octopus

Octopus is a self-hosted LLM API aggregation gateway, written in Go with a Next.js frontend, that lets individuals route requests across multiple LLM providers through a single unified endpoint. It connects to Claude and other models via direct API integration, and notably handles protocol conversion between OpenAI Chat, OpenAI Responses, and Anthropic API formats, meaning tools like Claude Code can point to an Octopus instance without modification. Key features include multi-key rotation per channel, latency-based smart endpoint selection, automatic load balancing across providers, model list synchronization, and automatic price updates for cost tracking. The web management panel provides dashboards for request analytics, token consumption, and spending by channel. Deployment is straightforward via Docker or a single prebuilt binary, with SQLite as the default database and optional MySQL or PostgreSQL backends. Developers and power users managing API budgets across several providers are the primary audience.

What people ask about octopus