Beatoven.ai API by Beatoven.ai

# Fix list: Beatoven.ai API

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/beatoven, the October 2026 research run, assessed 1 October 2026. Grade F, 22.2 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 Beatoven.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.

## 1. Reliability, 15 out of 100, up to 17 more on the total

Why it scored 15: No status page found (status.beatoven.ai doesn't resolve) (0). No readable incident history (5). Rate limits not published (0). No 429 or retry guidance in the spec (0). No SLA (0). The v1 API isn't labelled beta or preview (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. Payments & pricing, 0 out of 100, up to 12.5 more on the total

Why it scored 0: No x402, MPP or L402 on Beatoven's own endpoints, and fal's hosted copy has none either (0). No API price published by Beatoven (0). fal sells the same maestro model at $0.10 a request, but that's fal's price, not Beatoven's. No free tier documented (0). A key needs a dashboard sign-up or an email to hello@beatoven.ai (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.

## 3. Security & auth, 30 out of 100, up to 12.3 more on the total

Why it scored 30: A plain bearer key generated from a self-serve dashboard, with no scopes, expiry or rotation documented (20). No least-privilege or read-only mode (0). Returns generated audio only, no untrusted content (10). No per-call logs or audit trail found (0). No security.txt (404 on 2026-10-01), no disclosure policy, no bug bounty and no SOC 2 or ISO 27001 claim 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.

## 4. Schema & documentation, 27 out of 100, up to 11.9 more on the total

Why it scored 27: No machine-readable contract from Beatoven. The spec is a Markdown file on GitHub, and the only OpenAPI we found is a third-party profile by API Evangelist, which we don't count (0). The Markdown spec is readable by a model but there's no llms.txt (5). Two endpoints with one-line descriptions and nothing on when to use them (5). `format` is an enum of mp3, aac and wav, `looping` is a boolean and `prompt.text` is required, but length lives inside the free-text prompt (7). Request and response examples, no error responses documented (5). Versioned `/api/v1` path, 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. Agent ergonomics, 32 out of 100, up to 11.1 more on the total

Why it scored 32: The compose and status calls return small JSON with URLs for the mix and four stems (15). Format can be chosen, length can't, except by wording the prompt (5). No list or history endpoints, and polling uses three documented status values (`composing`, `running`, `composed`) with no webhook (5). No error codes or messages documented (0). No idempotency key or safe-retry guidance (0). One required field and sensible defaults (7), no published SDK, though the repo has an unpackaged `sdk` folder and a Python example (0).

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.

## 6. Maintenance & community, 3 out of 100, up to 8.5 more on the total

Why it scored 3: No dated API release or changelog entry found. The maestro model launched in August 2025 and sound effects in October 2025, but nothing dated in the last 180 days (0). No dated changelog entries in the last 90 days (0). No public changelog, support is an email address, and the GitHub repo has no open issues to judge replies by (3). No official SDK on npm or PyPI (0). No package to judge (0).

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.

## 7. Transparency & trust, 47 out of 100, up to 4.6 more on the total

Made of editorial 28, provenance 66.

Why it scored 47: Closed service. The terms (updated 2024-06-05) say Beatoven owns the copyright in generated music and grants you a licence to use it, but they don't mention the API (8 of 15). The privacy policy (2022-08-26) and the terms agree on keeping content while an account exists, the policy deletes personal data within 180 days of account deletion, and neither says whether prompts train models. No DPA found (10). No deprecation policy or dated notices (0). The privacy policy names Google Analytics, Microsoft Clarity, Stripe and auth0 and says data is processed in India and the US, but there's no full subprocessor list (10).

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: beatoven.ai, registered 2021-02-17 (5 years) (11 of 15)
- 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.

- The API page advertises a maestro SFX Generation API, but the public spec only documents track composition. We couldn't find SFX endpoints on Beatoven's own API.
- Whether the key dashboard issues keys without the email review step.
- Commit dates on the GitHub repo couldn't be read, so we couldn't date the last change to the API spec.
- Whether the 2024 terms, which give Beatoven ownership of generated music, apply to API output or a separate API agreement exists.

## Weaknesses

- No API price, free tier or rate limits published
- Spec is a Markdown file on GitHub with no OpenAPI, error codes, SDK package or changelog
- No status page, security.txt or disclosure policy
- Terms dated 2024-06-05 don't cover the API and say Beatoven owns the copyright in generated music

## 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.

- Poll `GET /api/v1/tasks/{task_id}` until `status` is `composed`, then fetch `track_url` and the four `stems_url` entries
- Put the length in the prompt text, e.g. "30 seconds peaceful lo-fi". There's no duration field
- Set `format` to `mp3`. The default is WAV
- If you only need a published price and a key you can top up, call `beatoven/music-generation` on fal instead

## What the review panel asked for

- Self-serve priced keys
- Document failure states
- Publish API prices
- State failed-track charge policy

## 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.