Partial outage
DeepInfra reports a partial outage that affects only the Qwen3.5-35B-A3B component. The provider has not given the latest state. The outage started 18 minutes ago.
State
Components degraded
Started
Ongoing for
53 min
Worst impact
Partial outage
Timeline
2 updatesComponents degraded
53 min 100%
Updates
Times in UTCAs posted by DeepInfra
Affected components
1DeepInfra in the last 90 days
Full historyIncidents in 90 days
11
Days with an incident
3
Median duration
54 min
This incident
About the median
Other DeepInfra incidents
All incidentsDeepInfra·Degraded performance
DeepInfra reports degraded performance on the Qwen3.5-397B-A17B model. DeepInfra resolved this incident. The incident lasted 54 minutes.
DeepInfra·Partial outage
The model Qwen3.5-35B-A3B does not work. The problem affects only this component. DeepInfra reports that the incident is resolved. The outage lasted 33 minutes.
DeepInfra·Partial outage
DeepInfra reports a partial outage that affects Qwen3.5-35B-A3B. The incident is resolved. It lasted 69 minutes, from 3 November 2026 23:24 UTC to 4 November 2026 00:33 UTC.
DeepInfra·Degraded performance
DeepInfra reports degraded performance for the Ling-3.1-flash component. DeepInfra states that this incident is resolved. The incident lasted 54 minutes.
DeepInfra·Degraded performance
DeepInfra reports degraded performance on the Qwen3.5-35B-A3B model. DeepInfra resolved the incident. The incident lasted 27 minutes.
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.
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.
https://outages.live/feed.xml?providers=deepinfra/feed subscribe https://outages.live/feed.xml?providers=deepinfraFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane