9qeklajc
a6dd105345
The streaming /v1/responses X-Cashu handler split the SSE body on the two-character sequence backslash-n and re-emitted with the same literal, so a real event stream was never framed into events. Even when a line happened to parse, usage and model were read at the top level, but the canonical Responses API nests them under "response" on response.completed. Both together meant usage was never found, the refund branch never ran, and the customer's whole token was retained. cost_data was also only bound inside that branch, so any path that did reach the re-emission loop would have raised NameError. Parse the body with a real SSE reader (CRLF, comment/keepalive lines, multi-line data fields, trailing event without terminator, [DONE] sentinel), resolve model and usage from the nested response object, and re-frame each event with genuine newlines so downstream clients get valid SSE. Settlement now always runs: unmeasured usage goes through the existing bounded fallback and settles at the authorized maximum with the remainder refunded, rather than silently keeping the full token.
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