Creatomate

# Fix list: Creatomate

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/creatomate, the October 2026 research run, assessed 8 October 2026. Grade D, 47.7 out of 100.

This 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.

For a coding agent working on Creatomate: 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.

## 1. Reliability, 40 out of 100, up to 12 more on the total

Why it scored 40: Hosted lines. No status page found. status.creatomate.com does not resolve and no page we read links to one (0). No readable incident history (5). 30 requests per 10 seconds per account, documented (15). `Retry-After` on 429, `X-RateLimit-*` headers on every response, which we saw first-hand, and advice to queue requests, but no idempotency key for renders, which are writes (10). No SLA found on the pricing page, in the docs or in the terms (0). The REST API and MCP server carry no beta label (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 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.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 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.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 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.

## 2. Security & auth, 48 out of 100, up to 9.1 more on the total

Why it scored 48: MCP uses OAuth authorisation code with PKCE S256 and dynamic client registration, one scope, with connections revocable per application. REST uses one unscoped key per project, and key rotation is not documented (22). Each MCP connection reaches one project and a project can have a monthly credit budget, but there is no read-only mode and no server-side confirmation before a render or delete (8). Returns the account's own templates and renders (10). Account Settings lists MCP connections with last use, and the dashboard has an API log of renders (8). No security.txt, disclosure policy, bounty or certification found (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 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.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 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.
- 0 to 15, audit logs or per-call visibility for the operator.
- 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.

## 3. Payments & pricing, 35 out of 100, up to 8.1 more on the total

Why it scored 35: No x402, MPP or L402 (0). The credit formula per image and per video is public, and the docs state $54 and $129 for two plans, but the pricing page's plan prices are drawn by a Paddle script and did not render for us (15). Trial with 50 credits and no card (20). A person signs up in a browser and copies a key or signs in through OAuth (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

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.
- 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.
- 20, a free tier or trial that doesn't need a card.
- 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.

## 4. Schema & documentation, 53 out of 100, up to 7.6 more on the total

Why it scored 53: No OpenAPI file found (api.creatomate.com/openapi.json returns 404), and the MCP tool schemas can't be read without an account (0). llms.txt with 27 Markdown topic pages and llms-full.txt (10). Reference and topic pages state purpose and when to use `dry_run`, templates or raw RenderScript, with an out-of-scope page (16). Render options are typed with ranges and `status` is an enum, but `modifications` and `source` are open objects, and unknown names are ignored without an error (9). Examples in nine languages and a documented error body with five status codes (13). `/v1` and `/v2` paths, no changelog (5).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 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.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 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.

## 5. Maintenance & community, 34 out of 100, up to 5.8 more on the total

Why it scored 34: No changelog. The newest dated release we found is `@creatomate/preview` 1.6.1 on 3 September 2026, 35 days before the check (20). Two dated releases in 90 days, that one and the n8n node 0.2.0 on 11 August 2026 (0). Support by email, no public changelog or forum found, and two open GitHub issues across the libraries (5). The Node library was last published on 23 September 2024 and calls `/v1`, the PHP library was last pushed on 21 October 2024, and the Preview SDK is current (7). No CI in the Node repository (2).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 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.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 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.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 6. Agent ergonomics, 67 out of 100, up to 5.4 more on the total

Why it scored 67: Eight MCP tools by the vendor's list, definitions unseen, and the template list omits sources (22). A `tags` filter on the template list, with no pagination, limit or render list found (6). Every failure returns a `hint` and a `documentation` URL, confirmed on a 401, plus advisory `errors` and `warnings` and a free `dry_run` (20). No idempotency key. `dry_run` and status polling are safe, template delete is described as recoverable for 30 days, and MCP annotations were not readable (8). `template_id` alone starts a render, and the Node and PHP libraries are official but last published in 2024 (11).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 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).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 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.

## 7. Transparency & trust, 51 out of 100, up to 4.3 more on the total

Made of editorial 37, provenance 65.

Why it scored 51: Closed service under published terms, with MIT client libraries (15). Render retention of 30 days is stated the same way in the docs, pricing page and llms.txt. The privacy policy is dated 27 June 2022 with no retention period for personal data, no DPA was found, and the terms let Creatomate make user Content available to other users (12). No deprecation policy, and `/v1` and `/v2` are documented side by side with no dates (2). The privacy policy names Paddle, AWS, DigitalOcean, Google Analytics, Cloudflare and GitLab, with no data locations (8).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 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.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 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.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: creatomate.com, registered 2021-03-27 (5 years) (11 of 15)
- Terms of service: read, states 6 of the 7 things a reader expects (9.1 of 10)
- Status page: not found (0 of 10)
- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## What we couldn't check

What 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.

- unchecked: the plan prices on creatomate.com/pricing, which a Paddle script draws in the browser. Only the $54 and $129 figures in the docs were read
- unchecked: the MCP tool schemas, descriptions and annotations, which need a signed-in account
- No status page, changelog, SLA, DPA, security contact or deprecation policy was found on the pages we read
- The docs page for template delete does not mention recovery, while llms.txt says a delete is recoverable for 30 days
- The render `status` list differs between the docs page (six values) and llms.txt (seven, adding `cancelled`)
- The legal form of the company is not stated. The terms name Creatomate, Leeuwarden, and the footer gives company number 90174356
- Whether failed renders are charged credits, and whether a project API key can be rotated, were not found
- GitHub star count is for creatomate/creatomate-node as returned by the GitHub API

## Weaknesses

- No status page, incident history or SLA found. `status.creatomate.com` does not resolve
- No OpenAPI file and no changelog. `/v1` and `/v2` routes are both documented with no deprecation policy
- Plan prices on the pricing page are drawn by a Paddle script. The docs name only $54 (Essential) and $129 (Growth 10K)
- No security.txt, disclosure policy or certification found, and REST keys have no scopes
- Terms and privacy policy are dated 27 June 2022, define the Service as the website, and let Creatomate make user Content available to other users

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Send `"dry_run": true` to `POST /v2/renders` before a paid render. It returns `valid`, `errors`, `warnings` and the effective source
- Read `warnings` on every render response. A modification keyed to an unknown element or property name is ignored without an error
- Keep under 30 requests per 10 seconds across the whole account, and wait for `Retry-After` on a 429
- Download each file when the webhook fires. Renders, their URLs and their status records are deleted after 30 days
- Use `render_scale` 0.5 for draft videos, about a quarter of the credits, and remember MCP `create_render` spends credits without a confirmation step from the server

## When it's done

Send 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.