gpu-io.net Request API

OpenAI-compatible inference on owned Macs

For smaller workloads, gpu-io.net can expose a managed API backed by local Apple Silicon. Bare-metal remains the primary product; API is added when the workload benefits from a managed endpoint.

API principles

  • OpenAI-compatible request format where practical.
  • Models listed only after license and commercial-use review.
  • No medical diagnosis, legal advice, or other high-risk production use without separate agreement.
  • Prompts are not logged by default for normal API operation.
curl https://api.gpu-io.net/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen3.5-27b","messages":[{"role":"user","content":"Hello"}]}'