Official MCP RegistryListed
LLM Latency Tracker
Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.
First seen 2 Oct 2026. Evidence as of 10 Oct 2026.
2
Tools
From an anonymous probe
1
Source listings
Each with its own history
0
Recorded changes
Since first seen
Tools
| Tool | Description | Behaviour |
|---|---|---|
| get_ai_api_latency | Measured latency (TTFB p50/p95) and uptime rankings of AI inference API providers by region, from llmlatency.dev. | Not declared |
| 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). Every entry is verified against the provider own deprecation page. | Not declared |
Change history
No changes since the first observation. The first snapshot is the baseline.
| Source | Listing | First seen | Last seen | Versions |
|---|---|---|---|---|
| Official MCP Registry | dev.llmlatency/llm-latency-tracker | 2 Oct 2026 | 10 Oct 2026 | 1 |