Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.manticscore.com/llms.txt

Use this file to discover all available pages before exploring further.

ManticScore uses a credit system to meter AI-powered operations. Each time you run a research job, start a Forge session, or send a chat message, a small number of credits is deducted from your balance.

​
Credit costs

OperationCredits
Market research3
Feature deep research3
Forge (agentic coding)2
Build graph1
Chat message1

​
Free tier vs. paid plans

Free tier: you receive 20 credits per day. Credits reset automatically every 24 hours based on your last reset timestamp. Pro and Early Access: credits are lifetime — they don’t reset daily and don’t expire.
The daily reset for free accounts runs automatically when you call GET /auth/bootstrap or GET /profile if more than 24 hours have passed since your last reset. No manual action is required.

​
Checking your usage

Your current credit usage is included in your profile and bootstrap responses. 
GET /profile
Authorization: Bearer <token>

{
  "credits_used": 3,
  "credits_total": 20,
  ...
}
When credits_used equals credits_total, the next AI operation that requires credits returns 429 Too Many Requests. Free-tier accounts recover automatically when the daily reset fires.

​
Rate limits

Credits and rate limits are separate mechanisms. Rate limits cap how many requests you can send per minute, regardless of your credit balance.
EndpointLimit
Research10 / minute
Feature research5 / minute
Chat20 / minute
Forge10 / minute
When a rate limit is hit, the response includes a Retry-After header indicating when you can try again. 
HTTP 429 Too Many Requests
Retry-After: 30
Rate-limited research requests with a valid session token may be captured to a retry queue rather than dropped entirely. Each account can have up to 5 pending queued requests.

​
Research quality stats

You can view aggregate quality scores across all completed research to understand how well the AI is performing on your ideas. 
GET /projects/quality-stats
Authorization: Bearer <token>

{
  "total_research": 10,
  "avg_quality_score": 72.5,
  "min_quality_score": 45.0,
  "max_quality_score": 95.0,
  "monthly": [
    {"month": "2026-04-01T00:00:00Z", "count": 3, "avg_score": 70.0}
  ]
}
Quality scores range from 0 to 100 and reflect factors like competitor coverage, feature depth, signal quality, and interpretation specificity.