Head to head · Document parsing · October 2026 research run

Docling vs OpenDocRouter

Docling scores 64.3 (B) on agent readiness against OpenDocRouter's 62.8 (B), and leads in 5 of 7 scored categories. OpenDocRouter leads on schema & documentation and agent ergonomics. Both do document parsing.

Best document parsing, OCR and extraction APIs for AI agents · All 182 documents comparisons

Which one, for what

Docling B

Best 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 68
  • Security & auth, 53 against 41
  • Payments & pricing, 60 against 30
  • Maintenance & community, 89 against 75
  • Transparency & trust, 65 against 49

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

OpenDocRouter B

Best for Agents that need page-level markdown from PDFs and images and want to choose or compare models on price and published benchmark scores with one key.

Ahead on

  • Schema & documentation, 85 against 77
  • Agent ergonomics, 84 against 77

Also in its favour

  • A hosted endpoint, with nothing to install
  • No incidents deducted, where Docling loses 8 points for them

Watch for

Launched on 7 October 2026. The domain was registered on 23 September 2026 and both SDKs have one release, 1.0.0

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Payments & pricing Docling +30

Docling 60

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

OpenDocRouter 30

No x402, MPP or L402 (0). Token prices for every model, an average and a maximum charge per page, the layout price and the 5% top-up fee are public on the models page and in the docs (20). New accounts get $5 of promotional credit. Whether a card is needed at sign-up isn't stated and the dashboard needs a sign-in (10 of 20, our call until that's confirmed). A person signs in through a browser to create a key (0).

Reliability Docling +17

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.

OpenDocRouter 68

Read with the hosted lines. The site still links no status page. LlamaIndex's Statuspage at llamaindex.statuspage.io lists LlamaParse Docs, API and UI components and none for OpenDocRouter. A vendor status page with no component for the product takes 15 in this run, as sentry-mcp and honeycomb-mcp do (15). Its history shows no incident in October or November 2026 and none naming OpenDocRouter. The service launched on 7 October 2026, so the record covers 28 days, read as a short record (15). Limits are published with numbers, 300 parse calls and 60 polls a minute and 10 requests running at once per account (15). 429 and 503 carry Retry-After per the docs, each page error is marked as worth retrying or not, and cache: true makes a repeated request free. There is no idempotency key, and without the cache a resend is charged again. Kept at 13 as partly met (13). No SLA found, and the terms allow changes with or without notice (0). The API is version 1 with 1.0.0 SDKs and no beta or preview label (10). 15+15+15+13+0+10 = 68.

Transparency & trust Docling +16

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.

OpenDocRouter 49

Closed service under the LlamaIndex terms with an OpenDocRouter addendum, SDKs MIT (15). The docs, the OpenAPI document and the addendum agree that nothing is stored without cache: true, cached results are encrypted and kept 24 hours, uploads are deleted once read or after an hour, and request records are kept for billing. The terms say LlamaIndex trains no models on user content. No DPA or retention period for request records was found, and the privacy notice dates from March 2024 and doesn't mention the service (22 of 30). No deprecation policy. Recipe and price versions are dated, and the terms allow changes and price changes without notice (3 of 20). The addendum names Anthropic, Google and OpenAI as examples of model providers that receive pages, leaves its infrastructure providers unnamed and gives no data location beyond processing in the United States (5 of 20).

Maintenance & community Docling +14

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.

OpenDocRouter 75

A closed service read on its dated changes. The models page now lists 19 models, and the newest recipe versions are dated 21 October (nvidia/nemotron-3.5-parse) and 22 October 2026 (llamaindex/ocria-1), 13 days before this check (30). Recipe versions dated from 25 September to 22 October, including 8 and 13 October after launch, plus the 1.0.0 SDKs of 7 October, give three or more dated entries in the 90 days (20). No public changelog or community channel found, support is by email, and GitHub issues weren't readable (3 of 15). Current official SDKs in Python and TypeScript, both still at 1.0.0 with no commit since 7 October (15). The SDK repositories have CI workflows for lint and build, release-please and lock files. Run results weren't readable (7 of 10). 30+20+3+15+7 = 75.

Security & auth Docling +12

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.

OpenDocRouter 41

Bearer API keys created in the dashboard, and the terms say a key can be revoked. No scopes, expiry or rotation were found, and the dashboard needs a sign-in we didn't have (20 of 30). No read-only or restricted key found. One key can spend credit and read cached results, with spending bounded by the prepaid balance (6 of 20). The API returns untrusted document text and no prompt-injection guidance was found. Document URLs must be public HTTPS on the default port (0 of 15). GET /v1/parse/{id} shows what each request did and cost, and the docs mention a usage log keyed by X-Request-Id. No audit log found (8 of 15). SECURITY.md in both SDK repositories asks for private reports to security@runllama.ai, covering the SDK and the APIs it calls, with no acknowledgement time, which this run scores 7. No security.txt per the 8 October check, no advisories in OSV, and LlamaIndex's SOC 2 statement (read for llamaparse on 4 November) names the LlamaParse Platform, so no certification is confirmed for this service (7). 20+6+0+8+7 = 41.

Schema & documentation OpenDocRouter +8

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.

OpenDocRouter 85

Public OpenAPI 3.1 document at /v1/openapi.json covering all six operations (25). No llms.txt (404), but the docs page is served as Markdown at /docs.md (10). The parse, get, delete and upload operations say when to use sync or async, when the cache is needed and what is charged. The credits and models operations have no description, per the 8 October reading of the OpenAPI document, which wasn't re-read because it sits on the API path (16 of 20). mode and mime_type are enums, expand has a pattern and required fields are marked, while pages is a free string and model isn't enumerated (12 of 15). Examples in curl, Python and TypeScript, a table of 15 request errors and a table of 12 page errors (14 of 15). Models carry dated recipe versions and responses a price_version, and the SDKs have changelogs on GitHub, but there is no changelog for the service (8 of 15).

Score by category

CategoryWeight this runDoclingOpenDocRouterEdge
Reliability16%208568Docling +17
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27785OpenDocRouter +8
Agent ergonomics13%16.27784OpenDocRouter +7
Security & auth14%17.55341Docling +12
Payments & pricing10%12.56030Docling +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88975Docling +14
Transparency & trust7%8.86549Docling +16
Negative events≤15-80
TotalB 64.3/100B 62.8/100

Facts side by side

FactDoclingOpenDocRouter
KindSDK + MCPHTTP API
VendorDocling Project (LF AI & Data Foundation, started at IBM Research Zurich)LlamaIndex
Hosted endpointno (local only)https://www.opendocrouter.ai/v1
Transportsstdio, Streamable HTTP, HTTPHTTP
AuthNoneAPI key
PricingFreePay per use
Price for document parsingfree$0.73 per 1,000 pages
x402nono
LicenceMITProprietary service under the LlamaIndex Terms of Service with an OpenDocRouter addendum. The Python and TypeScript SDKs are MIT
Tools exposed25none
Read-only variant documentednono
llms.txtnono
MCP registryio.github.docling-project/docling-mcpnot listed
Last release2026-11-052026-10-07
Terms last updatedno document linked2026-10-07
Privacy policy last updatedno document linked2024-03-30
Customer content may train modelsnot read yetnot found in the text
Terms restrict automated accessnot read yetnot found in the text
Terms restrict benchmarkingnot read yetyes
Terms or service can change without noticenot read yetyes
Arbitration or class-action waivernot read yetyes
Popularity70k stars, 947k PyPI/wknone

How the scores have moved

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.

OpenDocRouter

One endpoint reaches 19 parsing models, each with a dated recipe version, a published token price and a ParseBench score, and failed pages aren't charged. The service launched on 7 October 2026, so it has no status component, SLA or changelog of its own, and no key scopes were found in the reviewed documentation.

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

OpenDocRouter

  1. Read the models page first and choose a model by its per-page average and ParseBench scores. Send its id as model
  2. Send cache: true on any request you might repeat. Without it the markdown exists only in the POST response and a resend is charged as a new request
  3. Raise the SDK timeout above its 60-second default for sync parses. Pages can run for 270 seconds and the SDKs retry a timed-out request twice
  4. Check every page's status before using its markdown. A 200 can be partial, and failed pages can be resent alone with pages
  5. Treat 402 as final until credit is added. The hold is the model's maximum charge per page times the page count, and GET /v1/credits shows available_usd

Questions

Which is better for AI agents, Docling or OpenDocRouter?

Docling scores 64.3 (B) on agent readiness against OpenDocRouter's 62.8 (B), and leads in 5 of 7 scored categories. OpenDocRouter leads on schema & documentation and agent ergonomics.

Which is cheaper for document parsing, Docling or OpenDocRouter?

Docling, at free against $0.73 per 1,000 pages for OpenDocRouter. These are the vendors' published prices for the job.

Can an agent call Docling and OpenDocRouter without installing anything?

Docling runs on your own machine, with no hosted endpoint listed. OpenDocRouter has a hosted endpoint at https://www.opendocrouter.ai/v1.

Are Docling and OpenDocRouter open source?

Docling is open source (MIT). No open-source release is listed for OpenDocRouter.

Other comparisons with Docling or OpenDocRouter

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.