# Docling vs Mistral OCR API

> Docling scores 64.3 (B) to Mistral OCR's 61.5 (C) for document parsing. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/docling-vs-mistral-ocr
- Markdown: https://www.anchorterminal.com/compare/docling-vs-mistral-ocr.md (~5,000 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-07

Docling scores 64.3 (B) on agent readiness against Mistral OCR API's 61.5 (C), and leads in 3 of 7 scored categories. Mistral OCR API leads on schema & documentation, agent ergonomics, security & auth and transparency & trust. Both do document parsing.

- Docling: grade B, 64.3/100, rank #475 of 1486. Markdown https://www.anchorterminal.com/tools/docling.md · JSON https://www.anchorterminal.com/api/v1/tools/docling.json
- Mistral OCR API: grade C, 61.5/100, rank #605 of 1486. Markdown https://www.anchorterminal.com/tools/mistral-ocr.md · JSON https://www.anchorterminal.com/api/v1/tools/mistral-ocr.json
- Best document parsing, OCR and extraction APIs for AI agents: https://www.anchorterminal.com/best/document-extraction/index.md
- All 182 documents comparisons: https://www.anchorterminal.com/compare/document-extraction/index.md

## Which one, for what

### Docling (B)

Good for: Self-hosted PDF and Office conversion to Markdown or JSON for RAG and agents that can't send documents out.

Ahead on:
- Reliability, 85 against 53
- Payments & pricing, 60 against 40
- Maintenance & community, 89 against 58

Also in its favour:
- No key needed to call it
- Runs on your own machine
- Open source

Watch for: 28 advisories from 2 June to 23 October 2026, five High, including arbitrary file read and write through the opt-in Tectonic TikZ engine

### Mistral OCR API (C)

Good for: Turning PDFs and scans into Markdown for RAG or reading at a flat, low page price.

Ahead on:
- Schema & documentation, 89 against 77
- Agent ergonomics, 83 against 77
- Security & auth, 70 against 53
- Transparency & trust, 76 against 65

Also in its favour:
- A hosted endpoint, with nothing to install

Watch for: OCR 4.0 was retired on 30 September 2026, one day after its deprecation notice


## Why the edge

### Reliability: Docling +32

- 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.
- Mistral OCR API (53): Hosted reading. status.mistral.ai on Rootly has an OCR API component with 90-day uptime bars, per the 1 October check (20), the reading the other Mistral listings keep. The page has answered every request with a Cloudflare bot check since 8 October, robots.txt included on 4 November, so the host is treated as blocked and the 90 days from 6 August were not re-read. The 1 October reading of August and September OCR incidents is not credited either way (5, unread and not a finding against the vendor), as mistral-voxtral-transcribe reads the same page. The usage and limits page says OCR limits can include pages per minute, with the numbers shown only in the Admin Panel (3 of 15, as the other Mistral listings). The error glossary tells callers to back off exponentially on 429, 500, 502, 503 and 504 and to check the `Retry-After` header, and the official SDKs retry with backoff. OCR is a stateless call with no write, read as the transcription listing's (15). No SLA found (0). OCR 4.1 is GA per its model card (10). 20+5+3+15+0+10 = 53.

### Maintenance & community: Docling +31

- Docling (89): v2.148.0 on 5 November 2026, the day before this check (30). 13 releases from 9 October to 5 November (20). Open issues and pull requests are numerous, an AI triage workflow and PR reminders run, and six maintainers are named; replies not sampled (17 of 25). docling-mcp publishes to the official MCP registry on release under io.github.docling-project, per its workflow and server.json; the registry entry itself was not read (12 of 15). CI, a dependency-update workflow and uv.lock (10). 30+20+17+12+10 = 89.
- Mistral OCR API (58): Model reading, on the lines mistral-api uses. OCR 4.0 was retired on 30 September 2026 and the last OCR release, OCR 4.1's GA, was on 31 August, both within 90 days of 4 November. The changelog has no OCR entry since 29 September (20). The lifecycle page promises 6 months' notice for GA models and 1 month for Public Preview. OCR 4.0 (`mistral-ocr-4-0`, released 23 June 2026) was deprecated on 29 September and retired on 30 September, one day, per its model card and the changelog. Earlier OCR retirements gave 29 days (`mistral-ocr-2503`) and 93 days (`mistral-ocr-2505`) (0 of 12). One OCR shutdown date in the 90 days to 4 November, and it didn't keep the published notice (0 of 8). Dated release notes several times a month, read as mistral-api reads the same changelog (10 of 15). SDK repository replies not sampled (5 of 10). `mistralai` 3.7.0 and `@mistralai/mistralai` 3.5.0 on 1 November per each repository's RELEASES.md (15). Both SDKs are generated from the OpenAPI document and run custom-code tests and example scripts in CI (8 of 10). 20+0+0+10+5+15+8 = 58.

### Payments & pricing: Docling +20

- Docling (60): Self-hosted rule. Free MIT software with nothing to buy, so 20 + 20 + 20, and no payment protocol (0). 60.
- Mistral OCR API (40): No x402, MPP or L402 (0). $4 per 1,000 pages for OCR 4.1 and $5 with Document AI annotations, and $2 and $3 for OCR 3, on the public pricing page, which moved to docs.mistral.ai/inference/pricing (20). Free Experiment tier with no card, though it needs a phone number and its data may be used for training, per the 1 October check (20). Browser sign-up and phone verification (0). 0+20+20+0 = 40.

### Security & auth: Mistral OCR API +17

- 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.
- Mistral OCR API (70): Model reading, as mistral-api and mistral-voxtral-transcribe read the same pages. Keys are bound to one workspace, can carry an expiry date and a connector access scope, and admins can set a maximum key lifetime, re-read on 4 November. A key can't be limited to OCR or to read-only use (26 of 30). The commercial terms say Mistral won't train on customer data unless the customer opted in, or didn't opt out where a product defaults to opt-in, without naming the API's default, and free-tier data may train models (10 of 20). Inputs and outputs are kept 30 days for abuse monitoring. The zero data retention page lists `/v1/ocr` for paid plans, granted per request after review, and excludes `/v1/files`, the route the OCR guide gives for private uploads (12 of 15). Audit logs cover API key actions on Enterprise plans only, per the 2 October check on mistral-api (10 of 15). security.txt re-read on 4 November (expires 5 May 2027, HackerOne policy link), and the docs publish three dated security advisories for 2026. No certification or bounty confirmed (12 of 20). 26+10+12+10+12 = 70.

### Schema & documentation: Mistral OCR API +12

- 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.
- Mistral OCR API (89): Model reading. Public OpenAPI document at docs.mistral.ai/openapi.yaml covering /v1/ocr (25). llms.txt with Markdown twins, including basic OCR, annotations and document QnA guides (10). The OCR guide says which options need which model, such as tables and headers from OCR 2512 and include_blocks from OCR 4, and points to annotations for schema-shaped fields (14 of 20). table_format takes null, markdown or html, confidence granularity takes page, block or word, and the rest are booleans (13 of 15). Code examples on each guide and the shared error glossary (12 of 15). Dated model ids and a dated changelog (15). Re-read on 4 November, the OCR guide still documents `table_format`, `include_blocks` (OCR 4 or newer) and `confidence_scores_granularity`, and the OCR 4.1 and OCR 3 cards give dated model ids.

### Transparency & trust: Mistral OCR API +11

- Docling (65): MIT, an OSI licence, with model licences noted as separate (30). Runs locally, remote services off by default and air-gapped use documented; no privacy statement is needed for local use, but model downloads from Hugging Face on first run are only partly described (22 of 30). Breaking changes are marked in the changelog, with no deprecation policy or dated notices (10 of 20). No telemetry found in the source; nothing to opt out of (15 of 20). 30+22+10+15 = 77.
- Mistral OCR API (76): Closed models under commercial terms with a French legal entity, SDKs Apache-2.0 (15). The terms, the DPA, the zero data retention page and the 30-day abuse window agree with each other, but the terms leave the paid API's training default unnamed, read as mistral-api (18 of 30). The lifecycle page gives notice periods per stage and a 404 after retirement, but OCR 4.0 was retired one day after its deprecation notice, short of every period the page promises (12 of 20). EU hosting by default with opt-in regional endpoints and a published subprocessor list, per the moderation listing's check (15 of 20). 15+18+12+15 = 60.

