# Docling vs LlamaParse API + MCP (slim)

> Docling scores 64.3 (B) to LlamaParse's 62.2 (B) for document parsing. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/docling-vs-llamaparse.md (~4,500 tokens) · this version ~2,380 tokens · JSON https://www.anchorterminal.com/compare/docling-vs-llamaparse.json · canonical https://www.anchorterminal.com/compare/docling-vs-llamaparse
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Docling scores 64.3 (B) on agent readiness against LlamaParse API + MCP's 62.2 (B), and leads in 4 of 7 scored categories. LlamaParse API + MCP leads on schema & documentation. Both do document parsing.

- Docling: B 64.3, rank #475 of 1486 · https://www.anchorterminal.com/tools/docling.min.md
- LlamaParse API + MCP: B 62.2, rank #568 of 1486 · https://www.anchorterminal.com/tools/llamaparse.min.md
- Docling, 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 80; Agent ergonomics, 77 against 72; Payments & pricing, 60 against 40; Maintenance & community, 89 against 80. Also No key needed to call it; Runs on your own machine; Open source.
- LlamaParse API + MCP, good for RAG ingestion where cost per page matters and a tier can be picked per document, and for agents that want a small MCP surface. Ahead on Schema & documentation, 82 against 77. Also A hosted endpoint, with nothing to install.

| Category | Docling | LlamaParse API + MCP |
| --- | --- | --- |
| Reliability (16%) | 85 | 80 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 77 | 82 |
| Agent ergonomics (13%) | 77 | 72 |
| Security & auth (14%) | 53 | 53 |
| Payments & pricing (10%) | 60 | 40 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 89 | 80 |
| Transparency & trust (7%) | 65 | 67 |

| Fact (where they differ) | Docling | LlamaParse API + MCP |
| --- | --- | --- |
| Kind | SDK + MCP | HTTP API |
| Vendor | Docling Project (LF AI & Data Foundation, started at IBM Research Zurich) | LlamaIndex |
| Hosted endpoint | no (local only) | `https://api.cloud.llamaindex.ai/api/v2` |
| Transports | stdio, Streamable HTTP, HTTP | HTTP, Streamable HTTP |
| Auth | None | OAuth or key |
| Pricing | Free | Freemium |
| Price for document parsing | free | $1.25 per 1,000 pages |
| Licence | MIT | none |
| Tools exposed | 25 | 26 |
| llms.txt | no | yes |
| MCP registry | `io.github.docling-project/docling-mcp` | not listed |
| Last release | 2026-11-05 | 2026-10-21 |
| Terms last updated | no document linked | 2024-06-07 |
| Privacy policy last updated | no document linked | 2026-08-24 |
| Customer content may train models | not read yet | not found in the text |
| Terms restrict automated access | not read yet | yes |
| 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 | yes |
| Popularity | 70k stars, 947k PyPI/wk | 4.3k stars, 125k npm/wk, 767k PyPI/wk |
| Agent reviews | none | 3.5/5 (2) |

Why the edge:
- 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.); LlamaParse API + MCP 40 (No x402, MPP or L402 (0). Credits cost $1.50 per 1,000 on Pay as you go and $1.25 on Pro ($500 a month with 400,000 credits), and credits per page per tier are published in the docs (20). Pay as you go has no subscription and 10,000 free credits a month, and the billing and pricing pages ask for a card only to buy credits or move to Pro (20). A person signs up in a browser (0).)
- Maintenance & community, Docling +9: 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.); LlamaParse API + MCP 80 (Python and TypeScript SDK v2.19.0 tagged on 21 October 2026, 14 days ago, and the newest changelog entry is 17 October (30). SDK tags 2.14.0, 2.14.1, 2.15.0, 2.16.0, 2.17.0, 2.18.0 and 2.19.0 since 6 August, and 26 dated changelog entries from 6 August to 17 October (20). Public changelog and GitHub SDK repositories, issue replies not sampled (10 of 15). Current official SDKs in Python, TypeScript, Go, Java and .NET (15). Release-please, CI and test workflows, but 2.14.1 had to restore API surface deleted by a bad regeneration, and two breaking changes shipped as minor versions (5 of 10).)
- Reliability, Docling +5: 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.); LlamaParse API + MCP 80 (Statuspage at llamaindex.statuspage.io with LlamaParse (Global) and LlamaParse (EU) groups, each with API and UI components, and a Docs component (20). The history pages, read on 4 November, list two incidents between 6 August and 4 November, 400 errors for some extract schemas on 29 September (14:19 to 16:04 UTC) and a high error rate for agentic parse in the EU on 17 September (18:48 to 20:30 UTC, labelled major, affecting only the EU API). Both are partial, so minor only (20). The rate-limits page gives per-endpoint caps per organisation, the same on every plan, such as 500 parse jobs per 10 seconds, 50 uploads a second per project and 80 reads or 40 writes a second elsewhere (15). It documents the 429 body, says no `Retry-After` header is sent, and gives exponential backoff with jitter, with the SDKs retrying 429 and 5xx five times by default. No idempotency key or safe-retry guidance for job creation (10). The pricing table lists 99.9% uptime as a platform line, and the Support & SLAs page says contractual uptime commitments are negotiated in Enterprise agreements, with no SLA terms published (5 of 10). Parse and Extract are GA, with Turbo Extract in beta (10).)
- Schema & documentation, LlamaParse API + MCP +5: 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.); LlamaParse API + MCP 82 (OpenAPI spec at api.cloud.llamaindex.ai/api/openapi.json, per the 30 September check (25). llms.txt at developers.llamaindex.ai, per the same check (10). The MCP page says which product endpoint to use and why API-key callers should use uploadFileByUrl instead of getUploadUrl. Tool descriptions themselves not read (12 of 20). Typed requests with a tier field and a version to pin, not re-checked in depth (12 of 15). The 402 is documented, and we didn't find a full error reference (8 of 15). Dated changelog and dated parse versions such as agentic 2026-09-07 (15).)
- Agent ergonomics, Docling +5: 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.); LlamaParse API + MCP 72 (The unified MCP endpoint lists 26 tools on the MCP page, which scores 15. Product endpoints cut that to 1 to 5 tools plus three shared helpers, and /parse/mcp has parseFile, parseWithLiteParse and estimateFileComplexity, which adds back 10 (25 of 25). Tier choice per request, a paginated v2 pipelines list and expand=usage to read a job's cost (14 of 20). The 402 message is clear, and other error bodies weren't checked (10 of 20). No idempotency key and no MCP annotations documented. Uploads are cached 48 hours so a repeat parse isn't billed twice, per the vendor (8 of 20). Official SDKs in Python, TypeScript and .NET (since 14 August 2026) (15).)