dev.llmlatency/llm-latency-tracker

up checked 2026-11-11T01:37:39.689Z

Unclaimed · Unverified

Publisher-provided title

LLM Latency Tracker

Publisher-provided description

Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.

Summary by lookupd

Lets an agent query measured latency, time-to-first-token, uptime rankings, and model deprecation schedules for AI inference API providers.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http llm-latency-tracker https://llmlatency.dev/mcp

Codex, remote (streamable-http)

codex mcp add llm-latency-tracker --url https://llmlatency.dev/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

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

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

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/

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/dev.llmlatency/llm-latency-tracker.svg)](https://lookupd.com/servers/dev.llmlatency/llm-latency-tracker)