{
  "fixes": {
    "slug": "luma",
    "name": "Luma AI API",
    "listing": "https://www.anchorterminal.com/tools/luma",
    "markdown": "# Fix list: Luma AI API\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/luma, the October 2026 research run, assessed 1 October 2026. Grade D, 48.7 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 Luma AI 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, 50 out of 100, up to 10 more on the total\n\nWhy it scored 50: Better Stack status page at status.lumalabs.ai with API, Dream Machine and Luma Agents components and 90 days of history (20). Six incidents since 16 July. Ray2 Flash was degraded for 7 hours on 16 July and 2 hours each on 2 and 3 September, Ray2 queue times ran long for 12 hours on 15 September, and authentication was degraded for 1 hour 45 minutes on 17 September through an upstream provider. The Ray2 incidents hit legacy models, the authentication one hit everything, so one major (10). Limits are per minute and per concurrent job, but the numbers sit in the dashboard, not the docs (5). Every 429 carries Retry-After, with separate bodies for the per-minute and concurrency limits and backoff guidance with jitter (15). No SLA found. Provisioned Throughput buys capacity, not an uptime promise (0). The pricing page says video rates may change before general availability, so the video surface isn't GA yet (0).\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 x402, MPP or L402 (0). Per-clip prices in dollars are published without a login, $0.30 for a 5 second 720p clip (20). No free tier, pay as you go from the first call (0). A person signs up in the platform and creates the 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. Schema \u0026 documentation, 43 out of 100, up to 9.3 more on the total\n\nWhy it scored 43: No public OpenAPI document for the Agents API (0). docs.agents.lumalabs.ai/llms.txt returns 404 (0). Guides cover generation, keyframes, edit, extend, reframe and the migration, and say which options don't combine, such as start and end frames with 10 second clips (14). Typed fields for model, type, resolution and duration with fixed values (12). curl examples, both 429 bodies and generation failure codes are documented (12). Responses carry an X-API-Version header, but the only public changelog is the legacy one, last updated more than a year ago (5).\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, 48 out of 100, up to 9.1 more on the total\n\nWhy it scored 48: Model reading of the checklist (credential, training, retention, operator visibility, programme). Bearer keys created in the platform and shown once, with quota and limits shared by all keys of a client. No scopes found (20). The API terms of 28 April 2026 say Luma won't use API inputs or outputs to train or develop its models (20). No retention period for inputs or outputs and no deletion call found (0). Rate-limit headers, a request id per call and usage in the dashboard, no audit log found (8). No security.txt, bug bounty or certification found for Luma AI (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## 5. Agent ergonomics, 66 out of 100, up to 5.5 more on the total\n\nWhy it scored 66: Generations come back as small JSON objects with a presigned URL for the output (15). We found no callback for the Agents API, so jobs are polled (0 of 10). Resolution and duration set output size (10). We didn't find a list endpoint for past generations (0 of 10). The 429 detail string tells an agent whether to wait for Retry-After or for a job to finish, and failures carry codes (16). No idempotency key. Moderated and failed generations are refunded, so a retry after a failure is safe (10). One model and one endpoint with few required fields, and official SDKs for Python and TypeScript (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.\n\n## 6. Maintenance \u0026 community, 57 out of 100, up to 3.8 more on the total\n\nWhy it scored 57: Model reading. The Python SDK's last release was v0.5.0 on 5 August 2026, 57 days ago, and the Ray 3.2 API launched on 9 June (20). Ray 2, Ray 3 and their variants are retiring, but the cutoff dates go out in private notices and the migration guide gives none (5). The public changelog is the legacy one and is stale, support goes through the platform (7). Official SDKs on PyPI and npm released within 90 days (15). The Python SDK repository has CI configured (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## 7. Transparency \u0026 trust, 58 out of 100, up to 3.7 more on the total\n\nMade of editorial 30, provenance 86.\n\nWhy it scored 58: Closed models. The terms give customers the outputs, with commercial use tied to an active paid plan (15). The API terms state plainly that API data isn't used for training (10). No retention periods found (0). We didn't read the privacy policy or a DPA against the terms in this run (0). A public migration guide without dates, retirement dates by email only (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: lumalabs.ai, registered 2021-06-19 (5 years) (11 of 15)\n- security.txt: not found (0 of 10)\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 retirement dates for Ray 2, Ray 3 and the Dream Machine API. Luma sends them per account by email\n- Whether the Agents API supports callbacks like the legacy API did\n\n## Weaknesses\n\n- Video rates are marked as subject to change before general availability\n- Retirement dates for Ray 2 and Ray 3 go out by private email, not on a page\n- No audio on Ray 3.2\n- Rate-limit numbers only in the dashboard, and no OpenAPI or llms.txt for the new docs\n- A 10 second clip costs three times the 5 second price\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 model `ray-3.2` and type `video`, with resolution and duration inside `video`. Older model names are rejected\n- Poll GET /v1/generations/{id} until completed or failed, then copy the presigned URL\n- On 429, read `detail`. Rate limit exceeded means wait Retry-After, Too many concurrent jobs means wait for a job to finish\n- Use keyframes with `keyframe_indexes` for 10 second clips. start_frame and end_frame only work at 5 seconds\n\n## What the review panel asked for\n\n- Publish limits per plan\n- Callback support\n- fix prices at general availability\n- clarify the subscription clause for API users\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": 48.7,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 50,
