Compare

Reducto vs LlamaExtract: price, confidence scores, grounding, benchmarks and terms, with Velrim in the same table

Reducto and LlamaExtract are the two extraction platforms most often shortlisted together, and both have terms that prohibit the use a benchmark run would require. This page puts them side by side on what each publishes, with Velrim in a third column so the comparison includes the vendor writing it. Every Reducto and LlamaExtract entry is a quotation from that vendor's page with the day it was read.

Side by side

Reducto, LlamaExtract and Velrim on product, price, confidence, evidence, grounding, benchmarks, terms, SDKs and funding
ReductoLlamaExtractVelrim
What it isParse, Split, Extract, Classify, Edit and Studio. "The agentic document platform".Extract on LlamaCloud, beside Parse, Classify and Split. "Extract structured data from documents using custom schemas."One extraction API. Schema in, typed fields out, each with a page location and a 0 to 1 confidence score.
Extraction list price per 1,000 pagesExtract $20. Deep Extract $40. Standard tier.Cost-effective $10.00. Agentic $31.25. Agentic Plus $75.00. Turbo $43.75. Credits at $1.25 per 1,000, extract plus parse.$20, grounding and confidence included.
Free tier$150 in free usage on Standard.10K credits: 400 Agentic pages.~500 pages, no card, 90 days.
How to buyStandard self-serve. Growth and Enterprise: "Custom pricing", "Contact sales".Free, Starter $50 a month, Pro $500 a month, Enterprise "Custom".Self-serve. Prepaid balance from $5.
Per-field confidenceWith citations on: confidence as "high" or "low", plus extract_confidence and parse_confidence as 0 to 1 numbers.With confidence_scores: true: parsing_confidence, extraction_confidence and a combined confidence.One 0 to 1 score per field, always on.
What the docs say the score means"Low parse_confidence suggests OCR errors. Low extract_confidence suggests the model was uncertain about interpretation.""a score approximates a real probability of correctness" on three tiers. "At a 0.8 threshold roughly 75% of extraction errors fall below the line."A probability that the field is correct. Claimed against observed differed by 13 points on average in the published comparison.
Evidence for the scoreNone published on the citations, extract overview or response format pages as of 2026-09-03.None published on the extensions, configuring or product pages as of 2026-09-04.Error curves, regenerated on every refit. Per-bucket table and raw outputs in the published comparison.
Grounding"Return page number, bounding box, and source text for each extracted value." Citations cannot be combined with chunking.Page number, verbatim text, box x, y, w, h and page dimensions with cite_sources: true. On Turbo, text-level only.Page, bounding box and matched snippet on every field, from a word map, no second model call.
Benchmarks publishedRD-TableBench, 1,000 table images, dataset and grading code public (Nov 2024). Ranked first on the micro1 long-extraction benchmark (Jun 2026).ParseBench, ~2,000 pages and 167,000 test rules, 14 methods, LlamaParse Agentic 84.9% (Apr 2026). Reducto is one of the 14.A pre-registered comparison of six extraction setups on 124 public documents (Sep 2026). Raw outputs and scorer public, DOI 10.5281/zenodo.22233430.
Terms on benchmarking"Access or use the Services for any competitive purpose." is a prohibited use. Effective 17 April 2026."for benchmarking or competitive analysis of the Service" is a prohibited use, §2.2(h). Last updated Jun 7, 2024.None. The eval CLI ships adapters for both.
SDKsPython and Node, CLI, MCP server.Python, TypeScript, Go, Java, CLI, REST, web UI.TypeScript and Python, MCP server.
Funding$108M total, $75M Series B led by a16z (Oct 2025).$27.5M total, $19M Series A led by Norwest (Mar 2025).Self-funded.

Confidence scores, in each vendor's words

Each citation includes a confidence field with a categorical value ("high" or "low").
Reducto docs, Citations, read
By default in v3, numerical_confidence is enabled, which adds granular_confidence with numeric 0-1 scores. extract_confidence: How confident the LLM is about the extraction. parse_confidence: How confident the OCR/parsing is about the underlying text.
Reducto docs, Citations, read
Low parse_confidence suggests OCR errors. Low extract_confidence suggests the model was uncertain about interpretation.
Reducto docs, Citations, read
This feature adds three confidence-related fields to the extraction metadata: parsing_confidence: Confidence score indicating how well the relevant context was parsed from the source document. extraction_confidence: Confidence score indicating the relevance of the extraction based on the JSON schema field. confidence: Combined confidence score that incorporates both parsing and extraction confidence.
LlamaExtract docs, Metadata Extensions, read
Calibrated on Cost Effective, Agentic, and Agentic Plus. On those tiers a score approximates a real probability of correctness, so you can set a threshold directly rather than only ranking fields against each other. At a 0.8 threshold roughly 75% of extraction errors fall below the line.
LlamaExtract docs, Metadata Extensions, read
Agentic Max and Turbo return scores from an earlier model. They are still useful for ranking fields, but the calibration above does not apply to them.
LlamaExtract docs, Metadata Extensions, read

