routstr-devandredshift f1d4b3c175 fix(ehbp): restore the version prefix on EHBP upstream paths
The proxy accepts an API endpoint with or without a leading `v1/`
(`_canonical_api_path`) and forwards the caller's path verbatim, so a
client that spells the endpoint `chat/completions` reaches the upstream
as `chat/completions`. That is fine for providers whose `default_base_url`
carries the version prefix (openai, groq, fireworks, ...) — the client's
`v1/` is stripped and the base URL re-adds its own — but Tinfoil's base URL
is unversioned and its router serves only `/v1/...`. Every Tinfoil request
from such a client therefore got

  404 {"error":{"message":"Not found.","type":"invalid_request_error"}}

from `https://inference.tinfoil.sh/chat/completions`, while the same
request with the prefix succeeded. Tinfoil's own error text blamed the
model id, which sent the search in the wrong direction.

Give the EHBP path builders the same hooks the non-EHBP forwarding path
uses: `normalize_request_path` strips the client's optional `v1/`, and a
new `ehbp_path_prefix` re-adds the prefix the provider's enclave actually
serves (`v1` for Tinfoil, `private/v1` for PPQ.AI, whose target had the
same latent bug). Both spellings now reach the same upstream URL.

`_resolve_ehbp_target_url` re-appended the caller's raw path to the
client-supplied enclave URL, re-introducing the spelling the provider had
just normalized away; it now takes the path from the target URL the
provider built, so the override swaps the host only.
2026-10-04 15:15:23 +08:00
2026-09-16 13:15:32 +02:00
2025-10-22 12:18:00 +08:00
2026-08-06 22:58:44 +02:00
2026-10-01 11:58:08 +02:00
2025-06-09 23:46:19 +02:00
2025-08-12 15:02:22 -03:00
2025-04-08 21:42:32 +08:00
2025-08-01 22:31:18 -03:00

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, the recommended way to start Routstr Core is to clone the repository at the latest release and run it with Docker Compose:

  1. Clone the latest release:

    git clone https://github.com/Routstr/routstr-core.git
    cd routstr-core
    git checkout v0.4.7   # current release — see https://github.com/Routstr/routstr-core/releases/latest
    

    Docker Compose builds the node and the admin dashboard from source, so there is no image to pull.

  2. Prepare your .env:

    cp .env.example .env
    

    Then edit it with your details:

    # 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())"
    
  3. Start the services:

    docker compose up -d
    

    The first start builds both images (the dashboard build takes a few minutes).

  4. 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.)

  5. 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%