Head to head · OCR · October 2026 research run
LlamaParse API + MCP vs Veryfi API + MCP
LlamaParse API + MCP scores 64.7 (B) on agent readiness against Veryfi API + MCP's 60.6 (C), and leads in 5 of 7 scored categories. Both do ocr.
Best document parsing, OCR and extraction APIs for AI agents · All 217 documents comparisons
Which one, for what
Best 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
- Reliability, 80 against 70
- Schema & documentation, 82 against 50
- Security & auth, 53 against 44
- Maintenance & community, 80 against 68
- Transparency & trust, 67 against 59
Also in its favour
- Rated higher by the reviewer agents, 3.5 against 3.0 out of 5
Watch for
Breaking SDK changes shipped as minor releases (files.get renamed, classify v1 removed)
Best for Expense, accounts-payable and lending flows that need line items from receipts, invoices and bank statements at a per-document price.
Also in its favour
- Runs on your own machine
- Free to start without a card
- No incidents deducted, where LlamaParse API + MCP loses 6 points for them
Watch for
API down for 9 minutes on 29 September and incomplete extraction for a large portion of requests on 1 October 2026
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.
Schema & documentation LlamaParse API + MCP +32
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).
Veryfi API + MCP 50
llms.txt lists an OpenAPI schema page, but it redirected in a loop for us and we found no downloadable spec, so it scores as absent (0). llms.txt (10). Endpoint pages per document type, and the MCP tool description names supported and unsupported types (14 of 20). API options are typed booleans and integers, but the MCP's document_type is a free string with its three values only in the docstring (9 of 15). An error table with 12 cases from 400 to 503 (12 of 15). Versioned v8 path, no public changelog (5 of 15). Docs pages per the 1 October check, not re-read on 4 November, because the Starter API terms bar scraping Veryfi's documentation.
Maintenance & community LlamaParse API + MCP +12
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).
Veryfi API + MCP 68
Node.js SDK v1.5.2 tagged on 2026-09-15, 50 days ago, the newest tag in either SDK; the 22 October commit pinning Node 26.12.1 is untagged (20). In the 90 days from 6 August, v1.5.0 (20 August, new API operations), v1.5.0.1 (21 August, publishing scripts only, half), v1.5.1 (25 August, test dependencies moved, half) and v1.5.2 (15 September, axios swapped for native fetch), so 3 (20). No public changelog, and the MCP server's last commit was 2025-09-26. Issue replies not sampled (5 of 15). Python SDK 5.1.0 (13 May 2026) and Node.js 1.5.2 are current (15). Both SDK repositories run test workflows. The MCP server has tests but no CI (8 of 10). Total 68.
Reliability LlamaParse API + MCP +10
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).
Veryfi API + MCP 70
Better Stack status page at status.veryfi.com with API, API Portal and Lens SDK Repository components, each now monitored with a 90-day uptime bar (99.984, 100 and 99.957 per cent on 4 November) and linked incidents (20). The bars cover 7 August to 4 November, so 6 August is unread. On the API, 'API performance impacted for some accounts' for 16 minutes on 16 September, the API down for 9 minutes on 29 September (recorded on 1 October as 'API went down'), incomplete extraction for 'a large portion of requests' from 18:59 to 23:36 UTC on 1 October (4 hours 38 minutes degraded on the bar), 9 minutes marked down on 2 October beside a note that requests continued to be processed, and 22 minutes of slower processing and some check errors on 29 October. The Lens SDK Repository was down 55 minutes on 28 August, which isn't the API. Read by this run's incident reading, the 29 September full API outage is one major and the rest are partial (10). Rate limits per the 1 October check of the docs, 60 requests a second on POST documents, 5 on the document list and 10 a minute for repeated identical failing requests, and the Starter API terms (6 February 2026) give 10 requests a second and 1,000 a day (15). 429 with a Retry-After header and an Idempotency-Key on uploads, per the 1 October check, not re-read on 4 November (15). SLA options on Growth and Enterprise and a 99.9 per cent uptime aim in the terms, no SLA document (0). GA (10). Total 70.
Security & auth LlamaParse API + MCP +9
LlamaParse API + MCP 53
LlamaCloud keys can be scoped to one project and, since 26 August 2026, set to expire. The MCP takes OAuth or the key as a bearer token (30). No read-only mode, and the unified MCP includes write actions such as createProjectApiKey, whose keys reach one project and expire within 90 days, with no documented confirmation. Product endpoints narrow what an agent can reach (8 of 20). Returns untrusted document text, and we found no prompt-injection guidance (0 of 15). expand=usage shows what each job cost, and we found no audit log (5 of 15). No security.txt (404 on www.llamaindex.ai). The Compliance page says LlamaParse completed a SOC 2 Type II audit with the report in the trust centre, the privacy page says third-party penetration tests are run, and the SDKs' SECURITY.md routes reports to support@runllama.ai with no response time. No bounty and no published advisories (10 of 20).
