outages.live
Live
DeepSeekIncident ·

DeepSeek Web/API Partially Unavailable

ResolvedOfficial update
0

DeepSeek reported a partial outage on the DeepSeek V4.1 Flash API Service, the Chatservice, and the DeepSeek V4 Pro API Service. DeepSeek reported that the incident is resolved. The outage lasted 110 minutes.

State

Resolved

Started

Lasted

1 h 50 min

Worst impact

Partial outage

Timeline

5 updates
08:5809:2509:5310:2010:48
Partial outageDegradedUpdate postedTimes in UTC

Investigating

11 min 10%

Monitoring

1 h 39 min 90%

Updates

Times in UTC

As posted by DeepSeek

Resolved

The incident has been resolved and service has been restored.

Monitoring

A fix has been implemented and the results are being monitored.

Monitoring

A fix has been implemented and the results are being monitored.

Monitoring

A fix has been implemented and the results are being monitored.

Investigating

The issue is being investigated to identify the cause.

Affected components

3
DeepSeek V4.1 Flash API ServiceChatserviceDeepSeek V4 Pro API Service

DeepSeek in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

8

Days with an incident

7

Median duration

15 min

This incident

7.4× the median

How long each incident lasted, on the day it started. The outlined bar is this incident.

4 h 52 min
median 15 min
90 days agoToday

Other DeepSeek incidents

All incidents

DeepSeek·DeepSeek API Degraded Performance

The incident has been resolved and service has been restored.

Resolved

DeepSeek·Search service error

The incident has been resolved and service has been restored.

Resolved

DeepSeek·DeepSeek Web/API Partially Unavailable

The incident has been resolved and service has been restored.

Resolved

DeepSeek·DeepSeek Web/API Degraded Performance

The incident has been resolved and service has been restored.

Resolved

DeepSeek·- DeepSeek Web Partially Unavailable

The incident has been resolved and service has been restored.

Resolved

Follow DeepSeek

Your coding agent knows when DeepSeek is down, and tells you when a failure is theirs, not yours. You can also get DeepSeek incidents in a feed reader or in Slack.

Prompt
Install the outages.live MCP server, so that when something breaks you can tell if the cause is a provider we depend on and not my code. It reads the official status pages of cloud, AI, payment and developer providers and gives you their incidents as MCP tools.

Add it as a remote MCP server named "outages" at https://outages.live/mcp (Streamable HTTP, no authentication), with your CLI command or your MCP config file.

Then:
1. Make sure it connects and shows the tools get_provider, list_feed and send_feedback.
2. Call get_provider with "deepseek" and tell me if DeepSeek has a problem right now.
3. From now on, when a call to a third-party service fails or becomes slow, call get_provider for that service before you change my code.

Paste this into any coding agent. It adds the server with its own MCP setup.

RSS
https://outages.live/feed.xml?providers=deepseek
Slack
/feed subscribe https://outages.live/feed.xml?providers=deepseek

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane