AI & Machine Learning

llmlatency.dev

Provides latency and uptime metrics for AI inference APIs across regions.

1 endpoint2 known toolsFirst detected July 25, 2026Last detected August 29, 2026

ENDPOINT 1

https://llmlatency.dev/mcp

No auth detected

MCP server metadata

Name: llmlatency-mcp
Version: 1.0.0

Capabilities

tools

Known tools 2

get_ai_api_latency

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

Inferred read-only

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).

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.llmlatency-mcp]
url = "https://llmlatency.dev/mcp"
enabled = true

Claude Code

.mcp.json

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

Claude Desktop

Settings → Connectors → Add custom connector

Name: llmlatency-mcp
Remote MCP URL: https://llmlatency.dev/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

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

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

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

Generic MCP

Client-specific MCP configuration

{
  "name": "llmlatency-mcp",
  "transport": "streamable-http",
  "url": "https://llmlatency.dev/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for llmlatency.dev was fetched 2026-08-04T02:55:05.943Z and is being refreshed.

Trust status Neutral

llmlatency.dev is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.