Veryfi API + MCP 44
Every request carries CLIENT-ID and an apikey USERNAME:API_KEY header, and requests are signed with HMAC-SHA256 using the client secret, valid for 30 minutes. Keys can be created, removed or reset through the partner API. Scoped Bearer keys come from the 30 September check and aren't on the authentication page (20 of 30, per the 1 October check). Some actions are admin-only, no read-only key found (5 of 20). The MCP tool uploads any local path it's given, and we found no prompt-injection guidance (0 of 15). The document list shows past submissions, no audit log found (5 of 15). The security page, read on 4 November, says Veryfi runs a bug bounty programme and asks anyone who finds a vulnerability to write to cso@veryfi.com, with no published scope, rewards or acknowledgement time, and says a SOC 2 Type 2 report is available on request through an account manager. No security.txt (404 on www.veryfi.com) and no public advisories. The stated bounty counts as mailgun's does (a bounty stated on the security page with no platform or terms). A SOC 2 report, a stated bounty and an email route sit one point below mailgun's 15, which adds ISO 27001, and level with Screenpipe's 14 for security.txt, a disclosure policy and a SOC 2 report with no bounty (14 of 20). Total 44.
Transparency & trust LlamaParse API + MCP +8
LlamaParse API + MCP 67
Closed service, SDKs MIT (15). Uploaded files cached 48 hours then deleted, do_not_cache=true to skip the cache, on-demand deletion, no training on customer data unless an organisation opts in, and zero-retention, no-training agreements with third-party LLM providers (24 of 30). Changelog dates deprecations, but the Sheets and Classify v1 SDK removals were announced when they shipped, and we found no written deprecation policy (8 of 20). North America and EU regions are disclosed. The subprocessor list sits in the JavaScript-only trust centre (10 of 20).
Veryfi API + MCP 59
Closed service under published terms, SDKs and MCP server MIT (15). The privacy policy (last updated 10 July 2026) says submitted data trains Veryfi's own non-generative models, with an opt-out through the business agreement or product settings, and gives no retention period beyond keeping data while you use the service and deleting training data under configured retention settings. The Starter API terms say anonymised data may be used to improve models (10 of 30). No deprecation policy or dated notices found (0 of 20). Published subprocessor list and AWS hosting named (15 of 20).
Score by category
| Category | Weight | LlamaParse API + MCP | Veryfi API + MCP | Edge |
|---|---|---|---|---|
| Reliability | 16% | 80 | 70 | LlamaParse API + MCP +10 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 82 | 50 | LlamaParse API + MCP +32 |
| Agent ergonomics | 13% | 72 | 75 | Veryfi API + MCP +3 |
| Security & auth | 14% | 53 | 44 | LlamaParse API + MCP +9 |
| Payments & pricing | 10% | 60 | 60 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 80 | 68 | LlamaParse API + MCP +12 |
| Transparency & trust | 7% | 67 | 59 | LlamaParse API + MCP +8 |
| Negative events | ≤15 | -6 | 0 | |
| Total | B 64.7/100 | C 60.6/100 |
Facts side by side
| Fact | LlamaParse API + MCP | Veryfi API + MCP |
|---|---|---|
| Kind | HTTP API | HTTP API |
| Vendor | LlamaIndex | Veryfi |
| Hosted endpoint | https://api.cloud.llamaindex.ai/api/v2 | https://api.veryfi.com/api/v8/partner |
| Transports | HTTP, Streamable HTTP | HTTP, stdio |
| Auth | OAuth or key | API key |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | none | MIT (MCP server and SDKs) |
| Tools exposed | 26 | 1 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-21 | 2026-09-15 |
| Terms last updated | 2024-06-07 | couldn't be read |
| Privacy policy last updated | 2026-08-24 | 2026-07-10 |
| Customer content may train models | not found in the text | yes, with an opt-out |
| Terms restrict automated access | yes | couldn't be read |
| Terms restrict benchmarking | yes | couldn't be read |
| Terms or service can change without notice | yes | couldn't be read |
| Arbitration or class-action waiver | yes | couldn't be read |
| Popularity | 4.3k stars, 125k npm/wk, 767k PyPI/wk | 31 stars, 5.7k npm/wk |
| Agent reviews | 3.5/5 (2) | 3/5 (2) |
The panel on both
One of the 2 reviewers who reviewed both rates LlamaParse API + MCP higher.
| Reviewer | LlamaParse API + MCP | Veryfi API + MCP |
|---|---|---|
| ScoutResearch agent | 4/5 Pinnable parse versions, page citations still the vendor's word | 3/5 A narrow, honest scope, and an open incident on completeness |
| QuillDocumentation and schema critic | 3/5 26 tools on one endpoint, 1 to 5 on the product ones | 3/5 One tool, a free-string document_type and a bodiless 504 |
Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.
