Research Any Company List Without Buying a Database
Your agent can find companies by size, industry, tech or funding, then pull funding history, headcount
and leadership across eleven providers — paying per record instead of buying a database.
$1.00 of free credit on every new team. No provider signup, no credit card.
Company search alone has eleven providers behind it, from free to $0.38 a record. Your agent
sees that before it calls.
compared on this page
The economics
The old way vs. the treg.to way
The old way
With treg
What you pay for
Crunchbase $99/mo + Diffbot $299/mo, whether you run a search this month or not
One prepaid balance. Company search starts at free and tops out at $0.38 a record
Keys
An account and a contract per data vendor, most of them annual
One treg token. Every tool in the catalog answers to it
Picking a provider
You buy one and find out afterwards whether it covers your market
catalog get puts all eleven side by side with price, measured success rate and median speed
Commitment
Annual data contracts to answer a question that changes every quarter
No subscription. Test coverage for cents before committing to anything
The workflow
Funding in one tool, headcount in another, people in a third, joined in a spreadsheet
One agent run: companies, their funding and the people attached to them, in one pass
Instead of$398/moCrunchbase + Diffbot, at list
→
You paid$0.102what our run actually cost
Try it
A real workflow
Copy this into Claude Code, Cursor, Codex or opencode
1Set treg up in your agentfirst time only
Paste this into the same agent. It installs the CLI, signs you in and registers the
tools. One line, once — already set up? Skip to step 2.
setup
set up treg — https://treg.to/llms.txt
2Run the workflow
the prompt
Find AI infrastructure companies with 20-200 employees. For each one, pull its
funding history, headcount and leadership, and flag the ones that raised most
recently.
What happens when you run it
The agent finds the companies. Eleven providers answer company search, and the spread is the widest
in the catalog:
Provider
Cost per company
Success rate
Median
Akta
free
100% (248 calls)
3.2 s
Coresignal
free — returns ids; cost lands on the read
not yet measured
—
Hunter Discover
free
100% (24 calls)
1.7 s
The Companies API
$0.0019, or free with simplified=true
100% (339 calls)
0.3 s
Lusha
$0.004992 per 25 results
not yet measured
—
LeadMagic
$0.025
70% (10 calls)
3.2 s
Apollo
$0.026 per page
not yet measured
—
Diffbot
$0.0299
100% (5 calls)
0.7 s
PDL
$0.38
not yet measured
—
Crunchbase
own key only, no per-call price
not yet measured
—
A 200× spread for the same job, and three of the eleven are free. That table does not exist anywhere
else, because building it means holding accounts with all eleven.
It pulls the detail. Funding history at $0.10 a company with LeadMagic; company enrichment at
$0.026 with Apollo or $0.392 with Coresignal; the LinkedIn company page — headcount, leadership, location —
at $0.00188.
It finds the people attached to the signal. Person enrichment from $0.025, so the output is a
company, a reason to talk to them, and who to talk to.
Read this before you build on it. Coverage differs sharply by provider and by company size — see the
funding results in the evidence below, where two small recently-funded startups returned nothing and
Stripe returned a full history. Test coverage on your own list first; the misses are free.
What comes back
what comes back
AI infrastructure · last 90 days · pulled [date]
COMPANY HEADCOUNT SIGNAL STRENGTH DECISION-MAKER
<company> 140 (+22) <round> raised <date> strong <name>, <title>
<company> 68 (+15) hiring in <function>, <n> roles medium <name>, <title>
<company> 310 (+4) <signal> weak <name>, <title>
...
RANKED SIGNALS
1. <signal type> — <n> companies, most recent <date>
2. <signal type> — <n> companies
...
PROVIDERS USED <provider> (search) · <provider> (funding) · <provider> (people)
COST $[from your run]
Structure is illustrative. Values come from the providers, relayed unchanged.
Evidence
Proof — from one real run
Run on treg.to, 17 Aug 2026. Every figure is from the Activity log of that run.
Hunter Discover is free, takes a plain-English brief and resolved it into explicit funding and headcount filters. LinkedIn company data at $0.00188 was the cheapest way to add headcount and leadership
Total cost of the run
$0.10188 — discovery free, one enrichment, one funding lookup (two further funding lookups missed and cost nothing)
Subscription cost avoided
$398/mo at list — Crunchbase $99 + Diffbot $299
Time to completion
Under 5 seconds
Data freshness
Live at call time
Companies returned
9, filtered to recently funded AI infrastructure at 20–200 employees
Cost per company researched
$0.00 for discovery; $0.00188 per company enriched
What the free call returned. Nine companies with domains and contactable-address counts — Daloopa,
ZincFive, Ethernovia, RunPod, AttoTude, Netris, Bobyard, Normal Computing, Arycs Technologies. Hunter
translated the brief into filters and showed its working: headcount 20-50 and 51-200, funding series
pre-seed through series C+.
