log found (5 of 15). No security.txt on dev.meta.ai. Meta's bug bounty at bugbounty.meta.com is named in the Muse Code SDK's security policy, and a security commitments page describes TLS 1.2 or later, PCI-DSS card handling and an ISMS, with no named certification for the API (12 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## 5. Maintenance \u0026 community, 46 out of 100, up to 4.7 more on the total\n\nWhy it scored 46: Model reading. Muse Wonder launched on 12 October 2026 (30). No deprecation policy or notice period found. All three Muse Spark versions are still served, so no retirement has tested one (0 of 12). Three dated launches in the last 90 days that we read, Muse Spark 1.2 on 5 August, Muse Code out of beta on 31 August and Muse Wonder on 12 October (8 of 8). No Model API changelog. A help centre with support tickets, answered 'typically within two business days' by Meta's own account, which we didn't test (8 of 15). No SDK of Meta's own for the API (0 of 15, 0 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## 6. Transparency \u0026 trust, 52 out of 100, up to 4.2 more on the total\n\nMade of editorial 41, provenance 63.\n\nWhy it scored 52: Closed service with clear terms, under California law with AAA arbitration for Meta Platforms, Inc. and Irish law and courts for Meta Platforms Ireland Limited, with liability capped at the greater of 12 months of fees or $1,000. Muse Glimmer's open weights don't change the hosted service (15). The terms, the models page, the pricing page and the zero-retention help page agree that Standard content isn't used for training and Contributor content may be, but retention periods are not stated outside zero retention, and the privacy policy is Meta's general one (18 of 30). No deprecation policy or dated notices found, and the terms let Meta remove functionality without notice (0). A subprocessor list is linked from the terms but wasn't read, and no data locations were found (8 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Domain age: meta.ai, registered 2017-12-16 (8 years) (11 of 15)\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: not found (0 of 10)\n\n## 7. Agent ergonomics, 75 out of 100, up to 4.1 more on the total\n\nWhy it scored 75: Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool calls on all three endpoints, parallel calls, tool search with deferred loading, built-in web search and a computer-use tool, but `tool_choice` accepts only `auto`, so a call can't be forced or forbidden (15 of 20). Output constrained to the JSON Schema on every surface (15). Automatic prompt caching with no setup, and cached input at 5 per cent of the input price on Muse Wonder (15). 1,048,576-token context on Muse Wonder and every Muse Spark version, with no long-context premium (15). No batch endpoint or discount found. Background responses run asynchronously at the normal price (0). No SDK of Meta's own. The docs use the OpenAI and Anthropic SDKs against compatible endpoints, the same reading as StepFun (0). OpenAI-style error envelope with `type` and `code`, per-status fixes and named retryable codes (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## 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: whether an API call works before a card is added. The help centre says an admin adds a payment method to set up billing, and no free allowance is named\n- unchecked: the subprocessor list at forwork.meta.com/legal/mfw-subprocessor-list/ and the Meta Global Processor Terms, not read, and the Meta Privacy Policy, which www.facebook.com's robots.txt asks readers like ours not to fetch\n- unchecked: www.meta.ai/.well-known/security.txt. www.meta.ai's robots.txt disallows ClaudeBot from every path, so it wasn't requested\n- Whether the API itself is generally available. The 8 July 2026 launch called it a public preview, the docs now label only Muse Wonder a preview, and no GA notice was found\n- When Muse Spark 1.3 was released. The docs call it the latest version, and no dated page for it was found\n- No authenticated call was made. That `muse-wonder-1.0` answers on api.meta.ai rests on the models, pricing and rate-limit pages, which list it\n- No Meta Model API listing existed before. This listing covers the whole API with Muse Wonder as its flagship model, in line with the other model-vendor APIs in this category. llama-guard and llamafirewall are Meta's open-weight safety models and stay separate\n\n## Weaknesses\n\n- Muse Wonder is labelled a preview, and no deprecation policy or notice period was found\n- No free API allowance found, and billing is set up with a card\n- No status page with history. The docs' status link redirects to the home page, and `/v1/status` reports only the current state\n- `tool_choice` accepts only `auto`, so a call can't be forced or ruled out\n- No OpenAPI file, batch endpoint or Model API changelog found, and API keys have no scopes\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 `muse-wonder-1.0` for long multi-step work and `muse-spark-1.3` for cheaper, high-volume calls. Both take the same requests\n- Keep personal or confidential data away from `-contributor` model IDs. Meta may train on that content\n- Honour Retry-After on 429 and 503, which is 60 seconds for `service_overloaded`, and check `GET https://api.meta.ai/v1/status`, which needs no key\n- Pass the key to the OpenAI SDK explicitly or set `OPENAI_API_KEY`. The SDK doesn't read `MODEL_API_KEY`\n- Leave `tool_choice` at `auto`. The docs say `none` and `required` are not supported\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": 52.2,
