MCP server

LLM Latency Tracker Official

dev.llmlatency/llm-latency-tracker

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

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

Website Source

At a glance

Type

MCP server

Publisher

llmlatency.dev (verified by the MCP Registry)

Status

Working at last check

Tools

2

Token cost

About 216 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

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

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.llm-latency-tracker]
url = "https://llmlatency.dev/mcp"

Gemini CLI

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

Cursor

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

VS Code

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

Antigravity

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

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"llm-latency-tracker","server_url":"https://llmlatency.dev/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"llm-latency-tracker","server_url":"https://llmlatency.dev/mcp"}

Tools

• get_ai_api_latency ~88 tokens
  Measured latency (TTFB p50/p95) and uptime rankings of AI inference API providers by region, from llmlatency.dev.
• get_model_deprecations ~128 tokens
  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.

Browse

• Website monitoring
• Calendars
• Calling other AI models

Related MCP servers

• Ai-rook Trading
  72 x402 endpoints: trading, AI inference, blockchain, escrow. USDC on Base+Solana.
• Interzoid
  58 AI data quality, data matching, and data enrichment APIs for better data ROI
• Apizone
  Real-time status & uptime monitoring for 294 popular APIs — is it down, and how reliable?
• Kawal
  Evidence about ERC-8004 agents on BNB Smart Chain, gathered by calling them. No key.
• Parallax Protocol
  Read-only Parallax PoW chain data: blocks, transactions, mining, supply, explorer and network health
• PeppolStatus
  Peppol market intelligence and network monitoring: migrations, provider churn, leads, and uptime.
• Tensorust
  Receipts-first data: real crates.io downloads, dated LLM API prices, sourced answers, free dev tools
• Insight Oracle
  Decision-input integrity for onchain AI agents: verify oracle prices before signing a trade.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/dev.llmlatency/llm-latency-tracker.svg)](https://aptlynx.net/servers/dev.llmlatency/llm-latency-tracker)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents