LLM Latency Tracker

Last 30 days

Uptime

100%

Response time

176 ms typical, 176 ms slowest 5%

Last check

1 h ago

Next check

in 5 h

How to call it

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "llm-latency-tracker": {
      "type": "http",
      "url": "https://llmlatency.dev/mcp"
    }
  }
}

2 tools

• get_ai_api_latency

  Measured latency (TTFB p50/p95) and uptime rankings of AI inference API providers by region, from llmlatency.dev.

• get_model_deprecations

  AI model deprecation calendar: announced and shutdown dates, replacement models, and how many days of migration notice each provider actually gives (median/min/max). Every entry is verified against the provider own deprecation page.

Security scan

• No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks