Documentation
inference.club is a community-run inference network. Members run GPUs at home and expose their local model servers; everyone calls those models through one OpenAI-compatible API. One key works in both directions — to consume inference and to provide it.
Base URL https://api.inference.club/v1
Auth Authorization: Bearer <your-api-key>
Start here
Get a key and make your first request in five minutes.
For AI agentsModel discovery, routing, async, and workflows — written for automated callers.
ConceptsThe vocabulary: users, keys, providers, agents, models, routing.
Become a providerShare your own GPUs on the network with the Kubernetes agent.
What you can build with
The network serves far more than chat. Which modalities are live depends on what models the providers are running right now.
A browser tool for every modality — chat, agents, images, video, music, voice, and more.
Services & modalitiesEach model type, the endpoint it answers, and the model behind it.
API referenceEvery endpoint, request shape, and error code.
Async, batches & workflowsFire-and-forget jobs, 256-item batches, and multi-step DAGs.
How it fits together
A small always-on cloud box is the control plane — the website, the API, auth, routing, billing, and async orchestration. The heavy GPU compute lives on home hardware that is never exposed to the internet. A private Tailscale tunnel bridges the two, and generated media is offloaded to object storage so the small box stays off the hot path.
OpenAI SDKs · curl · browser · agents
inference-club-agent (kubernetes discovery) routes /v1/* to in-cluster services across 3× RTX 4090 + DGX Spark
The agent reports what it serves every ~30 seconds, so the platform's model list and routing always reflect what is actually online. For the full story — request path, the home k3s cluster, the Hetzner deployment, and storage — see Architecture.