Mindee API by Mindee

# Fix list: Mindee API

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/mindee, the October 2026 research run, assessed 1 October 2026. Grade C, 61.5 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 Mindee 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. Security & auth, 40 out of 100, up to 10.5 more on the total

Why it scored 40: Organisation-level API keys, several per organisation, deletable, with a recommendation to rotate every 3 months. Each key reaches every model in the organisation and keys never expire (20 of 30). The API only enqueues and reads jobs, so there's little to protect against, but there's no per-model or read-only key (10 of 20). Returns fields extracted from untrusted documents, with no prompt-injection guidance found (0 of 15). No audit log or per-key usage view found (0 of 15). The data processing page says Mindee V2 holds SOC 2 Type II and that a HIPAA BAA is available on Enterprise. No security.txt and no bug bounty found (10 of 20).

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.

## 2. Payments & pricing, 25 out of 100, up to 9.4 more on the total

Why it scored 25: No x402, MPP or L402 (0). Plan prices and a per-credit rate are public, but the platform fee rendered as a placeholder in our fetch (15 of 20, our call). A 14-day free trial, and the pricing page doesn't say whether it needs a card (10 of 20, our call until that's confirmed). A person signs up in a browser and has to create a model in the platform before the first call (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. Reliability, 65 out of 100, up to 7 more on the total

Why it scored 65: Statuspage at status.mindee.com with separate components for API V2 (api-v2.mindee.net) and Platform V2 (20). The front page shows no incidents from 18 September to 1 October. The incidents API is blocked by robots.txt, so the earlier 75 days are unread (15 of 30, our call for a clean but partial view). 200 enqueue and 1,200 polling requests a minute per organisation (15). A 429 entry says to wait a few seconds and try again, with no Retry-After and no idempotency key for enqueue (5 of 15). Custom SLAs on Enterprise only, none published (0). The V2 API is GA (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.

## 4. Agent ergonomics, 68 out of 100, up to 5.2 more on the total

Why it scored 68: Output is the schema you defined, so its size is under your control, and polygons, confidence and raw text are opt-in (20 of 25). Those switches are the only output controls, and results are fetched per job (12 of 20). Problem-details errors with a code per case (16 of 20). No idempotency key on enqueue. Failed jobs and 400s don't use credits, per the 30 September check, and webhooks replace polling (8 of 20). Two required fields, but model_id has to come from the web platform first. Python and Node.js SDKs checked, and the docs list more (12 of 15).

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.

## 5. Transparency & trust, 67 out of 100, up to 2.9 more on the total

Made of editorial 58, provenance 75.

Why it scored 67: Closed service under published terms, SDKs MIT (15). Extracted data kept 12 hours by default, configurable from 1 to 24, deletable on fetch, source files never written to disk, no training on customer documents, and a DPA published under mindee.com/legals (28 of 30). V1 and V2 run side by side and we found no written deprecation policy or dated notices this run (5 of 20). Processing in EU or US data centres is selectable, and no subprocessor list was checked (10 of 20).

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):

- Endpoint on the vendor's domain: api-v2.mindee.net is not on mindee.com (0 of 15)
- security.txt: not found (0 of 10)

## 6. Schema & documentation, 86 out of 100, up to 2.3 more on the total

Why it scored 86: OpenAPI spec at api-v2.mindee.net/openapi.json, per the 30 September check (25). llms.txt and Markdown pages (10). The docs say plainly that a model must be defined in the platform before the API can use it, and recommend at most 25 fields per schema (13 of 20). Typed inputs, model_id and file required, optional switches for RAG, polygons, confidence and raw text (12 of 15). Errors follow a problem-details shape with status, title, detail and code, and the problem database lists 15 cases across eight HTTP statuses (14 of 15). V1 and V2 APIs versioned by host, and a public changelog at feedback.mindee.com that we didn't read this run (12 of 15).

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.

## 7. Maintenance & community, 85 out of 100, up to 1.3 more on the total

Why it scored 85: Python SDK v5.4.0 tagged on 2026-09-30 and Node.js SDK v5.10.0 on 2026-09-23 (30). Python has four releases and Node.js eight since 3 August (20). Public changelog, community support on every plan and live chat on Pro, replies not sampled (10 of 15). Current official SDKs (15). Both SDK repositories run unit, integration, regression and smoke-test workflows plus static analysis (10).

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.

## 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: incident history before 18 September. The Statuspage API is blocked by robots.txt
- The pricing page rendered the platform fee as a placeholder and its currency inconsistently. The listing's $29 and $119 platform fees and $0.06 credit packs no longer appear, so pricingNotes and unitPrices are patched from what we could read
- unchecked: whether the 14-day trial needs a card
- unchecked: the changelog at feedback.mindee.com and a subprocessor list

## Weaknesses

- Every call needs a model_id created in the web platform first
- No free tier after the 14-day trial, and the pricing page's platform fee and currency were unclear to us
- Organisation-wide keys that never expire and reach every model
- No official MCP server
- No Retry-After on 429 and no idempotency key

## 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.

- Create the model in the Mindee app and store its `model_id`; the API can't create one for you
- Enqueue returns 202; poll the job or use a webhook, and keep polling under 1,200 a minute
- Send `Authorization: $MINDEE_API_KEY` with no Bearer prefix
- Turn on confidence scores only when needed, since they cost 1.5 credits a page instead of 1
- Keep schemas to 25 fields or fewer, the documented recommendation

## What the review panel asked for

- Add Retry-After to 429
- model creation via API

## 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.