ShareInference

-- tokens served

Community-powered AI inference: share GPU time from a browser tab, spend it through an OpenAI-compatible API.

Connecting to the network...

Provide inference (earn credits)

Share your spare Mac or PC GPU straight from a browser tab. Nothing to install.

  • Earn credits for every token you serve (1 per input token, 5 per output token)
  • Auto-detects WebGPU capabilities
  • Runs quietly in a background tab; the model downloads once and is cached
Start Sharing GPU

Needs Chrome or Edge with WebGPU: Apple Silicon or a recent NVIDIA / AMD GPU

Access inference (spend credits)

Use an OpenAI-compatible API endpoint with open models from your apps.

  • Free tier with fair-queue access from day one
  • Spend credits for priority routing at the front of the queue
  • Standard OpenAI REST and streaming API (docs)
Get API Key & Start

Endpoint: ...

Top GPU providers

Top GPU providers
RankContributorTokens servedStatus

Loading...

See the full leaderboard