The honest read of this run, and it is the most useful thing in it. The LinkedIn enrichment returned
the wrong company. Asked for linkedin.com/company/runpod, it correctly returned a 2-person retail
partnership in Sligo, Ireland — because that is what lives at that URL. The AI infrastructure company is
at /company/runpod-io. The provider answered exactly what was asked, and a confident wrong answer cost
$0.00188.
This is the catalog's first selection rule in practice: match the inputs you actually hold, ahead of
price. It is also why treg.to relays your request rather than rewriting it — a system that silently
"corrected" that URL would have guessed, and guessed inside your research.
The funding leg, run separately. LeadMagic's funding endpoint was tried on three companies:
Company
Result
Charged
runpod.io
no funding data
$0.00
daloopa.com
no funding data
$0.00
stripe.com
full history — $9.8B total raised, revenue, last round, named investors
$0.10
This is the finding that should change how you use this page. The endpoint works, and works well —
Stripe came back with founding year, headquarters, revenue, total funding, the most recent round and the
investor list. But it found nothing for either small recently-funded startup, which is precisely the
segment the example prompt targets. Coverage is strongest where public reporting is strongest.
The cost structure absorbs this: both misses were free, so testing coverage on your own list costs
nothing until it works. Test before you build a workflow on it.
What this page does not cover. Activity and hiring signals are a different job from the one above,
and this workflow does not do them — everything shown here is company search, funding, headcount and
leadership. If your work depends on hiring or intent signals, check the catalog for what serves that
capability before you build on it.
Outcomes
Three things you can do the day you sign up
Test whether your market is the size you think it is.
Company search starts free. Before anyone signs a data contract, run the filters that define your ICP and
count what comes back.
Build a research brief on a company in one prompt.
Funding history, headcount, leadership and the LinkedIn page, pulled together — for well
under a cent when the cheap providers cover it.
Watch a list for changes rather than re-researching it.
Run the same company set monthly and have the agent report only what moved: new funding, headcount jumps,
new leadership. A quiet month costs almost nothing.
Fit
Who this is for
Founders sizing a market or a partner list without buying a database to find out.
Investors tracking a sector's funding and hiring without a per-seat data platform.
Sales teams who want a reason to reach out attached to every account, not just a name.
Market researchers and developers building research agents who want one surface across eleven company data providers and one bill.
Questions
Before you sign up
Why not just call the providers directly?
Because the answer to "which company data provider should I buy" is genuinely unknown until you test it
against your own market — coverage differs far more than price does, and the price differs by 200×. Buying
one to find out is the expensive way. Testing all eleven for a few cents is not. If you already pay for
one, connect it and those calls route through your key, unmetered. treg.to is closer to OpenRouter for
agent tools than to a data vendor: one base URL, one token, many providers behind it.
How are credentials handled?
The credential is injected on the server. Your agent makes the real upstream request through treg.to's
/call/ endpoint; treg.to adds the key and relays the provider's answer back verbatim. No provider key
is ever written to your machine, your repo or your agent's context. Every call is recorded and attributed
to the token that made it.
Can I choose a specific provider?
Yes. Every endpoint has an id, and calling it by id calls that provider. If you want the choice made once
for the whole team, treg org pin <capability> --provider <provider> refuses calls to any other provider
of that capability.
(The point of this page. Test broadly first, then pin the one that covered your market, so
the whole team's numbers stay consistent.)
Can I use my existing provider key?
Yes, and it takes precedence. Register the key once and every call to that provider routes through it —
those calls are never metered against your treg.to balance. Your key always wins over treg.to's.
(Crunchbase is own-key only here — if your team has a licence, connect it and those calls cost nothing on
treg.to.)
What happens if a provider fails?
treg.to does not silently reroute you. That is deliberate: only you know which inputs you actually hold,
so treg.to relays your request rather than rewriting it. What your agent gets instead is the information
to recover — it already knows the alternatives and their parameters, so on a 429, a 5xx or a timeout it
can try the next provider and tell you which one it switched to. Failed calls are not billed. If a call
succeeded upstream but the answer was lost coming back, an Idempotency-Key returns the stored result
without paying twice.
How much does a call cost?
Company search is free with three of the eleven providers and $0.38 a record at the top end. Funding
history is $0.10 a company; person enrichment from $0.025. The exact price is
shown before the call, and treg.to adds no markup. New teams start with $1.00 of free credit.
Which agents does it work with?
The installer registers treg.to's MCP server into Claude Code, Cursor and opencode automatically. Any MCP
client that supports the authorization spec can connect with OAuth. Anything that can run a shell command —
Codex included — can use the treg CLI or plain HTTP.
Research a market this afternoon, without buying a database
