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
| Endpoint | https://llmlatency.dev/mcp |
|---|---|
| Source | https://github.com/mazamaka/llm-latency-tracker |
| Transport | http |
| Tools | 2 |
| Auth | none |
| First seen | 2026-08-18 23:44:48 |
| Last checked | 2026-11-17 21:45:51 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 311 / 568 ms |
| Last successful check | 2026-11-17 21:45:51 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (2)
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 actuall
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:45:51 | ✓ | ✓ | 652 ms | 91 | active |
| 2026-11-17 21:30:44 | ✓ | ✓ | 266 ms | 94 | active |
| 2026-11-17 21:15:34 | ✓ | ✓ | 244 ms | 94 | active |
| 2026-11-17 21:00:02 | ✓ | ✓ | 474 ms | 91 | active |
| 2026-11-17 20:45:01 | ✓ | ✓ | 402 ms | 91 | active |
| 2026-11-17 20:29:59 | ✓ | ✓ | 215 ms | 94 | active |
| 2026-11-17 20:14:56 | ✓ | ✓ | 374 ms | 91 | active |
| 2026-11-17 19:59:04 | ✓ | ✓ | 472 ms | 91 | active |
| 2026-11-17 19:43:56 | ✓ | ✓ | 356 ms | 91 | active |
| 2026-11-17 19:28:53 | ✓ | ✓ | 237 ms | 94 | active |
| 2026-11-17 19:13:50 | ✓ | ✓ | 568 ms | 91 | active |
| 2026-11-17 18:57:35 | ✓ | ✓ | 415 ms | 91 | active |
| 2026-11-17 18:42:34 | ✓ | ✓ | 237 ms | 94 | active |
| 2026-11-17 18:27:33 | ✓ | ✓ | 413 ms | 91 | active |
| 2026-11-17 18:12:32 | ✓ | ✓ | 359 ms | 91 | active |
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