Skip to content
Velrim logo

Velrim

Turns documents into typed objects matching a schema, with per-field source grounding and confidence scores.

From $0.02 per useActively maintained

At a glanceswept Oct 24, 2026

not read yet

Use

For
Developers who extract typed data from documents and define the output shape with Zod or Pydantic schemas.
Price
From $0.02 per usepricing page, read Oct 25, 2026
Activity
Actively maintainedrelease 8 weeks ago
Runs as
APISDK
Used for
  • extract invoice vendors, dates and totals into typed objects
  • review low-confidence extracted fields before accepting them
  • run accuracy evals against a golden set in CI
read off velrim.com on Oct 25, 2026
Worth knowingcomputed from what we read · each with its source
Pricingpricing page, read Oct 25, 2026
Your datawhat they publish, each line with its page · read Oct 25, 2026

“We do not use your documents, or values extracted from them, to train models.”

security page ↗

These are Velrim's own statements, read from its pages. We did not audit them. A line that is missing was not found on the pages we read; it does not mean the practice is absent.

How a program reaches itfound, not claimed · read Oct 25, 2026
  • MCP servercom.velrim/extractverified in the MCP registry
  • Stateanswers, 2 toolschecked 2026-10-25
  • Address to connectmcp.velrim.com/mcp
  • MCP docsvelrim.com/docs/mcpthe vendor's page ↗
  • Status pagelinked from the homepagevelrim.com/status ↗

MCP server details →

This card as JSON, for your agent →

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.

Alternatives in Documentsby use, among tools still maintained

Figure and bar: visits/mo, estimate · year: online since

Compare Velrim with

Pick up to two.

All 10 alternatives to Velrim →

All Documents tools →

Not it? Say what you need

beta

Three tools from the Atlas for the job you describe, each with what fits and what does not.

From people who use itnot part of the reading

No notes yet. What do you use Velrim for?

Sign in to leave a note
Questions this page answers
  • What is Velrim?

    Turns documents into typed objects matching a schema, with per-field source grounding and confidence scores. It is listed in the Atlas under Documents.

  • Who is Velrim for?

    Developers who extract typed data from documents and define the output shape with Zod or Pydantic schemas.

  • How much does Velrim cost?

    Paid plans start at $0.02 per use, per Velrim's pricing page on 2026-10-25.

  • Do people use Velrim?

    Little sign of use.

  • Is Velrim still maintained?

    Actively maintained: release 8 weeks ago.

  • Does Velrim train AI on your data?

    No, per its security page (2026-10-25): “We do not use your documents, or values extracted from them, to train models.”

  • Is Velrim safe?

    We do not audit vendors. What Velrim publishes, read 2026-10-25: GDPR stated on its privacy policy; on training with your data, “We do not use your documents, or values extracted from them, to train models.”.

  • Does Velrim give refunds?

    In its own words (terms of service, 2026-10-25): “Ask at [email protected] from your account address; the refund is executed by the Merchant of Record back to your payment method, with any tax adjustment handled by the Merchant of Record.”

  • What are alternatives to Velrim?

    In Documents, by use: Nanonets, Invoice Data Extraction, AllPDFMagic, Abstria, Gemina, Invofox.

How we read a tool

No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.

  • Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
  • Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
  • Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
  • The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.

How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.

How we read every tool → · By INITE Atlas Desk