    "assessed": "2026-10-12",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 40,
        "maxGain": 12,
        "reason": "No status page with component history. The error guide's link to dev.meta.ai/status redirects to the home page, and `GET /v1/status` reports only the current state, `operational` when we called it on 12 October (0). No readable incident history (5). Rate limits published per team and per model, 3,000 RPM and 4,000,000 TPM for muse-wonder-1.0, 150 RPM for the contributor variants, 600 background submissions a minute (15). 429 and 503 carry Retry-After (60 seconds for `service_overloaded` and `backend_unavailable`), with backoff-with-jitter guidance, rate-limit headers on every token response and a documented mid-stream `server_shutting_down` event to retry (15). No SLA found, and the terms let Meta throttle or suspend access without notice (0). Muse Wonder is labelled a preview. Muse Spark 1.3 carries no preview label, but the API opened on 8 July 2026 as a public preview and we found no general-availability notice, so half (5 of 10, a departure from the all-or-nothing line).",
        "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": 20,
        "maxGain": 10,
        "reason": "No machine payment protocol (0). Per-token prices for Muse Wonder and Muse Spark, and per-image, per-hour and per-frame prices for the other models, published without a login (20). No free API allowance found. Billing needs a card, and Playground requests count towards usage (0). Browser sign-up with email, phone, Facebook, Google or GitHub (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": "schema",
        "name": "Schema \u0026 documentation",
        "score": 60,
        "maxGain": 6.5,
        "reason": "No OpenAPI or similar machine-readable contract found. The reference is Markdown pages with schema sections, and /openapi.json paths on dev.meta.ai return 404 (0). llms.txt at dev.meta.ai/llms.txt, and every docs page has a Markdown copy (10). The models page says when to choose Muse Wonder and when Muse Spark, and the tool-calling and structured-output guides state their limits, such as `tool_choice` only accepting `auto` and which schema keywords `strict` allows (16 of 20). JSON Schema tools and output, `reasoning_effort` an enum from minimal to max, a strict subset that returns 400 when violated, though `tool_choice` has one value (12 of 15). Curl, Python and TypeScript examples on each page and an error guide covering 400 to 504 with the error envelope, codes and a fix for each (15). Versioned model IDs (muse-spark-1.1 to 1.3, muse-wonder-1.0) and dated launch posts on the developer blog, but no API changelog (7 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": "security",
        "name": "Security \u0026 auth",
        "score": 64,
        "maxGain": 6.3,
        "reason": "Model reading. Bearer keys per team, named, shown once and revoked by deletion, with rotation advice. No scopes, read-only keys or per-key limits found (20 of 30). The terms say Meta will not use Content submitted to the Standard Services to train Meta Models, and training applies only to the `-contributor` model IDs a caller picks. Content may still be used to develop and improve safety and security systems (17 of 20). Retention is 'as needed' for the service, the law, flagged violations and safety review, with no period stated. Zero data retention for qualified accounts through sales, with flagged content kept up to 2 years (10 of 15). The usage dashboard shows tokens and requests per day by model, with no per-key or per-call log found (5 of 15). No security.txt on dev.meta.ai. Meta's bug bounty at bugbounty.meta.com is named in the Muse Code SDK's security policy, and a security commitments page describes TLS 1.2 or later, PCI-DSS card handling and an ISMS, with no named certification for the API (12 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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 46,
        "maxGain": 4.7,
        "reason": "Model reading. Muse Wonder launched on 12 October 2026 (30). No deprecation policy or notice period found. All three Muse Spark versions are still served, so no retirement has tested one (0 of 12). Three dated launches in the last 90 days that we read, Muse Spark 1.2 on 5 August, Muse Code out of beta on 31 August and Muse Wonder on 12 October (8 of 8). No Model API changelog. A help centre with support tickets, answered 'typically within two business days' by Meta's own account, which we didn't test (8 of 15). No SDK of Meta's own for the API (0 of 15, 0 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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 52,
