Modal
Infrastructure. Source: Modal status page.
This status page publishes only incidents that are still open, so this page shows only incidents that were open when the collector checked, every three hours.
History starts 2026-08-19 23:45 UTC, the oldest incident this status page still shows. Figures for the last 90 days cover only the part since then.
- Incidents, last 90 days
- 9+
- Median to mitigation
- not reported
- Median to resolution
- 14m
- p95 to resolution
- 2h 8m
- Naming an upstream provider
- 0%
- With a postmortem on the status page
- 0%
What failed, last 90 days
| The text does not say enough to tell | 5 |
| Orchestration, control plane, service discovery or load balancing failed | 1 |
| AI model returned degraded, wrong or empty output (not errors or timeouts) | 1 |
| Network, DNS, routing or connectivity failure | 1 |
| Exhausted memory, disk, CPU, queues, connection pools or quotas | 1 |
Tagged by deepseek/deepseek-v4.1-flash from each incident's updates. See the methodology.
Incidents per month
Hatched months are before the recorded history starts.
All recorded incidents
Web functions degraded
Affected: Web Functions
Failure mode: Orchestration, control plane, service discovery or load balancing failed. Root cause: A configuration change. Tagged by deepseek/deepseek-v4.1-flash with high confidence (taxonomy v0.3).
-
degraded
We observed a 2 minute period where 30-40% of web function requests failed. This was due to an infrastructure change that left our proxies unable to handle new requests.
-
resolved
The degradation is resolved and web functions are operating normally. We will be implementing mechanisms to protect against a recurrence of this issue in future.
Excerpts are shortened. Read the full incident on Modal's status page.
Kimi K3 shared endpoint downtime
Affected: Kimi K3 Shared Endpoint
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by deepseek/deepseek-v4.1-flash with low confidence (taxonomy v0.3).
-
downtime
We are actively investigating an issue with the Kimi K3 shared endpoint which is returning an elevated level of 5xx errors.
-
resolved
We identified the issue affecting the Kimi K3 shared endpoint and applied a mitigation. The endpoint is now fully operational.
Excerpts are shortened. Read the full incident on Modal's status page.
Kimi K3 shared endpoint is degraded
Affected: Kimi K3 Shared Endpoint
Failure mode: AI model returned degraded, wrong or empty output (not errors or timeouts). Root cause: The vendor does not say why it happened. Tagged by deepseek/deepseek-v4.1-flash with low confidence (taxonomy v0.3).
-
degraded
We are actively investigating an issue with the Kimi K3 shared endpoint which is returning an elevated level of 5xx errors.
-
resolved
We identified the issue affecting the Kimi K3 shared endpoint and applied a mitigation. The endpoint is now fully operational.
Excerpts are shortened. Read the full incident on Modal's status page.
Function and Sandbox execution degraded
Affected: Functions, Sandboxes
Failure mode: Network, DNS, routing or connectivity failure. Root cause: Network or DNS. Tagged by deepseek/deepseek-v4.1-flash with high confidence (taxonomy v0.3).
-
degraded
Workers responsible for function and sandbox execution have degraded networking.
-
resolved
We're seeing recovery for function and sandbox execution, worker networking has been restored
Excerpts are shortened. Read the full incident on Modal's status page.
Dashboard and sandbox outage
Affected: Dashboard, Deployment, Sandboxes
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by deepseek/deepseek-v4.1-flash with low confidence (taxonomy v0.3).
-
downtime
We're currently tracking an outage for our customer dashboard and sandboxes. We will update as we have more information.
-
downtime
We've identified the source of the issue and remediated.
-
resolved
We're observing recovery of impacted services and will continue to monitor.
Excerpts are shortened. Read the full incident on Modal's status page.
Storage is degraded
Affected: Volumes
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by deepseek/deepseek-v4.1-flash with low confidence (taxonomy v0.3).
-
degraded
We are observing an elevated error rate on an endpoint used to read application and volume contents. Many requests are retried by clients, but this may result in task failures or failures in direct reads.
-
resolved
Error rates on the impacted volume endpoint have subsided. We will continue to monitor.
Excerpts are shortened. Read the full incident on Modal's status page.
Snapshot restores are degraded
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by deepseek/deepseek-v4.1-flash with low confidence (taxonomy v0.3).
-
degraded
Some snapshot restores are failing to complete.
-
resolved
We have shipped a change to resolve this and are seeing remediation.
Excerpts are shortened. Read the full incident on Modal's status page.
Increased function latency
Affected: Functions, Web Functions
Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: Not enough capacity for the load. Tagged by deepseek/deepseek-v4.1-flash with high confidence (taxonomy v0.3).
-
degraded
We are experiencing increased load that caused latencies to rise.
-
resolved
Functions are seeing recovery
-
resolved
We are seeing full recovery
Excerpts are shortened. Read the full incident on Modal's status page.
Degraded latency on .spawn() calls
Affected: Functions
Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by deepseek/deepseek-v4.1-flash with high confidence (taxonomy v0.3).
-
degraded
Some percentage of .spawn() calls experienced elevated latency.
-
resolved
We have recovered.
Excerpts are shortened. Read the full incident on Modal's status page.