API · LIGHT
$0.20 / call
~1.5 min
- verdict + weakest point
- evidence with source links
- one first test + when to stop
- live web research · default tier
Cheaper than one wasted weekend.
Agents pay per call — $0.20 light, $0.50 full, refunded on failure, and the idea is deleted right after delivery. Humans get the same engine in the browser, from $14 a credit: a quick check is 1 credit, a full check 3. No subscriptions.
API pricing · per call
Cheaper than the prompt.
Your agent burns more than $0.20 thinking about whether to build. Pay per verdict, only when it is delivered — and the idea is deleted right after.
API · FULL
$0.50 / call
2–3 min
- everything in light
- deeper web research
- competitor + risk detail
- directions on PIVOT / CONDITIONAL_GO
API · DOMAINS
$0.20 / call
30–70 s
- up to 10 free domains
- built on real Bing search volumes
- niche + competitor research
- a reason for every name
- prepaid balance · min top-up $20
- failed calls are refunded to balance
- key without sign-up — one POST
- idea + report deleted after delivery
- 10 calls/min · 5 running per key
- llms.txt for your agent
- using IdeaKiller in ChatGPT or Claude? add funds to that key on the key page — the chat does not sell credits
- docs for agents: llms.txt
Web app · pay per report
No code? Same engine, in a form.
The browser app runs the same engine. A quick check costs 1 credit and takes about 90 seconds, with live web research. A full check costs 3 credits and takes 2–3 minutes. Every account gets 3 free credits every month. Credits never expire.
Starter
$14 / 1 credit
$14 a credit
- 1 quick check with live web research
- Weakest point + one first test
- Evidence with source links
- Devil's advocate
- Markdown export
Builder
$39 / 3 credits
$13 a credit · save 7%
- 1 full check or 3 quick checks
- Everything in Starter
- PDF export
- Side-by-side compare
- Priority queue
Pro
$69 / 7 credits
$9.86 a credit · save 30%
- Everything in Builder
- Priority processing
- Email support
FAQ · agents
Questions, answered.
Does my agent need an account to call the API?
No. One POST to /agent/v1/keys returns a key — no email, no sign-up. The key is shown once, so store it. The same key works for REST and MCP.
How does an agent pay for calls?
Every call is prepaid from a balance. POST /agent/v1/topups returns a checkout_url that a human pays once — minimum $20. After that the agent spends $0.20 per light call and $0.50 per full call on its own. There are no free calls.
What happens to my idea after the verdict?
It is deleted. Right after the result is delivered, the idea text and the report are wiped. A result that is never fetched is purged after 60 minutes. We keep only the fact of the call: time, tier, price, duration, and the error if it failed. Ideas are never published and never used to train models.
What if my agent sends garbage or an empty idea?
Nonsense or empty input is rejected up front, before any web search runs — and the call price is refunded. You never pay for a call that could not produce a real analysis.
What if a validation call fails midway?
The full call price goes back to your balance automatically. You only pay for delivered verdicts.
Is there an MCP server?
Yes: https://api.ideakiller.app/mcp (streamable HTTP, stateless). It exposes five tools — validate_idea, get_validation, find_domains, get_domains, get_balance — and uses the same key, prices and balance as REST. Add funds on the website, not in the chat. Works with Claude Code, Cursor and any MCP client.
Where are the machine-readable docs?
The full reference is at api.ideakiller.app/agent/v1/docs, and there is an llms.txt at api.ideakiller.app/llms.txt that any agent can read before its first call.
What are the rate limits?
Up to 10 validation calls per minute and 5 running validations per key. New keys are limited per network and per day.
Every week on a dead idea is a week you don't get back.
Check it where you already think — in ChatGPT or Claude. The first check is free while today's free checks last.