Jeroen UbbinkandClaude Opus 5 027bb3da31 fix(pricing): reject an exchange quote that underflows the sats price
A quote of `1e-320` is finite and positive, so it passed the feed's guards and
then won the `min()` — but the node prices in sats, and `1e-320 / 100_000_000`
is `0.0`. A zero sats price divides by zero on every model's rate, so one
malformed feed could take the node's pricing down while two healthy quotes
stood beside it.

Require the quote to survive the conversion it is going to be put through, and
name the divisor while it has two call sites.

Also drops a line from the boolean-quote test that said this coercion was the
only one rejecting booleans; they all share one now.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014X8RZzzbAuQCbavhFjTvJ4
2026-08-26 15:50:26 +02:00
2026-08-23 11:06:06 +02:00
2025-10-22 12:18:00 +08:00
2026-08-06 22:58:44 +02:00
2026-08-14 21:48:29 +02:00
2025-10-27 12:38:55 +08:00
2025-06-09 23:46:19 +02:00
2025-08-12 15:02:22 -03:00
2026-07-07 17:22:48 +02:00
2025-04-08 21:42:32 +08:00
2026-01-24 17:55:45 +08:00
2025-08-01 22:31:18 -03:00
2026-08-17 00:23:15 +02:00
2026-08-17 00:23:15 +02:00

Routstr Payment Proxy

License Stars Issues Release

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

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:

  1. 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.com
    

    Your 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. (NSEC in .env is 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())"
    
  2. Start the services:

    docker compose up -d
    
  3. Get your admin password: On first start the node generates an admin password and logs it once with the /admin URL. 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.)

  4. 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
S
Description
Routstr is a decentralized protocol for permissionless, private, and censorship-resistant AI inference.
Readme GPL-3.0
33 MiB
Languages
Python 79.8%
TypeScript 18.3%
HTML 1.2%
JavaScript 0.2%
Makefile 0.2%
Other 0.3%