Docling vs Mindee API

Docling 60

Self-hosted rule. Free MIT software with nothing to buy, so 20 + 20 + 20, and no payment protocol (0). 60.

Mindee API 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).

Docling 53

Framework reading. No credentials for local use; docling-serve has one optional shared key, off by default (20 of 30). Remote services are off unless explicitly enabled, local file fetch is guarded by flags, and MCP tools carry read-only and destructive annotations; manipulation tools can delete items and save files (12 of 20). Converted documents are untrusted text and no prompt-injection guidance was found (3 of 15). Logging only, no audit trail (3 of 15). A disclosure policy with private reporting, 28 advisories published in public with fixed versions, under the LF AI & Data Foundation; no bug bounty (15 of 20). 20+12+3+3+15 = 53. The advisories themselves are the deduction.

Mindee API 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).

Docling 77

About 25 MCP tools in the default groups (15), selectable as conversion, generation and manipulation groups, with anchor tools to read one part of a document (22 of 25). max_num_pages, max_file_size and page ranges on conversion, Markdown or JSON export (15 of 20). Errors are exceptions with messages, such as an unknown document key listing the valid ones (12 of 20). readOnlyHint and destructiveHint on the MCP tools, and conversions are repeatable (18 of 20). Sensible defaults and one call to convert; Python only, with a docling-client package for docling-serve (10 of 15). 22+15+12+18+10 = 77.

Mindee API 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).

Docling 85

Local-software lines, graded on the library with docling-serve and docling-mcp. Installs from PyPI (docling 2.148.0, per the PyPI release feed) for Python 3.10 and later on macOS, Linux and Windows (20). Public CI workflows for checks, tests and heavy examples; the pass state of the default branch was not read (20 of 25). About 719 open issues and 223 open pull requests on the repository page against 13 releases in four weeks, many of them fixes; replies not sampled (15 of 25). Semantic-release changelog with Feature and Fix sections and Breaking sections where they apply (15). Version 2.x since 2024 (15). 20+20+15+15+15 = 85.

Mindee API 80

Statuspage at status.mindee.com with separate components for API V1, API V2 (api-v2.mindee.net) and Platform V2 (20). Its history feed, read on 2 November, lists two incidents since 4 August, both on API V1 only. They were 500 errors from the Invoices, Expense Receipts and Financial Documents APIs for 15 minutes on 11 August, and slower responses and failed requests for 10 minutes on 5 October. The listing is the V2 API, so no incident touches it in the window (30). 200 enqueue and 1,200 polling requests a minute per organisation (15). The error page says to wait a few seconds and try again on a 429, 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). 20 + 30 + 15 + 5 + 0 + 10 = 80.

Docling 77

No OpenAPI file is published; docling-serve is a FastAPI app that serves its schema when run, and docling-mcp's tools carry typed inputs with Field descriptions from Pydantic (20 of 25). No llms.txt on the docs site; Markdown docs and AGENTS.md in the repository (5 of 10). MCP tool docstrings say what each tool returns and which other tool supplies its key, with little on when not to use one (14 of 20). Pydantic types with descriptions, few enums (12 of 15). Many runnable examples in docs/examples, with errors raised as Python exceptions that name the fix, such as OperationNotAllowed and unknown document keys listing valid ones (11 of 15). Changelog per release (15). 20+5+14+12+11+15 = 77.

Mindee API 82

OpenAPI 3.1.0 spec at api-v2.mindee.net/openapi.json, version 2.0.0, 17 paths and 19 operations, 429 documented on 9 paths, read on 2 November (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 cases across eight HTTP statuses (14 of 15). V1 and V2 APIs versioned by host, the spec marks the older /v2/inferences operations deprecated in favour of /v2/products/*, and each SDK keeps a dated CHANGELOG, but the public changelog at feedback.mindee.com says "No changes published" (8 of 15). 25 + 10 + 13 + 12 + 14 + 8 = 82.