Failed to create Azure OpenAI deployment InternalServerError: Service temporarily unavailable. Please try again later
Hi, I am trying to deploy a fine-tuned model (gpt-4.1) and I am getting this error since yesterday: Failed to create Azure OpenAI deployment InternalServerError: Service temporarily unavailable. Please try again later This happened when I tried to…
Azure AI services
Address issue on Azure sign up
I am trying to sign up for Azure but it says my address has an issue when it is the correct address.
Azure AI services
Request example for multigrader with custom grader in Reinforcement fine tuning in AI foundry
Hi there, my custom grader is working fine when using it separately but when i combine with it with other in-built grader, it always failed. In the website tutorial, there is no template for multiple grader which includes custom grader, could u give an…
Azure AI services
The OpenAI Endpoints I create in Azure AI Foundry don't even DNS resolve
Azure AI constantly tries to get me to move my Azure OpenAI resources to AI Foundry. I did this today for one resource and then created new OpenAI 4o-mini and 4o end-points in the newly created Foundry Project. Neither of the end-points work as they…
Azure AI services
Why can't I create and Azure AI Foundry project with my trial subscription?
I followed all the training instructions but the "Create" button is greyed out and cannot be selected.
Azure AI services
We cannot deploy the embed-v-4-0 LLM model from Azure AI Foundry.
Why we cannot deploy the embed-v-4-0 LLM model from Azure AI Foundry? Could you help as to solve the issue? Thanks.
Azure AI services
grok 4 fast reasoning is down half of the time
I have deployed grok 4 fast reasoning in france central. The model seems great but it's down half of the time. When my app fails I go to the playground and it's the same behaviour. Either "model temporary unavailable" or it just keeps thinking…
Azure AI services
Server error occurs in Azure AI Foundry when generating graphs using code_interpreter
We are encountering an issue when executing Python code with code_interpreter in Azure AI Foundry. When running a graph generation task (e.g., using matplotlib), one of the following occurs: A server error is returned: Run failed: {'code':…
Azure AI services
How to fix Azure AI Foundry portal issue?
I just tried to log into the Azure AI Foundry portal, but found out that all the projects on my tenant have disappeared. Additionally, the section which lets me access the agents, and everything related to content understanding disappeared. Instead, in…
Azure AI services
Sometimes we receive the error "Multiple languages were identified. A single dominant language could not be determined" when using the Fast Transcription API with language identification enabled. How can we avoid receiving such responses?
Sometimes we receive the error "Multiple languages were identified. A single dominant language could not be determined" and "``No language was identified``"when using the Fast Transcription API with language identification enabled.…
Azure AI services
Azure AI Foundry support for locally hosted MCP servers?
Does AI Foundry have any plans for agent support for locally hosted MCP servers? I understand that there is currently a private preview for MCP servers for AI foundry agents, however this is only for remotely hosted servers. However, if I want to use the…
Azure AI services
OpenAI Response API and code interpreter tool
Hello, I recently switched to the OpenAI Response API in Aure ( instead of the Assistants API, which is set to be deprecated soon ) I am running into issues with the code interpreter tool, where it works for a bit then stops working saying that it…
Azure AI services
How can I deploy an AI Agent created in Microsoft AI Foundry to a website for public access?
Hi, I created an AI agent using Microsoft AI Foundry, and it works perfectly using the thread and agent ID when tested within the Azure portal. Now I want to deploy this agent on a website so that anyone (public users) can access it via a frontend .…
Azure AI services
How to fix incorrect coordinates from Azure AI vision Read API
We are using Azure AI Vision API (Read OCR) as part of our production OCR pipeline for text extraction and bounding box generation in Monotype’s AI-based font recognition services (e.g., WhatTheFont / Font-Lens). After successful PoC completion, we have…
Azure AI services
Calculate the savings $ and % against PTU vs Standard pricing for OpenAI service
I am trying to find the right calculation that will help us know what is the % and savings when used OpenAI in PayGo/OnDemand vs going into PTU for US East - Gpt-4o - global deployment type.
Azure AI services
why is not trigger URL available for Sora-2?
We've recently received access to the Sora 2 model and have successfully deployed it in both USA and Sweden Central regions. However, we're unable to retrieve the trigger URL needed to use the model through the API. Is there a configuration step we may…
Azure AI services
GPT 5 API requests - We are getting 429 responses but not even appearing to touch our quota this morning.
We are getting 429 responses but not even appearing to touch our quota this morning. GPT 5 API requests: It should be able to handle 100 API requests per min, analytics shows no more than 10. Locally our Developer made the same request and he's…
Azure AI services
401 Authentication Error When Deploying Managed Compute Endpoint
I’m deploying an endpoint using Managed Compute mode for the gpt-5-mini model, and the deployment fails with a 401 “Server failed to authenticate the request” error. From the logs, it appears that the container is attempting to download the model from an…
Azure AI services
Trying to upgrade gpt-4o model in azure maximum quota is assigned and I cannot update it
Hello, I am trying to edit my gpt-4o deployment in azure.. was previously on version 2024-08-26 now I am editing and i am selecting version 2024-11-20 and it is moving the quota selection to the max 29M tokens and i cannot move that arrow. I certainly…
Azure AI services
Azure AI Foundry – Research Models Auto-Deploying to Sweden Central and Hanging on Quota Load After Hub Deletion
I was previously approved to use models like gpt-5-codex and sora-2, and everything worked fine through the Responses API. After reading that OpenAI’s Codex could be accessed through Azure as a provider, I attempted to configure that setup but couldn’t…