        "maxGain": 4.2,
        "reason": "Closed service with clear terms, under California law with AAA arbitration for Meta Platforms, Inc. and Irish law and courts for Meta Platforms Ireland Limited, with liability capped at the greater of 12 months of fees or $1,000. Muse Glimmer's open weights don't change the hosted service (15). The terms, the models page, the pricing page and the zero-retention help page agree that Standard content isn't used for training and Contributor content may be, but retention periods are not stated outside zero retention, and the privacy policy is Meta's general one (18 of 30). No deprecation policy or dated notices found, and the terms let Meta remove functionality without notice (0). A subprocessor list is linked from the terms but wasn't read, and no data locations were found (8 of 20).",
        "blend": "editorial 41, provenance 63",
        "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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 75,
        "maxGain": 4.1,
        "reason": "Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). Tool calls on all three endpoints, parallel calls, tool search with deferred loading, built-in web search and a computer-use tool, but `tool_choice` accepts only `auto`, so a call can't be forced or forbidden (15 of 20). Output constrained to the JSON Schema on every surface (15). Automatic prompt caching with no setup, and cached input at 5 per cent of the input price on Muse Wonder (15). 1,048,576-token context on Muse Wonder and every Muse Spark version, with no long-context premium (15). No batch endpoint or discount found. Background responses run asynchronously at the normal price (0). No SDK of Meta's own. The docs use the OpenAI and Anthropic SDKs against compatible endpoints, the same reading as StepFun (0). OpenAI-style error envelope with `type` and `code`, per-status fixes and named retryable codes (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"
      }
    ],
    "provenance": [
      {
        "label": "Domain age",
        "value": "meta.ai, registered 2017-12-16 (8 years)",
        "points": 11,
        "max": 15
      },
      {
        "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": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "unchecked: whether an API call works before a card is added. The help centre says an admin adds a payment method to set up billing, and no free allowance is named",
      "unchecked: the subprocessor list at forwork.meta.com/legal/mfw-subprocessor-list/ and the Meta Global Processor Terms, not read, and the Meta Privacy Policy, which www.facebook.com's robots.txt asks readers like ours not to fetch",
      "unchecked: www.meta.ai/.well-known/security.txt. www.meta.ai's robots.txt disallows ClaudeBot from every path, so it wasn't requested",
      "Whether the API itself is generally available. The 8 July 2026 launch called it a public preview, the docs now label only Muse Wonder a preview, and no GA notice was found",
      "When Muse Spark 1.3 was released. The docs call it the latest version, and no dated page for it was found",
      "No authenticated call was made. That `muse-wonder-1.0` answers on api.meta.ai rests on the models, pricing and rate-limit pages, which list it",
      "No Meta Model API listing existed before. This listing covers the whole API with Muse Wonder as its flagship model, in line with the other model-vendor APIs in this category. llama-guard and llamafirewall are Meta's open-weight safety models and stay separate"
    ],
    "weaknesses": [
      "Muse Wonder is labelled a preview, and no deprecation policy or notice period was found",
      "No free API allowance found, and billing is set up with a card",
      "No status page with history. The docs' status link redirects to the home page, and `/v1/status` reports only the current state",
      "`tool_choice` accepts only `auto`, so a call can't be forced or ruled out",
      "No OpenAPI file, batch endpoint or Model API changelog found, and API keys have no scopes"
    ],
    "agentNotes": [
      "Use `muse-wonder-1.0` for long multi-step work and `muse-spark-1.3` for cheaper, high-volume calls. Both take the same requests",
      "Keep personal or confidential data away from `-contributor` model IDs. Meta may train on that content",
      "Honour Retry-After on 429 and 503, which is 60 seconds for `service_overloaded`, and check `GET https://api.meta.ai/v1/status`, which needs no key",
      "Pass the key to the OpenAI SDK explicitly or set `OPENAI_API_KEY`. The SDK doesn't read `MODEL_API_KEY`",
      "Leave `tool_choice` at `auto`. The docs say `none` and `required` are not supported"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-12",
    "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"
  }
}