Reducto returns two 0 to 1 numbers and a high or low label, and says what a low value suggests. LlamaExtract returns three numbers and says the combined one approximates a probability of correctness on three of its five tiers, with one figure attached, 75% of errors under 0.8. As of 2026-09-04, neither vendor's pages carry a dataset, a sample size or an error curve for its score. One number per field, 0 to 1. In Velrim's published comparison of six extraction setups (September 2026), across every field the score graded, the claimed confidence and the observed share correct differed by 13 points on average with refusals counted as a coin flip, 10 points without them. On the 33 values Velrim itself invented, the score averaged 0.40 against 0.64 overall. The curves are on the error curves page and regenerate on every refit. The definition of the fabrication measure is on the metric page.

Grounding

Return page number, bounding box, and source text for each extracted value. Useful for verification and debugging.
Reducto docs, Extract overview, read
The page number where the information was found. The verbatim text that was used to extract the field value. Bounding box coordinates (x, y, w, h) indicating the exact location of the cited text on the page. Page dimensions (width, height) to help you render the bounding boxes accurately.
LlamaExtract docs, Metadata Extensions, read
Cite sources: Enable cite sources to attach citations to extracted fields so you can trace every value back to its origin in the document. On Turbo, citations are text-level and carry no bounding boxes.
LlamaExtract docs, Configuring Extract, read

Both return a page number, a box and the source text per field when citations are on, and both document a cost for turning them on: Reducto's citations cannot be combined with chunking, and LlamaExtract's docs say citations and confidence scores "will significantly slow down extraction processing time". Velrim returns page, box and matched snippet on every field from the PDF's own word map, with no option to turn off and no second model call.

Benchmarks each vendor publishes

1000 complex table images from a diverse set of publicly available documents, manually annotated by a team of PhD-level human labelers. Dataset at huggingface.co/datasets/reducto/rd-tablebench, grading code at github.com/reductoai/rd-tablebench. November 4, 2024.
Announcing RD-TableBench, read
micro1 released an independent benchmark evaluating document extraction systems on difficult, high-field-count workloads. Reducto Deep Extract ranked first overall, 100% completeness, 99.6% precision, 99.6% recall, and 99.3% leaf accuracy. June 30, 2026.
Reducto Deep Extract Leads Benchmark, read
Today we're releasing ParseBench, a benchmark of ~2,000 human-verified enterprise document pages with over 167,000 test rules, organized around five capability dimensions: tables, charts, content faithfulness, semantic formatting, and visual grounding. We evaluated 14 methods spanning vision-language models, specialized document parsers, and LlamaParse. While no single method is good at everything, LlamaParse Agentic was the only method tested that is competitive across five key dimensions, scoring 84.9% overall. Apr 13, 2026.
ParseBench announcement, read
We tested 14 methods across three categories: general-purpose VLMs (GPT-5 Mini, Haiku 4.5, Gemini 3 Flash, Qwen 3 VL, Dots OCR 1.5), specialized document parsers (Textract, Azure Document Intelligence, Google Cloud Document AI, Reducto, Docling, Extend, LandingAI), and LlamaParse (Cost Effective and Agentic modes).
ParseBench announcement, read

Reducto's benchmark scores tables and LlamaIndex's scores parsing, and each vendor's own product leads its own table. ParseBench lists Reducto among the 14 methods it scores. Neither is an extraction benchmark with a public answer key for absent fields. Velrim's published comparison of six extraction setups (September 2026) is that, on 124 documents with 96 audited absent fields, and neither vendor is in it, for the reason below.

