Models Tracked
12
across 6 providers
Avg Latency (now)
387 ms
↓ 42 ms vs. 1 h ago
30-day Uptime
99.4%
across all providers
Open Incidents
0
last 7 days: 2 resolved
Regions Monitored
5
US-E · US-W · EU · APAC · SA
Model Status
Model Status Latency 1h Avg Uptime 30d Checked
Loading…
Latency Trends — Last 24 Hours
OpenAI vs Anthropic vs Google
Regional Latency Discrepancies
Model US-East US-West EU-West APAC SA
Loading…

Color scale: <400 ms 400–699 ms 700–999 ms ≥1,000 ms

Recent Incidents
Claude Opus 4 — Elevated latency (US-East, US-West)
Median response time elevated 3–4× baseline. Anthropic has acknowledged and is investigating. No full outage. Other Claude models unaffected.
May 9 · 08:14 UTC
Monitoring
OpenAI API — Partial outage (EU-West)
GPT-4o and GPT-4.1 returned 503 errors for ~18 min affecting EU-West region. OpenAI resolved at 14:32 UTC. All other regions unaffected throughout.
May 3 · 14:14–14:32 UTC
Resolved
Mistral AI — Increased error rate (all regions)
Elevated 5xx error rate (~4%) across all regions for approximately 35 minutes. Impacted Mistral Large and Mistral Small. Fully resolved with no data loss.
Apr 28 · 09:50–10:25 UTC
Resolved
LLM Monitoring Premium

Go beyond the
public dashboard.

The free Status Hub gives you a real-time snapshot. Premium gives your team the infrastructure to act on it — before your users notice a thing.

Founding member pricing · 3 of 10 spots claimed
Founding Member
$49 $79 Save 38%
per month · your rate is locked in forever
🔥 Founding rate — 7 spots remaining 3 / 10 claimed
Price rises to $79/mo once all 10 founding spots are filled.
Claim founding rate — $49 / month →

🔒 Secured by Stripe · Pre-order, no charge until launch · Founding rate locked in forever · Cancel anytime

Everything you need is in the integration guide — clear, step-by-step, written so you can move at your own pace. Most teams are live in under 10 minutes.

Questions? hello@modelvantage.com