SLA

• SLI - Service Level Indicator - 服务水平指标
  • 量化指标
  • 例如 响应时间、请求成功率等
  • Latency, Error Rate, Throughput, Availability
• SLO - Service Level Objective - 服务水平目标
  • 水平目标
  • 例如 系统响应时间小于 200ms
• SLA - Service Level Agreement - 服务水平协议
  • 承诺水平
  • 未满足 SLO 的补偿协议
• Error Budget - 允许的错误范围
• Uptime/Availability - 可用性
• Downtime - 停机时间
• Downtime Period - 停机时间段
• Error Rate - 错误率

---

• Azure OpenAI SLA
  • 99.9%
  • https://azure.microsoft.com/en-us/products/ai-foundry/models/openai/
  • https://www.microsoft.com/licensing/docs/view/Service-Level-Agreements-SLA-for-Online-Services
• Google Cloud Gemini SLA https://cloud.google.com/products/gemini/sla
  • Monthly Uptime >= 99.9%