1,000
upstream keys
Gateway API jailbreak
One gateway. Every model. Uncensored.
A pool of 1,000 upstream keys behind one OpenAI-compatible endpoint. Three jailbreak carriers, a scoring ledger, and a route that does not refuse.
Works with
3
pinned models
2
wire protocols
0
token caps
The route
What the gateway actually does
Three moving parts, all measured per request. Nothing on this page is a claim you cannot check against the ledger.
Pool
1,000 keys, rotated per request
Every call takes the next key from the pool and the next model in the class. The upstream cap is per model, not per key, so both rotate together.
1,000 keys
per-model rotation
exhausted -> 502
Carriers
Three jailbreak carriers, ranked
The ask is classified first, then the carriers for that class are ordered from the ledger. A refusal, or a prose answer to a code ask, is scored a loss.
laz-max
universal
universal-lite
Ledger
Every route is measured
Time to first token, escalation count and refusal count are written per request. The ranking is a number from that table, not a claim from a page.
ttft
escalations
refusals
Quickstart
From key to answer
Three steps, no SDK to install. If your client speaks OpenAI, it already works.
01
Create a key
Register with Discord, open the profile page, and copy the token. That is the whole signup.
02
Swap the base URL
Leave the SDK alone. Replace the host with this gateway and send the same payload.
03
Read the completion
The carrier that answers is the one the ledger ranked first. If it loses, the next one is tried before you see an error.
curl https://lazarus-th.duckdns.org/health
{"ok": true,
"models": ["Mythos China", "LARP", "LAZARUS"],
"served": 5, "escalated": 0, "refused": 5}
One key. The model you asked for.
Create a key, point your client at this gateway, and send the same payload you already send.