Free-tier first routing

Opensource. MIT License.

Scavenge every free LLM token with a single OpenAI-compatible gateway.

TokenScavenger is a lightweight Rust router that prefers free-tier providers, falls back automatically, and exposes a single API surface for existing OpenAI clients.

View on GitHub Read docs

Live status

All providers central health and fallback routing.

LIVE

Scavenged tokens

12.4M

Providers

14+

Install

Start with the latest release binary

Download one self-contained binary, run it, and let the setup wizard guide you through provider keys and routing policy. Use the current version shown on the latest release page.

Latest release downloads

Apple Silicon binary

Download the signed and notarized archive, unzip it, then launch the setup wizard.

VERSION=v0.1.2
curl -LO https://github.com/kabudu/token-scavenger/releases/download/$VERSION/tokenscavenger-$VERSION-aarch64-apple-darwin.zip
unzip tokenscavenger-$VERSION-aarch64-apple-darwin.zip
./tokenscavenger

Static Linux binary

Use the x86_64 release artifact for most server installs.

VERSION=v0.1.2
curl -LO https://github.com/kabudu/token-scavenger/releases/download/$VERSION/tokenscavenger-$VERSION-x86_64-unknown-linux-gnu
chmod +x tokenscavenger-$VERSION-x86_64-unknown-linux-gnu
./tokenscavenger-$VERSION-x86_64-unknown-linux-gnu

Windows executable

Fetch the release executable with PowerShell.

$Version = "v0.1.2"
$Url = "https://github.com/kabudu/token-scavenger/releases/download/$Version/tokenscavenger-$Version-x86_64-pc-windows-msvc.exe"
Invoke-WebRequest `
  -Uri $Url `
  -OutFile tokenscavenger.exe
.\tokenscavenger.exe

Release artifacts include SHA256 checksums. Prefer source builds, Docker, systemd, or reverse proxy deployment?

Deployment docs

Providers

Native support for 14+ free-tier and fallback endpoints

Built-in adapters for the most important free inference providers plus DeepSeek and xAI paid fallback, with per-provider health, rate-limit handling, and model group-aware routing.

Groq

Llama 3 · Mixtral

Gemini

Free and flash models

Cloudflare

Workers AI routing

GitHub

Azure-hosted models

Mistral

Free model discovery

Cerebras

CSoft inference

NVIDIA

NIM endpoints

SiliconFlow

DeepSeek v3

DeepSeek

Paid fallback

xAI Grok

Paid fallback

Why TokenScavenger?

Tokens are the new currency of the AI era. TokenScavenger ensures you get the most value out of every free token available.

Drop-in OpenAI compatibility

Keep your existing OpenAI SDKs and only update the base URL. TokenScavenger normalizes provider differences at the adapter boundary.

Smart circuit breakers

Automatically detect provider failures and route traffic to the best available free provider without client-side changes.

Single binary Rust

Self-hosted durability in one static binary. No Python runtime required for core production operation.

Open Source

Built in public for self-hosted operators

TokenScavenger is MIT-licensed, inspectable, and designed to run as infrastructure you control. The routing rules, provider adapters, SQLite schema, release workflow, and operator UI live in the repository.

View on GitHub MIT license

Transparent routing

Provider selection, fallback policy, and rate-limit behavior are visible in code, docs, logs, metrics, and the admin UI.

Self-hosted by default

The core runtime is one Rust binary with SQLite storage and no required managed control plane.

Contributor-friendly

Provider adapters follow a shared abstraction, making new upstream integrations easier to review and maintain.

Release artifacts

Cross-platform release builds include checksums so operators can verify the binary they deploy.