Replicate incident: Replicate Pruna issue

Affected components

• Replicate

1. resolvedSep 17, 2026, 21:51 UTC

   This incident has been resolved.

2. identifiedSep 17, 2026, 01:09 UTC

   Some Pruna models may not be able to scale up and are therefore either experiencing long queue times or entirely unavailable. We are working with Pruna to resolve the issue.

What APIStatus.watch saw

Our 5-minute checks didn't record a change in Replicate's overall status around this incident. Smaller or regional incidents often leave a provider's overall status green.

Other services with incidents at the same time

Overlapping incidents aren't necessarily related.

• MongoDB Atlas: Impaired Cluster operations in AWS me-central-1 and AWS me-south-1Major · Sep 3, 2026, 16:44 UTC
• Elasticsearch: Elastic Agent enrollment/check-in failures on 9.5.3 (and 9.4.6) with Fleet remote Elasticsearch outputMajor · Sep 9, 2026, 20:44 UTC
• Pinecone: [Serverless][AWS][us-west-2] 5xx errors on the readpathMajor · Sep 17, 2026, 05:37 UTC
• Cursor: Investigating service degradation — Grok BotMajor · Sep 17, 2026, 12:30 UTC
• Elasticsearch: AutoOps node metrics temporarily unavailable in some regionsMajor · Sep 17, 2026, 15:50 UTC
• Discord: Issue / Delay in establishing call connectionMajor · Sep 17, 2026, 18:18 UTC
• OpenAI: Elevated errors affecting ChatGPT Work modeMajor · Sep 17, 2026, 19:03 UTC
• Twilio: Voice Call Failures from a Subset of Twilio Phone Numbers to Hong KongMinor · Sep 12, 2026, 00:16 UTC
• Telnyx: SMS Delivery — Encoding Issues on Outbound Messages to T-MobileMinor · Sep 15, 2026, 21:57 UTC
• Notion: Duplicate characters when editing with a Korean keyboard on iOSMinor · Sep 16, 2026, 23:58 UTC

How often does Replicate have incidents?

Replicate reported 3 incidents in the last 90 days. A typical incident lasted 1h 54m. See Replicate's uptime and incident history