{
  "fixes": {
    "slug": "spaitial",
    "name": "SpAItial API (Echo)",
    "listing": "https://www.anchorterminal.com/tools/spaitial",
    "markdown": "# Fix list: SpAItial API (Echo)\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/spaitial, the October 2026 research run, assessed 28 October 2026. Grade C, 56.7 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 SpAItial API (Echo): 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, 45 out of 100, up to 11 more on the total\n\nWhy it scored 45: Hosted-API reading. No status page found. The API catalogue's status link, api.spaitial.ai/v1/health, answered 404 on 28 October 2026 and status.spaitial.ai couldn't be reached (0 of 20). No readable incident history, so the 5-point default (5 of 30). Per-key limits published with numbers, 60 requests a minute in general, 10 world creations and 120 downloads (15). 429 carries Retry-After and X-RateLimit headers, with jitter guidance and Idempotency-Key on the mutating POSTs (15). No SLA found for any plan (0). The self-serve API isn't labelled beta or preview (10). Echo-3 isn't on it, which this line doesn't score.\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. Security \u0026 auth, 53 out of 100, up to 8.2 more on the total\n\nWhy it scored 53: Model reading of the checklist, as for the video-generation listings (credential, training, retention, operator visibility, programme). Scoped keys (worlds:create, worlds:read, worlds:write, files:create, files:read), several per account, revoked in the portal, never in a query string (30). The terms (clause 7.1) and the privacy policy let SpAItial train its models on inputs and generated worlds, with no opt-out found (0 of 20). Uploads and edited panoramas expire after 24 hours and deletion runs within 30 days of a verified request, but the terms grant a perpetual licence to retain inputs and outputs and the API has no delete-world call (5 of 15). Keys are the unit of rate limiting and observability and errors carry a request_id; usage sits in the portal, and no customer audit log was found (8 of 15). Valid security.txt, a disclosure policy with good-faith safe harbour and an annual third-party penetration test claimed; no bug bounty, SOC 2 or ISO 27001 (10 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## 3. Payments \u0026 pricing, 40 out of 100, up to 7.5 more on the total\n\nWhy it scored 40: No x402, MPP or L402 (0). Credit prices per model and per plan are published without a login, $0.01 a credit, 160 credits an Echo-2 world (20). Free plan of 800 credits a month with no card for the free account; card needed only for the paid plans' first free month (20). A person signs up at developers.spaitial.ai and creates the key in the portal (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## 4. Maintenance \u0026 community, 48 out of 100, up to 4.6 more on the total\n\nWhy it scored 48: Model reading. Echo-3 shipped on 27 October 2026 and the API's agent skill was synced with 'v1 API consistency changes' on 25 October (30). Model churn and notice: Echo-1 in December 2025, Echo-2 in April 2026 and Echo-3 in October; ids are called stable, but the `default` model id stopped working by 14 October with no public notice found (8 of 20). Monthly release notes and a support form and email, but no October entry yet and no public issue tracker for the API (10 of 15). No official SDK, and the MCP server isn't in the official MCP registry (0 of 15). No package or CI to read; the skill repository has none (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## 5. Schema \u0026 documentation, 81 out of 100, up to 3.1 more on the total\n\nWhy it scored 81: Public OpenAPI 3.0 file at api.spaitial.ai/v1/openapi.json with 25 operations and strict request schemas, though responses carry no schemas (25). llms.txt, a 205 KB llms-full.txt, Markdown copies of every page and a single-page agent skill (10). Guides say when to use each input, what is charged and what not to use SpAItial for, but the pages disagree on rate-limit buckets, the panorama-to-world price, top-up expiry and test keys, and the developers page still shows a model id the API now rejects (12 of 20). Typed inputs with a discriminated input union, enums for output_format, length limits and required fields; `model` is a free string (12 of 15). curl examples throughout and a full table of stable error codes per endpoint (15). /v1 paths and monthly release notes up to September 2026, but no API changelog, and the October model change isn't in the notes (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## 6. Transparency \u0026 trust, 66 out of 100, up to 3 more on the total\n\nMade of editorial 50, provenance 81.