Generate startup ideas
Synchronous idea generation - the backing route for the generate_ideas MCP tool. Spends no scan quota or tokens. Standard runs have an account hourly limit. Free accounts get 5 Standard generations per rolling 24 hours per account (GENERATION_LIMIT when exhausted). Paid-or-credited accounts get limit: null, under a ceiling of 20 Standard generations per rolling 24 hours per account, shared with the idea generator on preuve.ai and refused with DAILY_LIMIT_REACHED. Eligible Pro runs skip hourly and daily generation caps and return limit: null and remaining: null. After three refunded Pro runs (failed, timed out, paused or abandoned) in a rolling hour, the account’s next Pro run is refused with RATE_LIMITED and a Retry-After; a delivered Pro run never counts. General API request-rate protection still applies. The standard model runs unless pro: true asks for the Pro model, which costs 10 credits a run. The response pro says whether Gemini 4 Argon answered. A recoverable Pro failure retries the same Argon model once, never a different model. Each attempt allows 180 seconds. Allow up to 425 seconds end to end. A delivered Pro answer settles one 10-credit hold; final failure, pause or deadline releases that hold. pro: true on an account holding under 10 credits is refused before anything is spent: 402 INSUFFICIENT_CREDITS (details.balance and details.required) when the account can buy credits, else 403 PRO_PAID_REQUIRED. A pro that is not a boolean or null is 400 INVALID_INPUT. Founder-profile tailoring is automatic on paid plans with a saved profile (fit: false opts out); the response’s fitReason and fitHint state why tailoring did or did not apply.
Authorizations
Body
Response
Generated ideas. remaining and limit are null for paid-or-credited accounts, whose daily ceiling is not counted down here; free accounts see the rolling-24h window state. Pain points are teased as locked on non-paid plans.