Provider pricing

Xinference AI API pricing

Xinference distributes LLM inference across heterogeneous GPU clusters with one CLI. Pricing is tracked alongside hundreds of other providers in the TokenCost directory so teams can compare cost, capabilities, and tradeoffs in one place.

Founded2023
HeadquartersHangzhou, China
Tracked modelsDirectory

Best for

Teams self-hosting LLMs across mixed hardware.

Strengths

  • Open-source distributed engine
  • Heterogeneous GPU support
  • Built-in model registry
  • Listed in the TokenCost AI providers directory