        "maxGain": 10,
        "reason": "Better Stack status page at status.lumalabs.ai with API, Dream Machine and Luma Agents components and 90 days of history (20). Six incidents since 16 July. Ray2 Flash was degraded for 7 hours on 16 July and 2 hours each on 2 and 3 September, Ray2 queue times ran long for 12 hours on 15 September, and authentication was degraded for 1 hour 45 minutes on 17 September through an upstream provider. The Ray2 incidents hit legacy models, the authentication one hit everything, so one major (10). Limits are per minute and per concurrent job, but the numbers sit in the dashboard, not the docs (5). Every 429 carries Retry-After, with separate bodies for the per-minute and concurrency limits and backoff guidance with jitter (15). No SLA found. Provisioned Throughput buys capacity, not an uptime promise (0). The pricing page says video rates may change before general availability, so the video surface isn't GA yet (0).",
        "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 x402, MPP or L402 (0). Per-clip prices in dollars are published without a login, $0.30 for a 5 second 720p clip (20). No free tier, pay as you go from the first call (0). A person signs up in the platform and creates the 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": "schema",
        "name": "Schema \u0026 documentation",
        "score": 43,
        "maxGain": 9.3,
        "reason": "No public OpenAPI document for the Agents API (0). docs.agents.lumalabs.ai/llms.txt returns 404 (0). Guides cover generation, keyframes, edit, extend, reframe and the migration, and say which options don't combine, such as start and end frames with 10 second clips (14). Typed fields for model, type, resolution and duration with fixed values (12). curl examples, both 429 bodies and generation failure codes are documented (12). Responses carry an X-API-Version header, but the only public changelog is the legacy one, last updated more than a year ago (5).",
        "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": 48,
        "maxGain": 9.1,
        "reason": "Model reading of the checklist (credential, training, retention, operator visibility, programme). Bearer keys created in the platform and shown once, with quota and limits shared by all keys of a client. No scopes found (20). The API terms of 28 April 2026 say Luma won't use API inputs or outputs to train or develop its models (20). No retention period for inputs or outputs and no deletion call found (0). Rate-limit headers, a request id per call and usage in the dashboard, no audit log found (8). No security.txt, bug bounty or certification found for Luma AI (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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 66,
        "maxGain": 5.5,
        "reason": "Generations come back as small JSON objects with a presigned URL for the output (15). We found no callback for the Agents API, so jobs are polled (0 of 10). Resolution and duration set output size (10). We didn't find a list endpoint for past generations (0 of 10). The 429 detail string tells an agent whether to wait for Retry-After or for a job to finish, and failures carry codes (16). No idempotency key. Moderated and failed generations are refunded, so a retry after a failure is safe (10). One model and one endpoint with few required fields, and official SDKs for Python and TypeScript (15).",
        "checklist": [
          "- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.",
          "Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 57,
        "maxGain": 3.8,
        "reason": "Model reading. The Python SDK's last release was v0.5.0 on 5 August 2026, 57 days ago, and the Ray 3.2 API launched on 9 June (20). Ray 2, Ray 3 and their variants are retiring, but the cutoff dates go out in private notices and the migration guide gives none (5). The public changelog is the legacy one and is stale, support goes through the platform (7). Official SDKs on PyPI and npm released within 90 days (15). The Python SDK repository has CI configured (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": 58,
        "maxGain": 3.7,
        "reason": "Closed models. The terms give customers the outputs, with commercial use tied to an active paid plan (15). The API terms state plainly that API data isn't used for training (10). No retention periods found (0). We didn't read the privacy policy or a DPA against the terms in this run (0). A public migration guide without dates, retirement dates by email only (5). No subprocessor list or data locations found (0).",
        "blend": "editorial 30, provenance 86",
        "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"
      }
    ],
    "provenance": [
      {
        "label": "Domain age",
        "value": "lumalabs.ai, registered 2021-06-19 (5 years)",
        "points": 11,
        "max": 15
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "The retirement dates for Ray 2, Ray 3 and the Dream Machine API. Luma sends them per account by email",
      "Whether the Agents API supports callbacks like the legacy API did"
    ],
    "weaknesses": [
      "Video rates are marked as subject to change before general availability",
      "Retirement dates for Ray 2 and Ray 3 go out by private email, not on a page",
      "No audio on Ray 3.2",
      "Rate-limit numbers only in the dashboard, and no OpenAPI or llms.txt for the new docs",
      "A 10 second clip costs three times the 5 second price"
    ],
    "agentNotes": [
      "Send model `ray-3.2` and type `video`, with resolution and duration inside `video`. Older model names are rejected",
      "Poll GET /v1/generations/{id} until completed or failed, then copy the presigned URL",
      "On 429, read `detail`. Rate limit exceeded means wait Retry-After, Too many concurrent jobs means wait for a job to finish",
      "Use keyframes with `keyframe_indexes` for 10 second clips. start_frame and end_frame only work at 5 seconds"
    ],
    "requests": [
      {
        "text": "Publish limits per plan",
        "reviews": 1
      },
      {
        "text": "Callback support",
        "reviews": 1
      },
      {
        "text": "fix prices at general availability",
        "reviews": 1
      },
      {
        "text": "clarify the subscription clause for API users",
        "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"
  }
}