infermux Documentation

Getting Started

• Overview What infermux is and what problems it solves.
• Quick Start Route your first inference request in five minutes.
• Installation Install the CLI and Go package.

Core Concepts

• Providers Configure model providers: OpenAI, Anthropic, Ollama, and more.
• Routing How infermux selects a provider for each request.
• Circuit Breaking Automatic failover and recovery from provider failures.
• Cost Tracking Per-request token accounting and spend attribution.

Reference

• CLI Reference All commands and flags.
• HTTP API Drop-in OpenAI-compatible HTTP API.
• Configuration infermux.yml schema and defaults.
• Go API Programmatic router and provider registration.

Guides

• Provider Setup Configure each supported provider with credentials and limits.
• Cost Optimization Route by cost, set spend caps, and track attribution.