Outage in DigitalOcean
Gradient AI model availability
Resolved MinorIncident Report
Summary AI Generated
DigitalOcean's Gradient AI service experienced availability issues affecting multiple AI models including Llama3.1-8b, Qwen3-32b, several embedding models, and Guardrails functionality, while the Llama3.3-70b model suffered degraded performance. The incident lasted 4.8 hours and impacted users' ability to access models and run inference operations. Engineering teams implemented a fix that fully restored service and returned all affected models to healthy status.
Our Engineering team is investigating reports of Gradient AI model availability issues impacting multiple models. Users may experience issues with models availability, including Llama3.1-8b and Qwen3-32b, as well as embedding models such as GTE Large (v1.5), All-MiniLM-L6-v2, Multi-QA-mpnet-base-dot-v1, and Qwen3 Embedding 0.6B.
Additionally, Guardrails are not available, affecting associated agents, and users attempting to run inference on the Llama3.3-70b model will see degraded performance.
We apologize for the inconvenience and will share an update once we have more information.
Need to monitor DigitalOcean outages?
- Monitor all your external dependencies in one place
- Get instant alerts when outages are detected
- Be the first to know if service is down
- Show real-time status on private or public status page
- Keep your team informed
Latest Updates ( sorted recent to last )
RESOLVED
20 days ago - at 03/17/2026 07:49PM
Our Engineering team has implemented a fix, the issues impacting model availability and performance have been resolved. All models, including those previously degraded, are back up and healthy. Service has been fully restored.
INVESTIGATING
21 days ago - at 03/17/2026 03:00PM
Our Engineering team is investigating reports of Gradient AI model availability issues impacting multiple models. Users may experience issues with models availability, including Llama3.1-8b and Qwen3-32b, as well as embedding models such as GTE Large (v1.5), All-MiniLM-L6-v2, Multi-QA-mpnet-base-dot-v1, and Qwen3 Embedding 0.6B.
Additionally, Guardrails are not available, affecting associated agents, and users attempting to run inference on the Llama3.3-70b model will see degraded performance.
We apologize for the inconvenience and will share an update once we have more information.
Latest DigitalOcean outages
Serverless Inference Issue - about 15 hours ago
Gradient AI Platform agents and services Accessibility - 18 days ago
Degraded performance with BYOK Anthropic models - 23 days ago
Delay in App Platform Deployments - 24 days ago
Never miss outages in third-party dependencies
With IsDown, you can monitor all your critical services' official status pages from one centralized dashboard and receive instant alerts the moment an outage is detected. Say goodbye to constantly checking multiple sites for updates and stay ahead of outages with IsDown.
Start free trialNo credit card required · Cancel anytime · 6020 services available
Integrations with