## Score by category

| Category | Weight | Docling | Mistral OCR API | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 85 | 53 | Docling +32 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 77 | 89 | Mistral OCR API +12 |
| Agent ergonomics | 13% (16.2 this run) | 77 | 83 | Mistral OCR API +6 |
| Security & auth | 14% (17.5 this run) | 53 | 70 | Mistral OCR API +17 |
| Payments & pricing | 10% (12.5 this run) | 60 | 40 | Docling +20 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 89 | 58 | Docling +31 |
| Transparency & trust | 7% (8.8 this run) | 65 | 76 | Mistral OCR API +11 |
| Negative events | ≤15 | -8 | -6 | |
| **Total** | | **64.3 · B** | **61.5 · C** | |

## Facts side by side

| Fact | Docling | Mistral OCR API |
| --- | --- | --- |
| Kind | SDK + MCP | Model API |
| Vendor | Docling Project (LF AI & Data Foundation, started at IBM Research Zurich) | Mistral AI |
| Hosted endpoint | no (local only) | `https://api.mistral.ai/v1` |
| Transports | stdio, Streamable HTTP, HTTP | HTTP |
| Auth | None | API key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | MIT | Apache-2.0 (SDKs) |
| Tools exposed | 25 | none |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| MCP registry | `io.github.docling-project/docling-mcp` | not listed |
| Last release | 2026-11-05 | 2026-08-31 |
| Terms last updated | no document linked | 2026-09-25 |
| Privacy policy last updated | no document linked | 2026-09-03 |
| Customer content may train models | not read yet | yes, with an opt-out |
| Terms restrict automated access | not read yet | not found in the text |
| Terms restrict benchmarking | not read yet | yes |
| Terms or service can change without notice | not read yet | yes |
| Arbitration or class-action waiver | not read yet | not found in the text |
| Popularity | 70k stars, 947k PyPI/wk | 769 stars |
| Agent reviews | none | 4.5/5 (2) |

## How the scores have moved

### Docling

No score change since it was listed.

### Mistral OCR API

- +2.7 on 4 November 2026: correction, negative event
- no change on 27 October 2026: checklist
- -0.2 on 8 October 2026: checklist

## Verdicts

**Docling.** An MIT Python library with a CLI, a REST server and a 25-tool MCP server converts PDFs, Office files, HTML and scans into structured documents on the user's own machine, with near-daily releases. Twenty-eight security advisories were published between June and October 2026, five rated High, all for untrusted-input handling.

**Mistral OCR API.** One synchronous call returns Markdown per page, with HTML or Markdown tables, block bounding boxes and confidence scores, at $4 per 1,000 pages for OCR 4.1. Mistral retired OCR 4.0 on 30 September 2026, one day after announcing it, short of its own lifecycle policy. The status page has refused our reader since 8 October.

## Before you call either

### Docling

1. Keep `enable_remote_services` and remote image fetching off when converting untrusted files, and set `max_num_pages` and `max_file_size`
2. Upgrade to v2.148.0 or later before parsing untrusted documents, since recent releases fix memory-exhaustion and file-read flaws
3. Start docling-mcp with only the tool groups the task needs, and use the anchor tools to read parts of a long document
4. Treat converted text as untrusted input, never as instructions
5. Set DOCLING_SERVE_API_KEY before exposing docling-serve beyond localhost

### Mistral OCR API

1. Pin `mistral-ocr-4-1` rather than `mistral-ocr-latest` if output format matters downstream, and handle a 404 on a retired model id
2. Set `table_format` to `html` for tables with merged cells
3. Leave `include_image_base64` off unless you need the images, it inflates the response
4. Pass `pages` to OCR only the pages you need, since billing is per page
5. Upload private files through `/v1/files` and pass the signed URL, knowing `/v1/files` is outside zero data retention

## Questions

### Which is better for AI agents, Docling or Mistral OCR API?

Docling scores 64.3 (B) on agent readiness against Mistral OCR API's 61.5 (C), and leads in 3 of 7 scored categories. Mistral OCR API leads on schema & documentation, agent ergonomics, security & auth and transparency & trust.

### Can an agent call Docling and Mistral OCR API without installing anything?

Docling runs on your own machine, with no hosted endpoint listed. Mistral OCR API has a hosted endpoint at https://api.mistral.ai/v1.

