Analyze credential pooling operations and API reseller business models — economics, risks, detection patterns, and sustainability
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Framework for analyzing API reseller operations that use credential pooling (bulk account creation → free tier exploitation → resell access at markup).
Definition: Acquiring many free/trial accounts from a service, pooling their credits/quotas, and reselling access to end-users at a markup.
Common pattern:
User → Reseller API → Credential Pool (100s of accounts) → Official API (Claude/GPT/etc)
Economics:
Signals that indicate credential pooling:
✅ Pricing signals:
✅ Technical signals:
✅ Business signals:
Target pages:
Use escalation ladder (see cloud-browser-automation skill):
web_fetch firstKey data to extract:
{
"site": "example.com",
"tagline": "...",
"models": ["claude-opus-4", "gpt-5", ...],
"pricing": {"claude-opus-4": "$X per 1M tokens"},
"features": ["streaming", "openai-compatible", ...],
"contact": {"email": "...", "discord": "...", "telegram": "..."},
"location": "...",
"legal_docs": ["terms", "privacy", ...]
}
Calculate unit economics:
# Input costs
accounts_cost = 100 * 0.02 # $2 for 100 Google accounts
credits_per_account = 7.5 # $7.50 average free credits
total_credits = 100 * credits_per_account # $750
# Output revenue
markup = 0.5 # 50% of official price
official_price = 1.0
reseller_price = official_price * markup
revenue = total_credits / reseller_price # How much they can sell
# Profit
profit = revenue - accounts_cost
roi = profit / accounts_cost
Key metrics:
Operational risks:
| Risk | Impact | Likelihood | Mitigation |
|---|---|---|---|
| High ban rate | Service disruption | High (30-60%) | Diversify providers |
| Provider closes loophole | Business death | Medium | Have backup sources |
| Legal action | Shutdown | Low (hard to enforce) | Offshore entity |
| Detection patterns | Account bans | High | Rotate IPs, randomize usage |
| Credit exhaustion | Revenue loss | High | Continuous account creation |
Provider-specific ban rates (from user's data):
Detection signals providers look for:
Short-term (0-6 months):
Medium-term (6-18 months):
Long-term (18+ months):
Compare multiple operations:
| Operator | Models | Pricing | Location | Stage | Risk Level |
|----------|--------|---------|----------|-------|------------|
| adye.dev | 7 models | 50% off | Unknown | Operational | High |
| enowxlabs.com | Unknown | Unknown | Indonesia | Beta | Medium |
Differentiation strategies:
Characteristics:
Pros:
Cons:
Characteristics:
Pros:
Cons:
Characteristics:
Pros:
Cons:
Optimization:
Risk mitigation:
Scaling strategy:
Red flags:
Green flags:
After analysis, verify findings:
# Check if site is operational
curl -I https://example.com
# Test API endpoint (if public)
curl -X POST https://api.example.com/v1/chat/completions \
-H "Authorization: Bearer test-key" \
-H "Content-Type: application/json" \
-d '{"model": "claude-opus-4", "messages": [{"role": "user", "content": "test"}]}'
# Check DNS/hosting
whois example.com
dig example.com
# Check social presence
# Discord, Telegram, GitHub, Twitter
Executive summary:
## Executive Summary
[Site] is a [type] operation using [method] to provide [service].
**Economics**: ROI [X]x, [sustainability assessment]
**Risk**: [High/Medium/Low] — [key risks]
**Recommendation**: [Action for user]
Full report structure:
Problem: Some legitimate providers have lower costs (different infrastructure, regions, partnerships)
Solution: Look for multiple signals, not just price
Problem: High ROI looks attractive but ignores ban rate and provider countermeasures
Solution: Model worst-case scenarios (50%+ ban rate, free tier closure)
Problem: "Hard to enforce" ≠ "no risk"
Solution: Assess jurisdiction, provider aggressiveness, scale of operation
Problem: Pure reselling is commodity — easy to copy, race to bottom
Solution: Look for differentiation (features, reliability, niche, legitimacy)
references/chatgpt-pooling-proxies.md — Self-hosted ChatGPT pooling proxy solutions (PandoraNext, ChatGPT-to-API, Ninja)references/case-study-enowxlabs-adye.md — Case studies of existing operations还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
中文简介正在准备中。当前显示原文说明。
Airtable REST API via curl. Records CRUD, filters, upserts.
中文简介正在准备中。当前显示原文说明。
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
中文简介正在准备中。当前显示原文说明。
Build monitoring bots that poll APIs and send notifications on state changes (new listings, price alerts, status updates)
中文简介正在准备中。当前显示原文说明。
REST/GraphQL API testing with automated validation — test endpoints, validate responses, check status codes, and ensure API contracts
中文简介正在准备中。当前显示原文说明。
Manage Apple Notes via memo CLI: create, search, edit.
中文简介正在准备中。当前显示原文说明。