Terms

Access or use the Services for any competitive purpose.
Reducto Terms of Service, Prohibited Uses, read
Except to the extent a restriction is prohibited by Applicable Law, you will not do, and will not assist, permit, or enable any third party to do, any of the following:
LlamaIndex Terms of Service, §2.2, read
(h) use or display the Service in competition with us, to develop competing products or services, for benchmarking or competitive analysis of the Service, or otherwise to our detriment or disadvantage;
LlamaIndex Terms of Service, §2.2(h), read

Reducto's terms are dated "Effective: 17 April 2026" (Reducto Terms of Service, read 2026-09-03). LlamaIndex's carry "Last Updated: Jun 7, 2024" (LlamaIndex Terms of Service, read 2026-09-04). Both clauses are use-based, so a paid account does not cure them, and the LlamaIndex preamble extends the ban to third parties. Velrim sent both vendors a written consent request on 2026-07-12 with a deadline of 2026-07-20. Neither replied by the deadline, and the pre-registered outcome for silence was to drop the arm and disclose. The record is in the analysis plan. Both adapters remain published in velrim-eval for a buyer running them under their own account.

What the comparison measured

Headline table from Velrim's September 2026 comparison: accuracy, fabrication on absent fields, error among the top 90% by confidence, and price per thousand pages, six setups
Armmacro-F1 (norm)fabrication (absent fields)wrong among the top 90% by confidence$/1k pages
Velrim0.69111.5% [6.1, 19.8]36.1% [29.9, 44.1]$20 (list; measured matches)
Gemini free-decode0.70917.0% [10.1, 26.7]not requested~$2.2 (measured, token-priced)
Gemini constrained0.69712.8% [7.6, 20.5]not requested~$2.2 (measured, token-priced)
gpt-5.4-mini free0.73510.8% [5.7, 18.4]none surfaced~$1.0 (measured, prompt-cached)
gpt-5.4-mini structured0.71810.4% [5.3, 17.6]none surfaced~$1.0 (measured, prompt-cached)
Mistral OCR 40.71240.3% [31.0, 52.5]none surfaced$5 (list; measured $5.3)

Six setups on 124 public documents, 96 of their fields absent by the audited answer key. Pooled, the six invented a value for 17% of those fields. Velrim: 11.5% [6.1, 19.8]. Velrim is the most expensive row and ties on accuracy. The full comparison has the intervals, the per-document-type breakdown and every raw output.

Pricing

Reducto Standard-tier endpoints and LlamaExtract tiers per 1,000 pages beside Velrim, as read on 2026-09-03 and 2026-09-04
ProductList price per 1,000 pagesBasis
Reducto Extract$20Standard tier, per page
Reducto Deep Extract$40Standard tier, per page
Reducto r-1 Parse$10Standard tier, per page
LlamaExtract Cost-effective$10.008 credits a page at $1.25 per 1,000 credits
LlamaExtract Agentic$31.2525 credits a page
LlamaExtract Agentic Plus$75.0060 credits a page
LlamaExtract Turbo$43.7535 credits a page, no parse step
Velrim$20$0.02 per extracted page, grounding and confidence included
Standard: Free, $150 in free usage. r-1 Parse $10, Extract $20, Deep Extract $40, Split $20, Deep Split $40, Classify $7.50, Edit $60 or $15 for pre-filled pages, per 1,000 pages. Growth and Enterprise: Custom pricing, Contact sales.
Reducto pricing, read
Extract tier, Extract credits/page, Default parse tier, Parse credits/page, Default total: Agentic Plus, 50, Agentic, 10, 60. Agentic, 15, Agentic, 10, 25. Cost-effective, 5, Cost-effective, 3, 8. Turbo, 35.
LlamaCloud docs, Pricing, read
Free $0 /month, Includes 10K credits. Starter $50 /month, 40K credits. Pro $500 /month, 400k credits. Enterprise, Custom. 1,000 credits = $1.25.
LlamaIndex pricing, read

Reducto prices each endpoint per page on its Standard tier with $150 in free usage. LlamaExtract prices in credits, extract tier plus parse tier, so Agentic is 25 credits or $31.25 per 1,000 pages, and the free plan's 10K credits are 400 Agentic pages. Velrim is $20 per 1,000 extracted pages, prepaid from $5.

Which to pick

Reducto, for parsing, splitting, classifying and editing at enterprise volume, with a sales team and a Studio for review. LlamaExtract, for a schema builder in a web UI, a choice of tiers, and a free plan with no card on the same platform as LlamaParse. Velrim, when the requirement is a number per field to sort on and the evidence for that number in the open, at a list price with no sales call.