Provider pricing

Vultr Cloud Inference AI API pricing

Vultr Cloud Inference is a serverless LLM service from Vultr, founded in 2014 and headquartered in West Palm Beach, FL. Auto-scales Llama, Mistral, and Mixtral inference across 32 global edge regions.

Founded2014
HeadquartersWest Palm Beach, FL
Tracked modelsDirectory

Best for

Apps needing low-latency inference at the global edge.

Strengths

  • 32 global edge regions for low-latency inference
  • Serverless auto-scaling with per-token billing
  • Bundled with Vultr block, object, and VPC networking
  • Listed in the TokenCost AI providers directory