Is Modal down right now?
HTTP endpoint monitoring - checked every 5 minutes · How we classify outages
Weekly AI pricing & uptime digest
Price drops, new model releases, and incident summaries - every Monday. Free.
Modal is currently down - official outage reported - 642ms HTTP response. Last checked . 90-day uptime: 99.9%.
Endpoints - Kimi K3 is down
Stay informed
Follow @tickerr_ai
We post when tier 1 LLM APIs go down - before the official status page updates.
Follow on X →Or get the weekly reliability digest:
Add a status badge
Show live Modal status on your site, README, or docs.
90-day uptime
99.9%
15 incidents (90d)
Response now
642ms
HTTP p50 (7d)
786ms
median ping response
HTTP p95 (7d)
2036ms
tail ping response
Response time (7 days)
p50 786ms·p95 2036msⓘ HTTP response times from Tickerr's monitoring server to Modal's status or homepage endpoint - not API inference latency or time-to-first-token (TTFT). For API benchmark data, see third-party sources like Artificial Analysis.
90-day uptime
Incident history
Some percentage of .spawn() calls experienced elevated latency.
Endpoints - Inkling NVFP4 went down
Endpoints - Kimi K3 went down
Endpoints - Kimi K3 went down.
We're seeing recovery
Flash Proxy (us-west) went down.
We are investigating elevated rates of 5xx errors on modal.com
Flash Proxy (us-west) went down.
We're tracking errors in our storage subsystem which is causing issues with volumes and app deploys.
Volume CLI operations are no longer degraded.
Web endpoints went down.
Web endpoints went down.
Web endpoints went down.
## Impact Our authorization system will be briefly unavailable during the restart. Any request that requires a permission check will fail with an error for approximately **30–60 seconds**. Between 15-…
Related pages
About Modal status
Modal is a cloud compute platform for running Python workloads including ML inference, data pipelines, and AI agents. Modal downtime affects function execution and deployment. Modal is commonly used for custom model hosting and batch AI workloads.