By default we disguise activity on your pooled token — we only route traffic during your active session times and use sticky sessions so each consumer looks like one consistent user. You can further disguise it by using your own provider pool key, so your personal usage also goes through ClawPool and blends in with the rest of the traffic. The LLM provider has no way of telling the difference. From their perspective, it's indistinguishable from the provider sitting at their keyboard."
The correct response would be "Yes, it breaks Anthropic TOS".
Anthropic has been actively cracking down on this exact pattern. They've publicly stated they're "taking appropriate action" against account sharing and reselling, introduced weekly rate limits to combat it, and have been banning accounts that trigger abuse filters.
Their ToS explicitly prohibit reselling. Sellers risk permanent bans, buyers risk losing access overnight. Clever hack, but the runway seems very short.
To protect token holders I've put in a few tricks. Requests only route during the provider's normal active hours, and the whole thing looks like the subscriber just
had a busy afternoon. Anthropic sees normal usage patterns from a single account. I've had this running for weeks with no issues.
Proxy code is open source: https://github.com/peter-jammable/clawpool-proxy-function
I'm expecting some blowback on ToS despite the account protection — I'm all ears. Who wants $$$ and who wants cheap Opus? Form an orderly queue — no seriously,
there's a waitlist
Won't Anthropic just be able to get the IPs of your proxy by entering a known API key and observing what IPs use it? Could try to evade by tapping into a large proxy network though.
"Does this violate the terms of service?"
By default we disguise activity on your pooled token — we only route traffic during your active session times and use sticky sessions so each consumer looks like one consistent user. You can further disguise it by using your own provider pool key, so your personal usage also goes through ClawPool and blends in with the rest of the traffic. The LLM provider has no way of telling the difference. From their perspective, it's indistinguishable from the provider sitting at their keyboard."
The correct response would be "Yes, it breaks Anthropic TOS".
Anthropic has been actively cracking down on this exact pattern. They've publicly stated they're "taking appropriate action" against account sharing and reselling, introduced weekly rate limits to combat it, and have been banning accounts that trigger abuse filters.
Their ToS explicitly prohibit reselling. Sellers risk permanent bans, buyers risk losing access overnight. Clever hack, but the runway seems very short.
To protect token holders I've put in a few tricks. Requests only route during the provider's normal active hours, and the whole thing looks like the subscriber just had a busy afternoon. Anthropic sees normal usage patterns from a single account. I've had this running for weeks with no issues.
Won't Anthropic just be able to get the IPs of your proxy by entering a known API key and observing what IPs use it? Could try to evade by tapping into a large proxy network though.
Interesting idea, but I can see Anthropic coming down on this.
Also, you can have a Max at $100/month - that's what I have.