outages.live
Live
DeepInfraIncident ·

Degraded performance

DegradedOfficial update
0

DeepInfra reports degraded performance for MiniMax-M3. The provider is investigating the issue. No further updates are available.

State

Components degraded

Started

Ongoing for

32 min

Worst impact

Degraded

Timeline

1 update
12:1512:2312:3112:3912:47
DegradedUpdate postedTimes in UTC

Components degraded

32 min 100%

Updates

Times in UTC

As posted by DeepInfra

Components degraded

Affected components

1
MiniMax-M3

DeepInfra in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

48

Days with an incident

13

Median duration

57 min

This incident

43% shorter than the median

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

3 h 27 min
median 57 min
90 days agoToday

Other DeepInfra incidents

All incidents

DeepInfra·Degraded performance

DeepInfra reports degraded performance for Inkling-2-Small. DeepInfra resolved the incident. The outage lasted 63 minutes.

Resolved

DeepInfra·Partial outage

DeepInfra reports a partial outage of NVIDIA-Nemotron-3.5-Transcribe-30B-A4B. DeepInfra states that the incident is resolved. The outage lasted 60 minutes.

Resolved

DeepInfra·Partial outage

DeepInfra reported a major outage of Qwen3-Next-80B-A3B-Instruct. DeepInfra reports that the incident is resolved. The outage lasted 129 minutes.

Resolved

DeepInfra·Partial outage

DeepInfra reports a major outage on the Hy4-preview component. The outage is resolved. It lasted 90 minutes, from 03:24 to 04:54 UTC on 12 November 2026.

Resolved

DeepInfra·Partial outage

DeepInfra reports a partial outage on the Qwen3-Next-80B-A3B-Instruct component. DeepInfra resolved the outage. The outage lasted 66 minutes.

Resolved

Follow DeepInfra

Your coding agent knows when DeepInfra is down, and tells you when a failure is theirs, not yours. You can also get DeepInfra 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 "deepinfra" and tell me if DeepInfra 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=deepinfra
Slack
/feed subscribe https://outages.live/feed.xml?providers=deepinfra

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane