A catalog of AI models in Microsoft Foundry that you can discover, compare, and deploy using Azure’s built‑in tools for evaluation, fine‑tuning, and inference
Hi Denniver,
Yes, we're seeing similar reports from other customers.
Since the issue is occurring across multiple Azure regions (Germany, France, and Sweden), affects the Azure AI Foundry playground, and GPT-5.4/GPT-5.5 deployments continue to work normally, this points more toward a service-side issue affecting GPT-5.6 Sol rather than a deployment or configuration problem. The symptoms you describe was intermittent disconnection followed by "There was an issue with your request" for even simple prompts are consistent with a backend service degradation.
In the meantime, I'd recommend:
Checking Azure Service Health for any advisories related to Azure OpenAI or Azure AI Foundry in your affected regions.
Capturing the x-ms-request-id and timestamp from failed API calls (or the browser's developer tools if reproducing the issue in the playground) to assist Microsoft Support.
Temporarily routing production traffic to GPT-5.5 or another unaffected deployment until the issue is resolved.
If the issue persists and no advisory is posted, opening a Microsoft Support request with the affected regions, deployment names, timestamps, and request IDs.
Since the problem reproduces in the Foundry playground, it provides a strong indication that the issue is not application-specific and should help Microsoft narrow down the investigation.
Please "Accept the Answer" if this information helped you. This will help us and others in the community as well.