error 715-123420 when creating an available LLM model

Error 715-123420 during deployment is a generic platform-side failure that the portal surfaces when the deployment request cannot be completed, even though the model and region appear valid. The provided context does not include a product-side workaround or specific remediation steps for this exact error code.

Given that:

• The models being deployed (for example, gpt‑4.1, gpt‑4o, text-embeddings-3-small) are listed as available for the chosen region, and
• The error message explicitly instructs to contact support and provides Trace ID, Client Request ID, and Service Request ID,

the required next step is to open an Azure support request so the service team can investigate the backend failure using those IDs. Include:

• The exact error code 715-123420 and message.
• The region and model name/version selected.
• The Client Request ID, Trace ID, and Service Request ID from the portal screenshot.
• The approximate time (with timezone) when the failure occurred.

If the deployment is business‑critical, create the ticket under a technical support plan with appropriate severity so the engineering team can check for region‑specific capacity, subscription restrictions, or transient platform incidents that are not visible in the public documentation.

References:

• Azure OpenAI frequently asked questions
• Troubleshoot online endpoint deployment and scoring
• Foundry Models from partners and community