Arclan / Servers

Independent, measured latency & uptime for ~45 AI inference APIs, by region. JSO

Independent, measured latency & uptime for ~45 AI inference APIs, by region. JSON API + MCP server. Data CC-BY-4.0.

active Production-safe Score 95/100 http no auth

At a glance

Endpointhttps://llmlatency.dev/mcp
Sourcehttps://github.com/mazamaka/llm-latency-tracker
Transporthttp
Tools2
Authnone
First seen2026-08-18 23:44:48
Last checked2026-11-17 21:45:51

Observed reliability

7-day uptime100%
24-hour uptime100%
Handshake success100%
Latency p50 / p95311 / 568 ms
Last successful check2026-11-17 21:45:51

Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →

Tools (2)

Validation history

CheckedReachableHandshakeLatencyScoreState
2026-11-17 21:45:51✓✓652 ms91active
2026-11-17 21:30:44✓✓266 ms94active
2026-11-17 21:15:34✓✓244 ms94active
2026-11-17 21:00:02✓✓474 ms91active
2026-11-17 20:45:01✓✓402 ms91active
2026-11-17 20:29:59✓✓215 ms94active
2026-11-17 20:14:56✓✓374 ms91active
2026-11-17 19:59:04✓✓472 ms91active
2026-11-17 19:43:56✓✓356 ms91active
2026-11-17 19:28:53✓✓237 ms94active
2026-11-17 19:13:50✓✓568 ms91active
2026-11-17 18:57:35✓✓415 ms91active
2026-11-17 18:42:34✓✓237 ms94active
2026-11-17 18:27:33✓✓413 ms91active
2026-11-17 18:12:32✓✓359 ms91active

Query this programmatically

Agents can pull this record live over the MCP protocol or REST:

get_server("https://llmlatency.dev/mcp")   # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/llmlatency-dev-mcp   # JSON