ALL SYSTEMS LIVE·91 INSTRUMENTS · 19 VERTICALS
ED25519 · RFC 3161 TIMESTAMPED·--:--:-- UTC
RELIABILITY · MEASURED, NOT CLAIMED

Reliability, measured.

The AI-provider API latency and per-feed uptime we measure ourselves on a fixed schedule — vendor-neutral, time-stamped, and kept. A backfill-proof archive that can't be reconstructed after the fact.

AI PROVIDER LATENCY · ROLLING 24H

The latency we measure ourselves.

ProviderAvg latencyUptimeSamples
xAI52 ms100.0%163
Groq63 ms100.0%163
OpenAI65 ms100.0%163
Google78 ms99.4%163
Anthropic94 ms100.0%163
Mistral191 ms100.0%163
DeepSeek291 ms100.0%163

Live JSON: /benchmarks · embeddable widget: /widget/latency

PLATFORM UPTIME · MEASURED PROBES

Every feed, on the clock.

overall measured uptime across all live tools, over the selected window.

measuring…

Live status board: /uptime · status JSON: /status.json