Token Harbor
Access multiple AI models through a shared API, web chat, and coding-tool connections.
Route hosted and self-managed AI models through one gateway

Experiential Labs provides an open-source gateway for accessing AI models through a shared API endpoint. Teams can route requests to hosted providers, use their own provider credentials, or connect models running on their own infrastructure. The console brings together request logs, token usage, spending, and limits across people, agents, and models.
Administrators can create scoped keys, restrict model access, and set spending caps. Additional tools analyze traffic for model-routing and caching opportunities, with optional fine-tuning workflows that require activation by the user. The gateway can be self-hosted or used as a hosted service. Inference, hosted features, and plan allowances have separate terms, so a free gateway does not mean free model usage.
Tried it? Share a useful thought or ask a question.
Good conversations start with a hello.
Sign in to comment