530 questions
0
votes
1
answer
22
views
Azure OpenAI Realtime API: Token usage from `response.done` event does not match Azure Cost Management meter data
Problem
I'm using the Azure OpenAI Realtime API (gpt-realtime-mini-2025-12-15) via the .NET OpenAI.Realtime SDK to measure token consumption. The response.done server event includes a usage object ...
- 1,064
0
votes
0
answers
53
views
Does reaching one's monthly usage limit prevent from using an Azure OpenAI key with Cursor IDE? [closed]
I use Cursor IDE. I have reached my monthly usage limit. Therefore, I have added my Azure OpenAI key:
However, I'm still getting the error message when trying to use the model that is accessed via my ...
- 85.2k
3
votes
0
answers
89
views
Why does the first response in my OpenAI Realtime C# session show cached token usage (cached_input_tokens) even though no prior context exists?
I'm working with the OpenAI.Realtime C# SDK and logging detailed token‑usage metrics for a multi‑turn audio conversation. My setup is based on a custom RealtimeScenarioBase class and a derived ...
- 1,064
0
votes
0
answers
58
views
Azure OpenAI Realtime API returning server_error during response processing
I encountered a server error while using the Azure OpenAI Realtime API. The request fails with a server_error even though the request format and connection appear correct.
The error occurred during a ...
- 697
0
votes
1
answer
60
views
Not receiving webhook call from Azure Open AI realtime model
I've been following this documentation here: https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-sip#connect-to-sip
In Twilio, I created an elastic sip trunk for my phone ...
- 2,180
1
vote
0
answers
80
views
AzureOpenAI deployment Issue
I am creating a small POC where i am trying to get the response from LLM using gpt-4.1 model
Please Note i am using SDK here, i am able to get the response if i create plain REST API.
Below is my ...
0
votes
1
answer
80
views
Azure Agent Retrieval (Azure AI Search) returns JSON references instead of LLM-generated answer
I’m testing Azure Agent Retrieval with Azure AI Search and Azure OpenAI integration.
However, instead of getting a natural language LLM-generated answer, the response only returns raw JSON with ...
- 73
0
votes
0
answers
60
views
Is there a way to diagnose connection issues between the Azure OpenAI platform and other services?
We're setting up an Azure OpenAI instance that needs to connect to an Azure AI Search instance (i.e. "Bring Your Own Data"), we're currently using an API key to connect to the Search ...
- 27.1k
0
votes
1
answer
80
views
'metadata_storage_name' always null: Missing or empty value '/document/blob_name'
Using Azure's AI Search Service to chunk and read textfiles, the target field values are always NULL.
I tried using a simplified example, just for the fields metadata_blob_name / title and ...
- 2,115
0
votes
1
answer
157
views
Structured output with full response content and additional metadata
I want to create a structured output from an agent call that contains the full response content, as well as additional metadata.
For example, I am making a call to find the differences between two ...
- 1,248
0
votes
1
answer
84
views
How can I update the capacity of a finetuned GPT model on Azure using Python?
I want to update the capacity of a finetuned GPT model on Azure. How can I do so in Python?
The following code used to work a few months ago (it used to take a few seconds to update the capacity) but ...
- 85.2k
2
votes
1
answer
735
views
Implementing a custom LiteLlm for Google agent development kit that supports tool calls
I'm trying to implement a custom LiteLlm wrapper to access an LLM endpoint. This is the code I have:
import os
import litellm
import requests
from dotenv import load_dotenv
from litellm import ...
- 3
0
votes
0
answers
247
views
Configuring MCP with Microsoft.Extensions.AI
Using the following Microsoft template as my base:
https://devblogs.microsoft.com/dotnet/announcing-dotnet-ai-template-preview1/
I want to be able to add my local stdio MCP server as a tool but can't ...
- 756
1
vote
1
answer
381
views
how to download the files generated by Azure OpenAi Assistant Code Interpreter in streaming mode
In streaming mode, there is an event "response.output_text.annotation.added",
the data looks like
{
"type": "response.output_text.annotation.added",
"...
- 1,497
0
votes
0
answers
66
views
Correct input for OpenAI embeddings API?
I'm using the OpenAi text-embedding-3-small model to create embeddings for each product category in a file. In total it's about 6000 product categories and they look like this:
Vehicles & Parts &...
- 3,885