\n\nWhy it scored 66: Closed models with clear terms, updated 27 October 2026, that give the user ownership of outputs and set commercial use by plan (15). Terms, privacy policy and security page agree that inputs and outputs may be used for training, state 24-hour input lifetimes and 30-day deletion, but the privacy policy gives no fixed retention period for service data (18 of 30). No deprecation policy; model ids are called stable slugs, and one was removed without a dated notice (5 of 20). Subprocessors listed (Google Cloud, Cloudflare, Stripe, PostHog in the EU, OpenAI for moderation, Resend), with further infrastructure and moderation processors disclosed only to enterprise customers, and transfers outside the UK and EEA without named regions (12 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: spaitial.ai, registered 2024-10-31 (1 year) (3 of 15)\n- Status page: not found (0 of 10)\n\n## 7. Agent ergonomics, 82 out of 100, up to 2.9 more on the total\n\nWhy it scored 82: Small JSON responses, a cheap status endpoint separate from the full result, and a 15-tool MCP server that maps one-to-one to the API (20 of 25). limit and offset on files and jobs, a status filter on jobs, input_kind on models and asset subsets for zip exports; the panoramas list takes no parameters (17 of 20). Stable error codes with details.issues, required_credits and available_credits, and separate 429 codes for rate and concurrency limits (20). Idempotency-Key on world creation, panorama edits and captures, webhook delivery IDs for de-duplication and a cancel that is safe to retry; MCP tool annotations couldn't be read without a key (18 of 20). Two required fields, but no default model and no official SDK in any language (7 of 15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.\n\n## Deductions\n\nEach comes off the total. A fixed and documented problem counts for less at the next check.\n\n- By 14 October 2026 POST /v1/worlds stopped accepting a missing `model` or `model: \"default\"`, which the API docs had allowed and which now returns 400 INVALID_INPUT. The change is in SpAItial's agent skill commit of 14 October and the current Models page; no notice was found in the release notes or docs, and the developers page still shows the old example. Account emails, if any, couldn't be checked (https://github.com/spaitial-dev/spaitial-api-skill/commit/5519006adf67164ebd885966a056e0f56eac797f, https://docs.spaitial.ai/api/generation-models).\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- Whether Free accounts can call the API. The API docs say access is public for all users and the free credits work there, while the app plans table lists Echo-2 and Echo HQ API access under Standard\n- Whether the free 800 credits are monthly (API and billing pages) or a one-time starter balance (Core Concepts page)\n- The panorama-to-world price (160 credits on the billing page, 115 on the LLM Skills page) and the price of a panorama edit, which isn't published\n- Which rate-limit buckets apply. The Rate Limits page and service description say 60, 10 and 120 a minute; the LLM Skills page lists five buckets including 300 a minute for status\n- unchecked: MCP tool definitions and annotations, which need a key to list\n- unchecked: a status page. status.spaitial.ai couldn't be reached and none is linked\n- Whether the October change to require `model` was announced to existing API users by email\n- When the Echo-3 enterprise API opens; the release post uses the future tense\n\n## Weaknesses\n\n- Echo-3 phone-capture reconstruction is in the iOS app and enterprise-only on the API\n- Commercial use of outputs needs a paid Pro plan, $99.99 a month; Free and Standard are non-commercial\n- Terms let SpAItial train on API inputs and generated worlds, with no opt-out found\n- No status page, SLA or official SDK found\n- Docs disagree with each other on rate-limit buckets, panorama-to-world price, top-up expiry and test keys\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- Always send `model` (`echo-2` or `echo-hq`). Since a change dated 14 October, a missing model or `default` returns 400 INVALID_INPUT\n- Send an Idempotency-Key on POST /v1/worlds and POST /v1/panoramas/edit so a retry after a timeout isn't charged twice\n- Pass `webhook.url` or poll GET /v1/worlds/requests/{id}/status every 5 to 10 seconds. Echo-2 takes about 8 to 9 minutes, Echo HQ about an hour\n- Download through the /splat, /panorama or export download_url endpoints just before use; each redirect is a signed URL valid for about 5 minutes\n- Worlds made in the web app aren't visible to the API or MCP server. Create through the API if the agent must read the result back\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": "C",
    "score": 56.7,
    "assessed": "2026-10-28",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 45,
        "maxGain": 11,
        "reason": "Hosted-API reading. No status page found. The API catalogue's status link, api.spaitial.ai/v1/health, answered 404 on 28 October 2026 and status.spaitial.ai couldn't be reached (0 of 20). No readable incident history, so the 5-point default (5 of 30). Per-key limits published with numbers, 60 requests a minute in general, 10 world creations and 120 downloads (15). 429 carries Retry-After and X-RateLimit headers, with jitter guidance and Idempotency-Key on the mutating POSTs (15). No SLA found for any plan (0). The self-serve API isn't labelled beta or preview (10). Echo-3 isn't on it, which this line doesn't score.",
        "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": "security",
        "name": "Security \u0026 auth",
        "score": 53,
        "maxGain": 8.2,
        "reason": "Model reading of the checklist, as for the video-generation listings (credential, training, retention, operator visibility, programme). Scoped keys (worlds:create, worlds:read, worlds:write, files:create, files:read), several per account, revoked in the portal, never in a query string (30). The terms (clause 7.1) and the privacy policy let SpAItial train its models on inputs and generated worlds, with no opt-out found (0 of 20). Uploads and edited panoramas expire after 24 hours and deletion runs within 30 days of a verified request, but the terms grant a perpetual licence to retain inputs and outputs and the API has no delete-world call (5 of 15). Keys are the unit of rate limiting and observability and errors carry a request_id; usage sits in the portal, and no customer audit log was found (8 of 15). Valid security.txt, a disclosure policy with good-faith safe harbour and an annual third-party penetration test claimed; no bug bounty, SOC 2 or ISO 27001 (10 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": "payments",
        "name": "Payments \u0026 pricing",
        "score": 40,
        "maxGain": 7.5,
        "reason": "No x402, MPP or L402 (0). Credit prices per model and per plan are published without a login, $0.01 a credit, 160 credits an Echo-2 world (20). Free plan of 800 credits a month with no card for the free account; card needed only for the paid plans' first free month (20). A person signs up at developers.spaitial.ai and creates the key in the portal (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": 48,
        "maxGain": 4.6,
        "reason": "Model reading. Echo-3 shipped on 27 October 2026 and the API's agent skill was synced with 'v1 API consistency changes' on 25 October (30). Model churn and notice: Echo-1 in December 2025, Echo-2 in April 2026 and Echo-3 in October; ids are called stable, but the `default` model id stopped working by 14 October with no public notice found (8 of 20). Monthly release notes and a support form and email, but no October entry yet and no public issue tracker for the API (10 of 15). No official SDK, and the MCP server isn't in the official MCP registry (0 of 15). No package or CI to read; the skill repository has none (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": "schema",
        "name": "Schema \u0026 documentation",
        "score": 81,
        "maxGain": 3.1,
        "reason": "Public OpenAPI 3.0 file at api.spaitial.ai/v1/openapi.json with 25 operations and strict request schemas, though responses carry no schemas (25). llms.txt, a 205 KB llms-full.txt, Markdown copies of every page and a single-page agent skill (10). Guides say when to use each input, what is charged and what not to use SpAItial for, but the pages disagree on rate-limit buckets, the panorama-to-world price, top-up expiry and test keys, and the developers page still shows a model id the API now rejects (12 of 20). Typed inputs with a discriminated input union, enums for output_format, length limits and required fields; `model` is a free string (12 of 15). curl examples throughout and a full table of stable error codes per endpoint (15). /v1 paths and monthly release notes up to September 2026, but no API changelog, and the October model change isn't in the notes (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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 66,
        "maxGain": 3,
        "reason": "Closed models with clear terms, updated 27 October 2026, that give the user ownership of outputs and set commercial use by plan (15). Terms, privacy policy and security page agree that inputs and outputs may be used for training, state 24-hour input lifetimes and 30-day deletion, but the privacy policy gives no fixed retention period for service data (18 of 30). No deprecation policy; model ids are called stable slugs, and one was removed without a dated notice (5 of 20). Subprocessors listed (Google Cloud, Cloudflare, Stripe, PostHog in the EU, OpenAI for moderation, Resend), with further infrastructure and moderation processors disclosed only to enterprise customers, and transfers outside the UK and EEA without named regions (12 of 20).",