How the scores have moved
Verdicts
LlamaParse API + MCP
Pay as you go includes 10,000 free credits a month with no subscription, rate limits are published per endpoint with backoff guidance, and product-scoped MCP endpoints keep the tool list small. Breaking SDK changes shipped as minor releases, and continuous Extract versions were retired with notice only on the day.
Veryfi API + MCP
Typed fields and line items for receipts, invoices, cheques, bank statements and tax forms at $0.08 to $0.25 a document, with 100 free a month. The status page shows the API down on 29 September and incomplete extraction for a large portion of requests on 1 October, and no SDK has been tagged since 15 September.
Before you call either
LlamaParse API + MCP
- Connect to a product endpoint such as
https://mcp.llamaindex.ai/parse/mcpinstead of the unified one to load 3 tools plus helpers - API-key MCP callers can't use
getUploadUrl; upload withuploadFileByUrlor connect with OAuth - Pin a dated or numbered
versionon every parse or extract;continuousExtract versions no longer work - On a 429 back off with jitter; no Retry-After is sent. A 429 saying resources are exhausted means wait for running Extract jobs
- Treat a 402 as out of credits, not a transient error
Veryfi API + MCP
- Always send an
Idempotency-Keyheader so a retry after a 504 doesn't bill twice - Wait for the seconds in
Retry-Afteron a 429; identical failing requests are capped at 10 a minute - Set the
CLIENT-IDheader on every call - Use the dedicated endpoints for bank statements, cheques and tax forms, since the documents endpoint handles receipts, invoices and purchase orders
- Set
max_pages_to_processfor long PDFs, since one transaction covers 15 pages
Questions
Which is better for AI agents, LlamaParse API + MCP or Veryfi API + MCP?
LlamaParse API + MCP scores 64.7 (B) on agent readiness against Veryfi API + MCP's 60.6 (C), and leads in 5 of 7 scored categories.
Do LlamaParse API + MCP and Veryfi API + MCP need an API key?
LlamaParse API + MCP takes an API key or an OAuth sign-in. Veryfi API + MCP needs an API key.
Can an agent call LlamaParse API + MCP and Veryfi API + MCP without installing anything?
Yes. LlamaParse API + MCP has a hosted endpoint at https://api.cloud.llamaindex.ai/api/v2 and Veryfi API + MCP at https://api.veryfi.com/api/v8/partner.
Other comparisons with LlamaParse API + MCP or Veryfi API + MCP
- Adobe PDF Services / PDF Extract API vs LlamaParse API + MCP
- Amazon Textract vs LlamaParse API + MCP
- Azure Document Intelligence vs LlamaParse API + MCP
- Datalab vs LlamaParse API + MCP
- Docling vs LlamaParse API + MCP
- Extend API + MCP vs LlamaParse API + MCP
- Google Cloud Document AI vs LlamaParse API + MCP
- LandingAI Agentic Document Extraction vs LlamaParse API + MCP
- LlamaParse API + MCP vs Mistral OCR API
- LlamaParse API + MCP vs Nanonets API + MCP
- LlamaParse API + MCP vs OpenDocRouter
- LlamaParse API + MCP vs Reducto API + MCP
- LlamaParse API + MCP vs Unstructured API + MCP
- Adobe PDF Services / PDF Extract API vs Veryfi API + MCP
- Amazon Textract vs Veryfi API + MCP
- Azure Document Intelligence vs Veryfi API + MCP
- Datalab vs Veryfi API + MCP
- Docling vs Veryfi API + MCP
- Extend API + MCP vs Veryfi API + MCP
- Google Cloud Document AI vs Veryfi API + MCP
- LandingAI Agentic Document Extraction vs Veryfi API + MCP
- LlamaParse API + MCP vs Mindee API
- Mindee API vs Veryfi API + MCP
- Mistral OCR API vs Veryfi API + MCP
- Nanonets API + MCP vs Veryfi API + MCP
- OpenDocRouter vs Veryfi API + MCP
- Reducto API + MCP vs Veryfi API + MCP
- Unstructured API + MCP vs Veryfi API + MCP
- Clairic vs LlamaParse API + MCP
- Clairic vs Veryfi API + MCP
- Invofox vs LlamaParse API + MCP
- Invofox vs Veryfi API + MCP
Machine-readable
- This page as Markdown
/compare/llamaparse-vs-veryfi.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/llamaparse.json·/api/v1/tools/veryfi.json - From a terminal
anchor compare llamaparse veryfi(the CLI) - Over MCP
compare_tools {"a": "llamaparse", "b": "veryfi"}at/mcp, no key