Compare
Reducto alternative: Reducto and Velrim on price, confidence scores and published evidence
Reducto is a document platform with six products and $108M raised. Velrim is one extraction API with a confidence score on every field and the error curve for that score published. This page sets the two side by side on what each one publishes. Every Reducto entry is a quotation from a Reducto page with the day it was read. Velrim has not run Reducto, because Reducto's terms prohibit it. The clause is quoted below.
Side by side
| Reducto | Velrim | |
|---|---|---|
| What it is | Parse, Split, Extract, Classify, Edit and Studio. "The agentic document platform for parsing, extracting, splitting, classifying, and editing documents at enterprise scale." | One extraction API. Schema in, typed fields out, each with a page location and a 0 to 1 confidence score. |
| Extraction list price | Extract $20 per 1,000 pages. Deep Extract $40 per 1,000 pages. Standard tier. | $0.02 per successfully extracted page, $20 per 1,000. Grounding and confidence included, no surcharges. |
| Free tier | $150 in free usage on Standard. | ~500 pages free, no card, 90 days. |
| How to buy | Standard is self-serve. Growth and Enterprise: "Custom pricing", "Contact sales". | Self-serve. Prepaid balance from $5. |
| Per-field confidence | With citations enabled: confidence as "high" or "low", plus granular_confidence with extract_confidence and parse_confidence as 0 to 1 numbers. | One 0 to 1 score per field, always on. |
| Evidence for the score | None published on the citations or extract documentation pages, as of 2026-09-03. | Error curves published and regenerated on every refit, and a reliability chart in the published comparison. |
| Grounding | "Return page number, bounding box, and source text for each extracted value." Citations cannot be combined with chunking. | Page, bounding box and matched snippet on every field, from a word map, no second model call. |
| Benchmarks published | RD-TableBench, 1,000 table images, dataset and grading code public (Nov 2024). Ranked first on the micro1 long-extraction benchmark (Jun 2026). | A pre-registered comparison of six extraction setups including Velrim on 124 public documents, September 2026. Every raw output and the scorer are public, DOI 10.5281/zenodo.22233430. |
| Terms on benchmarking | "Access or use the Services for any competitive purpose." is a prohibited use. | None. The eval CLI exists to be run against Velrim. |
| SDKs | Python and Node, CLI, MCP server. | TypeScript and Python, MCP server. |
| Compliance | Trust center at trust.reducto.ai. | No SOC 2 report. Retention, deletion and every subprocessor published at /security. |
| Funding | $108M total, $75M Series B led by a16z (Oct 2025). | Self-funded. |
What Reducto says about its confidence score
Each citation includes aconfidencefield with a categorical value ("high"or"low").
By default in v3,numerical_confidenceis enabled, which addsgranular_confidencewith 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.
Lowparse_confidencesuggests OCR errors. Lowextract_confidencesuggests the model was uncertain about interpretation.
The score is two numbers, one for the OCR pass and one for the model, returned when citations are on. As of 2026-09-03, the citations, extract overview and response format pages give no dataset, sample size or error curve for either number.
What Velrim publishes about 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.
Why Reducto is not in the comparison
Access or use the Services for any competitive purpose.
The terms are dated "Effective: 17 April 2026" (Reducto Terms of Service, read 2026-09-03). The clause is use-based, so a paid account does not cure it. Velrim sent Reducto a written consent request on 2026-07-12 describing the protocol, the metrics, pre-publication replication access and a standing right of reply, with a deadline of 2026-07-20. No reply arrived by the deadline, and the pre-registered outcome for silence was to drop the arm and disclose. The full record is in the analysis plan.
What the comparison measured
| Arm | macro-F1 (norm) | fabrication (absent fields) | wrong among the top 90% by confidence | $/1k pages |
|---|---|---|---|---|
| Velrim | 0.691 | 11.5% [6.1, 19.8] | 36.1% [29.9, 44.1] | $20 (list; measured matches) |
| Gemini free-decode | 0.709 | 17.0% [10.1, 26.7] | not requested | ~$2.2 (measured, token-priced) |
| Gemini constrained | 0.697 | 12.8% [7.6, 20.5] | not requested | ~$2.2 (measured, token-priced) |
| gpt-5.4-mini free | 0.735 | 10.8% [5.7, 18.4] | none surfaced | ~$1.0 (measured, prompt-cached) |
| gpt-5.4-mini structured | 0.718 | 10.4% [5.3, 17.6] | none surfaced | ~$1.0 (measured, prompt-cached) |
| Mistral OCR 4 | 0.712 | 40.3% [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
| Endpoint | Reducto Standard, per 1,000 pages |
|---|---|
| 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 |
| Velrim, extraction with grounding and confidence | $20 |
Reducto Standard includes $150 in free usage and up to five Studio seats. Growth and Enterprise are custom-priced through sales (Reducto pricing, read 2026-09-03).
Which to pick
Reducto, for parsing, splitting, classifying and editing at enterprise volume, with a sales team, a trust center and a Studio for review. 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.