VoAPI/VoAPI

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

1076 stars · 127 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

VoAPI is a self-hosted AI large-model API aggregation and distribution gateway written in Go, deployed via Docker. It proxies requests to multiple upstream LLM providers while providing user management, API tokens, quotas, billing, rate limiting, and channel failover.

Use cases

• aggregate multiple llm api providers behind one gateway
• resell openai-compatible api access with quotas and billing
• manage api keys and user balances for llm access
• load balance and failover between llm channels
• self-host an api distribution platform for ai models
• track rpm and tpm usage per user and channel

When to choose

• you need a polished, self-hosted gateway to distribute LLM API access to multiple users with billing and quotas
• you want channel failover, retry, and per-key rate limiting across multiple AI providers
• you prefer a Docker-deployed Go service with multi-user management and i18n

When to avoid

• you only need a simple personal proxy for one provider without user management
• you require a fully permissive open-source license - the license is non-standard and some features are Pro-only
• you need a lightweight gateway without database dependencies like MySQL/Redis

Facets

service · maturity active

api-gateway proxy rate-limiting middleware webhook large-language-models apis self-hosted backend self-hosted go llm-gateway api-distribution openai-compatible token-management billing multi-tenant freemium ai-agents docker linux web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="VoAPI/VoAPI")