Launching today
AI Latency Tracker
Live latency and uptime of 44 AI APIs from 4 regions
2 followers
Live latency and uptime of 44 AI APIs from 4 regions
2 followers
Probes in Germany, US Central, Tokyo and São Paulo hit the official API host of 44 AI inference providers every 5 minutes. See which API is fastest from your region, real uptime, outages and model retirement dates. Free JSON API and MCP, CC BY 4.0.
Free
Launch Team
Render Sandboxes: a computer for every agentGive every agent its own machine. Starts in under a second
Promoted
I built this because every latency number I found was either the provider's own or a one-off benchmark. Probes in four regions hit each provider's official API host every five minutes, never through a gateway, and every number on the site traces back to raw probes. Fireworks is 16 ms from Germany and 254 ms from São Paulo, so "the fastest API" depends on where you are. Tell me which providers or regions to add, and where the method is wrong.