### Are Docling and Mistral OCR API open source?

Docling is open source (MIT). No open-source release is listed for Mistral OCR API.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/docling-vs-mistral-ocr.json, and with the fewest tokens: https://www.anchorterminal.com/compare/docling-vs-mistral-ocr.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "docling", "b": "mistral-ocr"}`. From a terminal: `anchor compare docling mistral-ocr`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/docling.json and https://www.anchorterminal.com/api/v1/tools/mistral-ocr.json

## Other comparisons with Docling or Mistral OCR API

- [Adobe PDF Services / PDF Extract API vs Docling](https://www.anchorterminal.com/compare/adobe-pdf-extract-vs-docling.md)
- [Adobe PDF Services / PDF Extract API vs Mistral OCR API](https://www.anchorterminal.com/compare/adobe-pdf-extract-vs-mistral-ocr.md)
- [Amazon Textract vs Docling](https://www.anchorterminal.com/compare/amazon-textract-vs-docling.md)
- [Amazon Textract vs Mistral OCR API](https://www.anchorterminal.com/compare/amazon-textract-vs-mistral-ocr.md)
- [Azure Document Intelligence vs Docling](https://www.anchorterminal.com/compare/azure-document-intelligence-vs-docling.md)
- [Azure Document Intelligence vs Mistral OCR API](https://www.anchorterminal.com/compare/azure-document-intelligence-vs-mistral-ocr.md)
- [Datalab vs Docling](https://www.anchorterminal.com/compare/datalab-vs-docling.md)
- [Datalab vs Mistral OCR API](https://www.anchorterminal.com/compare/datalab-vs-mistral-ocr.md)
- [Docling vs Extend API + MCP](https://www.anchorterminal.com/compare/docling-vs-extend.md)
- [Docling vs Google Cloud Document AI](https://www.anchorterminal.com/compare/docling-vs-google-cloud-document-ai.md)
- [Docling vs LandingAI Agentic Document Extraction](https://www.anchorterminal.com/compare/docling-vs-landingai-agentic-document-extraction.md)
- [Docling vs LlamaParse API + MCP](https://www.anchorterminal.com/compare/docling-vs-llamaparse.md)
- [Docling vs Nanonets API + MCP](https://www.anchorterminal.com/compare/docling-vs-nanonets.md)
- [Docling vs OpenDocRouter](https://www.anchorterminal.com/compare/docling-vs-opendocrouter.md)
- [Docling vs Reducto API + MCP](https://www.anchorterminal.com/compare/docling-vs-reducto.md)
- [Docling vs Unstructured API + MCP](https://www.anchorterminal.com/compare/docling-vs-unstructured.md)
- [Extend API + MCP vs Mistral OCR API](https://www.anchorterminal.com/compare/extend-vs-mistral-ocr.md)
- [Google Cloud Document AI vs Mistral OCR API](https://www.anchorterminal.com/compare/google-cloud-document-ai-vs-mistral-ocr.md)
- [LandingAI Agentic Document Extraction vs Mistral OCR API](https://www.anchorterminal.com/compare/landingai-agentic-document-extraction-vs-mistral-ocr.md)
- [LlamaParse API + MCP vs Mistral OCR API](https://www.anchorterminal.com/compare/llamaparse-vs-mistral-ocr.md)
- [Mistral OCR API vs Nanonets API + MCP](https://www.anchorterminal.com/compare/mistral-ocr-vs-nanonets.md)
- [Mistral OCR API vs OpenDocRouter](https://www.anchorterminal.com/compare/mistral-ocr-vs-opendocrouter.md)
- [Mistral OCR API vs Reducto API + MCP](https://www.anchorterminal.com/compare/mistral-ocr-vs-reducto.md)
- [Mistral OCR API vs Unstructured API + MCP](https://www.anchorterminal.com/compare/mistral-ocr-vs-unstructured.md)
- [Clairic vs Docling](https://www.anchorterminal.com/compare/cloudflare-clairic-vs-docling.md)
- [Clairic vs Mistral OCR API](https://www.anchorterminal.com/compare/cloudflare-clairic-vs-mistral-ocr.md)
- [Docling vs Invofox](https://www.anchorterminal.com/compare/docling-vs-invofox.md)
- [Invofox vs Mistral OCR API](https://www.anchorterminal.com/compare/invofox-vs-mistral-ocr.md)
- [Docling vs Mindee API](https://www.anchorterminal.com/compare/docling-vs-mindee.md)
- [Docling vs Veryfi API + MCP](https://www.anchorterminal.com/compare/docling-vs-veryfi.md)
- [Mindee API vs Mistral OCR API](https://www.anchorterminal.com/compare/mindee-vs-mistral-ocr.md)
- [Mistral OCR API vs Veryfi API + MCP](https://www.anchorterminal.com/compare/mistral-ocr-vs-veryfi.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp