9qeklajc a7d4e2832d fix: gate upstream-reported cost behind a per-provider trust policy
A positive cost reported by an upstream pre-empted token pricing with no
check on who reported it. Because the bearer overrun path settles
min(chargeable, total) against the key's balance minus sibling
reservations, any configured or chained provider that controls an
accepted cost field could bill far beyond the reservation it was
authorized against and drain the key. The mirror case bled the operator:
an under-reporting provider with omitted token usage settled at its own
low number.

Reported cost is now honoured only for provider types that opt in via
BaseUpstreamProvider.trusts_reported_cost, which defaults to off. A new
provider therefore prices from tokens until someone deliberately approves
it. PPQ.AI (BYOK — only PPQ knows the user's upstream bill) and
OpenRouter (per-request sub-provider routing) are approved; chained
Routstr peers and generic/custom rows are not. This is a policy gate, not
a clamp: PPQ BYOK legitimately settles above the reservation and still
does.

The flag is threaded from the serving provider instance through
adjust_payment_for_tokens to calculate_cost alongside provider_fee, at
every streaming and non-streaming settlement site in the upstream base
provider, so the two paths agree.

Two supporting changes:

- _coerce_usd rejects non-finite input. Infinity previously survived the
  clamp and reached math.ceil, where the OverflowError was swallowed by
  the USD path's broad handler — correct by accident. NaN was already
  folded to zero by max() comparison semantics; it is now explicit.
  Nothing about int/float msats arithmetic changed, so billing amounts
  are unaffected.

- A trusted provider's cost is compared against what its own reported
  tokens would have been priced at, and against the reservation. Ratios
  outside the bounds are logged in both directions. They are not
  clamped: the legitimate BYOK spread is wide enough that clamping would
  mis-bill real traffic, so the goal is that a mis-report is visible
  rather than silent.

Existing USD-path tests now declare their provider as cost-reporting;
no assertion was changed.
2026-08-25 00:38:12 +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
2025-10-16 16:03:39 +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%