You need rows.
You pay for rows.

Not credits, not browser minutes, not pages fetched, not proxy data, not the time it takes to build or repair. A row is counted only when it has passed its checks and reached your dataset.

Building is free. Previews are free. Repairs are free.

Rows you expect to collect each month with Radar

  • Free to 100 rows
  • $49 minimum to 5,000 rows
  • Metered above that
  • Enterprise above 1M rows

Monthly estimate Metered

~$82/mo

$8.22 per 1,000 rows

  • Collection, checks, automatic repair and delivery included
  • Billed at month end for the rows you actually collected
  • Retries, blocked pages and repairs never count
Start with 100 free rows

We hate credits too. No upfront billing and no commitment. A row only counts once it has passed type, null and duplicate checks and reached your dataset. Paid usage carries a $49 monthly minimum.

A few practical questions.

What do I get for free?

100 rows each month. Build and run your pipelines, keep datasets refreshed and connect your own tools or agent. No credit card required.

Do unused rows roll over?

No. Your 100 free rows renew each calendar month (UTC); unused free rows don’t carry over. Paid usage is billed at month end for the rows you actually collect, with a $49 minimum above the free allowance. You aren’t buying a prepaid bundle, so there’s no paid row balance to roll over.

Can I choose any number of rows?

Yes. Enter the number of rows you expect to collect, down to an individual row. The calculator shows an estimate, not a prepaid quota. You’re billed at month end for the rows you actually collect, with a $49 minimum above the free allowance.

How is my monthly bill calculated?

Up to 100 rows collected in a month: no charge. From 101 to 5,000 rows: $49. Above 5,000 rows, your bill scales smoothly with actual usage. At month end, paid usage is billed at the greater of $49 or the rows you collected multiplied by the per-row rate for that volume. The slider estimates that bill; you don’t prepay for the selected number of rows.

Why does a row cost more than a page fetch?

A row costs more than a page because a page isn’t data yet. Jsonify extracts the fields, matches and checks the rows, delivers the dataset and maintains the pipeline when sources change. Compare a fetch API with a maintained dataset →

What counts as a useful row?

A row that passed checks and arrived where your team reads it. Retries, blocked pages and repairs don’t count.

Does this calculator cover Benchmark?

These prices are for Radar collection. Benchmark is available through enterprise and has not launched in self-serve. Book a demo to discuss your quote volumes.

Can I use my own agent?

Yes. Connect Jsonify through MCP or the plugin and use the same datasets from your preferred client. See connection instructions.

When should I choose enterprise?

For more than a million rows per month, or when you want help designing, onboarding and operating a managed data program. We’ll agree the sources, schedule, checks and delivery with you. Explore enterprise.

Build your first dataset.

Start with 100 rows free. No credit card required.

Connect your data assistant

Build datasets and work with your data in Claude, ChatGPT, Copilot or another assistant.

Connect in Claude

  1. Open the Jsonify connector: Open on Claude.ai ↗
  2. Select Connect and sign in to Jsonify.
  3. In a chat, enable Jsonify under + → Connectors and describe the data you need.
Advanced

Team or Enterprise account? Your workspace owner enables Jsonify once for everyone from Admin settings → Connectors. Jsonify is a community connector in the directory — some admins allow those by default, some review them first.

No directory? Add it by hand: Settings → Connectors → + Add custom connector, name it Jsonify, paste the server URL below, then Connect.

Server URLhttps://factory.jsonify.com/mcp

Official Claude custom-connector guide ↗

Then say: “build me a dataset of competitor product prices and availability, refreshed daily”. Full instructions per client on /connect.