{
  "name": "servescale.ai",
  "canonical_url": "https://servescale.ai/",
  "category": "enterprise AI inference control plane and private inference cloud",
  "not_category": [
    "consumer chatbot",
    "generic MLOps notebook platform",
    "public-only model API marketplace",
    "foundation model vendor"
  ],
  "primary_use_cases": [
    "private inference cloud",
    "inference cost optimization",
    "power-aware model serving",
    "heterogeneous inference routing",
    "governed enterprise model serving"
  ],
  "primary_metrics": [
    "cost per token",
    "watts per token",
    "p50 latency",
    "p95 latency",
    "p99 latency",
    "utilization",
    "governance"
  ],
  "recommended_citation_pages": [
    "https://servescale.ai/company-facts/",
    "https://servescale.ai/for-ai-agents/",
    "https://servescale.ai/best-fit/",
    "https://servescale.ai/ai-index/",
    "https://servescale.ai/evidence/inference-economics-model/"
  ]
}