        "blend": "editorial 50, provenance 81",
        "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": 82,
        "maxGain": 2.9,
        "reason": "Small JSON responses, a cheap status endpoint separate from the full result, and a 15-tool MCP server that maps one-to-one to the API (20 of 25). limit and offset on files and jobs, a status filter on jobs, input_kind on models and asset subsets for zip exports; the panoramas list takes no parameters (17 of 20). Stable error codes with details.issues, required_credits and available_credits, and separate 429 codes for rate and concurrency limits (20). Idempotency-Key on world creation, panorama edits and captures, webhook delivery IDs for de-duplication and a cancel that is safe to retry; MCP tool annotations couldn't be read without a key (18 of 20). Two required fields, but no default model and no official SDK in any language (7 of 15).",
        "checklist": [
          "- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.",
          "Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      }
    ],
    "provenance": [
      {
        "label": "Domain age",
        "value": "spaitial.ai, registered 2024-10-31 (1 year)",
        "points": 3,
        "max": 15
      },
      {
        "label": "Status page",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "deductions": [
      "By 14 October 2026 POST /v1/worlds stopped accepting a missing `model` or `model: \"default\"`, which the API docs had allowed and which now returns 400 INVALID_INPUT. The change is in SpAItial's agent skill commit of 14 October and the current Models page; no notice was found in the release notes or docs, and the developers page still shows the old example. Account emails, if any, couldn't be checked (https://github.com/spaitial-dev/spaitial-api-skill/commit/5519006adf67164ebd885966a056e0f56eac797f, https://docs.spaitial.ai/api/generation-models)."
    ],
    "unchecked": [
      "Whether Free accounts can call the API. The API docs say access is public for all users and the free credits work there, while the app plans table lists Echo-2 and Echo HQ API access under Standard",
      "Whether the free 800 credits are monthly (API and billing pages) or a one-time starter balance (Core Concepts page)",
      "The panorama-to-world price (160 credits on the billing page, 115 on the LLM Skills page) and the price of a panorama edit, which isn't published",
      "Which rate-limit buckets apply. The Rate Limits page and service description say 60, 10 and 120 a minute; the LLM Skills page lists five buckets including 300 a minute for status",
      "unchecked: MCP tool definitions and annotations, which need a key to list",
      "unchecked: a status page. status.spaitial.ai couldn't be reached and none is linked",
      "Whether the October change to require `model` was announced to existing API users by email",
      "When the Echo-3 enterprise API opens; the release post uses the future tense"
    ],
    "weaknesses": [
      "Echo-3 phone-capture reconstruction is in the iOS app and enterprise-only on the API",
      "Commercial use of outputs needs a paid Pro plan, $99.99 a month; Free and Standard are non-commercial",
      "Terms let SpAItial train on API inputs and generated worlds, with no opt-out found",
      "No status page, SLA or official SDK found",
      "Docs disagree with each other on rate-limit buckets, panorama-to-world price, top-up expiry and test keys"
    ],
    "agentNotes": [
      "Always send `model` (`echo-2` or `echo-hq`). Since a change dated 14 October, a missing model or `default` returns 400 INVALID_INPUT",
      "Send an Idempotency-Key on POST /v1/worlds and POST /v1/panoramas/edit so a retry after a timeout isn't charged twice",
      "Pass `webhook.url` or poll GET /v1/worlds/requests/{id}/status every 5 to 10 seconds. Echo-2 takes about 8 to 9 minutes, Echo HQ about an hour",
      "Download through the /splat, /panorama or export download_url endpoints just before use; each redirect is a signed URL valid for about 5 minutes",
      "Worlds made in the web app aren't visible to the API or MCP server. Create through the API if the agent must read the result back"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-28",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.7",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  }
}