9qeklajc
9beead5ece
A dead token (already spent, malformed, zero value) presented as a bearer key triggers a full mint redemption attempt on every request, because the failed attempt rolls back and leaves no api_keys row behind. Polling clients that never back off turn one dead token into thousands of pointless mint calls per day (~800/day observed against minibits alone), hammering mints that are already degraded. Add an in-memory bounded TTL+LRU cache keyed by token hash that remembers terminal redemption failures (already spent, invalid token, zero value, fees exceed amount). Repeat presentations are rejected locally with the exact same sanitized error envelope the mint-backed failure produced. Transient classifications (mint unreachable, rate limited) are never cached so a brief mint outage cannot poison valid tokens. The cache is deliberately memory-only: persisting a row per failed token would let an attacker fill the database with garbage tokens for free.
Routstr Payment Proxy
Routstr is a decentralized protocol for permissionless, private, and censorship-resistant AI inference. It combines Nostr for discovery and Cashu for private Bitcoin micropayments.
This repo contains Routstr Core: a FastAPI-based reverse proxy that sits in front of OpenAI-compatible APIs and handles pay-per-request billing.
Start Here
- Overview: https://docs.routstr.com/overview/
- Provider Guide: https://docs.routstr.com/provider/quickstart/
- User Guide: https://docs.routstr.com/user-guide/introduction/
Basic Usage
If you are a user/developer, you just point an OpenAI-compatible SDK at a Routstr node and pay with a Cashu token.
OpenAI SDK
from openai import OpenAI
client = OpenAI(
base_url="https://api.routstr.com/v1",
api_key="cashuBo2FteCJodHRwczovL21...",
)
response = client.chat.completions.create(
model="gpt-5-nano",
messages=[{"role": "user", "content": "hello"}],
)
print(response.choices[0].message.content)
cURL
curl https://api.routstr.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "x-cashu: cashuBo2FteCJodHRwczovL21..." \
-d '{
"model": "gpt-5-nano",
"messages": [{"role": "user", "content": "hello"}]
}'
Quick Start (Docker)
If you are a node runner, start a Routstr Core instance using Docker Compose:
-
Prepare your
.env:# Optional: encrypts node secrets at rest. If unset, the node generates a key # on first start, writes it to routstr_secret.key, and prints it once — back # up that file. Set it explicitly to manage the key yourself (recommended in # production). ROUTSTR_SECRET_KEY=<generated-key> NAME="My AI Node" DESCRIPTION="Fast access to models" RECEIVE_LN_ADDRESS=yourname@wallet.comYour Nostr identity (
nsec) is not set in.env— configure it from the admin UI after first start, where it's stored encrypted in the database. (NSECin.envis still read once as a legacy seed for existing deployments.)If you don't set one, a key is generated and printed on first start — save it somewhere safe (losing it makes previously encrypted secrets unreadable). To supply your own, generate it once and keep it stable:
uv run python -c "from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())" -
Start the services:
docker compose up -d -
Get your admin password: On first start the node generates an admin password and logs it once with the
/adminURL. Read it from the logs:docker compose logs routstr | grep -i admin(Lost it? Reset with
docker compose exec routstr /.venv/bin/python scripts/reset_admin_password.py --regenerate.) -
Configure: Open http://localhost:8000/admin/ to connect your AI providers and set pricing.
For full instructions, see the Provider Quick Start Guide.
Development
make setup
cp .env.example .env
fastapi run routstr