update model name from gpt-4.1-mini to gpt4.1-mini

Author: Priyanka-Microsoft

docs/CustomizingAzdParameters.md

@@ -12,7 +12,7 @@ By default this template will use the environment name as the prefix to prevent
 | `AZURE_ENV_NAME`            | string  | `azdtemp`           | Used as a prefix for all resource names to ensure uniqueness across environments.                    |
 | `AZURE_LOCATION`            | string  | `<User selects during deployment>`         | Sets the Azure region for resource deployment.  |
 | `AZURE_OPENAI_MODEL_DEPLOYMENT_TYPE`             | string  | `GlobalStandard`    | Change the Model Deployment Type (allowed values: Standard, GlobalStandard).                         |
-| `AZURE_OPENAI_DEPLOYMENT_MODEL`               | string  | `gpt-4.1-mini`            | Set the GPT model name (allowed values: `gpt-4.1-mini`, `gpt-4`, `gpt-4o`).                                                      |
+| `AZURE_OPENAI_DEPLOYMENT_MODEL`               | string  | `gpt4.1-mini`            | Set the GPT model name (allowed values: `gpt4.1-mini`, `gpt-4`, `gpt-4o`).                                                      |
 | `AZURE_OPENAI_API_VERSION`     | string  | `2025-04-14`        | Set the Azure OpenAI model version.                                       |
 | `AZURE_OPENAI_DEPLOYMENT_MODEL_CAPACITY`     | integer | `30`               | Set the model capacity for GPT deployment. Choose based on your Azure quota and usage needs.         |
 | `AZURE_OPENAI_EMBEDDING_MODEL`            | string  | `text-embedding-ada-002`  | Set the model name used for embeddings.                                                              |

docs/QuotaCheck.md

@@ -1,7 +1,7 @@
 ## Check Quota Availability Before Deployment
 
 Before deploying the accelerator, **ensure sufficient quota availability** for the required model.
-> **For Global Standard | gpt-4.1-mini - increase the capacity to at least 50K tokens for optimal performance.**
+> **For Global Standard | gpt4.1-mini - increase the capacity to at least 50K tokens for optimal performance.**
 
 ### Login if you have not done so already
 ```
@@ -11,7 +11,7 @@ azd auth login
 
 ### 📌 Default Models & Capacities:
 ```
-gpt-4.1-mini:30, text-embedding-ada-002:45
+gpt4.1-mini:30, text-embedding-ada-002:45
 ```
 ### 📌 Default Regions:
 ```
@@ -37,19 +37,19 @@ australiaeast, francecentral, japaneast, northcentralus, southcentralus, westus,
    ```
 ✔️ Check specific model(s) in default regions:
   ```
-  ./quota_check_params.sh --models gpt-4.1-mini:30,text-embedding-ada-002:45
+  ./quota_check_params.sh --models gpt4.1-mini:30,text-embedding-ada-002:45
   ```
 ✔️ Check default models in specific region(s):
   ```
 ./quota_check_params.sh --regions eastus,westus
   ```
 ✔️ Passing Both models and regions:  
   ```
-  ./quota_check_params.sh --models gpt-4.1-mini:30 --regions eastus,westus
+  ./quota_check_params.sh --models gpt4.1-mini:30 --regions eastus,westus
   ```
 ✔️ All parameters combined:
   ```
- ./quota_check_params.sh --models gpt-4.1-mini:30,text-embedding-ada-002:45 --regions eastus,westus --verbose
+ ./quota_check_params.sh --models gpt4.1-mini:30,text-embedding-ada-002:45 --regions eastus,westus --verbose
   ```
 
 ### **Sample Output**

infra/main.bicep

@@ -19,7 +19,7 @@ param location string = resourceGroup().location
 param gptModelDeploymentType string = 'GlobalStandard'
 
 @description('Optional. Name of the GPT model to deploy:')
-param gptModelName string = 'gpt-4.1-mini'
+param gptModelName string = 'gpt4.1-mini'
 
 @description('Optional. Version of the GPT model to deploy:')
 param gptModelVersion string = '2025-04-14'

infra/main.json

@@ -6,7 +6,7 @@
     "_generator": {
       "name": "bicep",
       "version": "0.37.4.10188",
-      "templateHash": "3418531138421621433"
+      "templateHash": "7824757243182327261"
     }
   },
   "parameters": {
@@ -43,7 +43,7 @@
     },
     "gptModelName": {
       "type": "string",
-      "defaultValue": "gpt-4.1-mini",
+      "defaultValue": "gpt4.1-mini",
       "metadata": {
         "description": "Optional. Name of the GPT model to deploy:"
       }

infra/scripts/checkquota.sh

@@ -32,7 +32,7 @@ echo "✅ Azure subscription set successfully."
 
 # Define models and their minimum required capacities
 declare -A MIN_CAPACITY=(
-    ["OpenAI.Standard.gpt-4.1-mini"]=$GPT_MIN_CAPACITY
+    ["OpenAI.GlobalStandard.gpt4.1-mini"]=$GPT_MIN_CAPACITY
     ["OpenAI.GlobalStandard.text-embedding-ada-002"]=$TEXT_EMBEDDING_MIN_CAPACITY
 )
 

infra/scripts/quota_check_params.sh

@@ -47,7 +47,7 @@ log_verbose() {
 }
 
 # Default Models and Capacities (Comma-separated in "model:capacity" format)
-DEFAULT_MODEL_CAPACITY="gpt-4.1-mini:30,text-embedding-ada-002:45"
+DEFAULT_MODEL_CAPACITY="gpt4.1-mini:30,text-embedding-ada-002:45"
 
 # Convert the comma-separated string into an array
 IFS=',' read -r -a MODEL_CAPACITY_PAIRS <<< "$DEFAULT_MODEL_CAPACITY"

src/.env.sample

@@ -17,7 +17,7 @@ AZURE_SEARCH_STRICTNESS=3
 AZURE_OPENAI_RESOURCE=
 AZURE_OPENAI_MODEL=
 AZURE_OPENAI_KEY=
-AZURE_OPENAI_MODEL_NAME=gpt-4.1-mini
+AZURE_OPENAI_MODEL_NAME=gpt4.1-mini
 AZURE_OPENAI_TEMPERATURE=0
 AZURE_OPENAI_TOP_P=1.0
 AZURE_OPENAI_MAX_TOKENS=1000

src/app.py

@@ -86,7 +86,7 @@ def assets(path):
 )
 AZURE_OPENAI_STREAM = os.environ.get("AZURE_OPENAI_STREAM", "true")
 AZURE_OPENAI_MODEL_NAME = os.environ.get(
-    "AZURE_OPENAI_MODEL_NAME", "gpt-4.1-mini"
+    "AZURE_OPENAI_MODEL_NAME", "gpt4.1-mini"
 )
 AZURE_OPENAI_EMBEDDING_ENDPOINT = os.environ.get("AZURE_OPENAI_EMBEDDING_ENDPOINT")
 AZURE_OPENAI_EMBEDDING_KEY = os.environ.get("AZURE_OPENAI_EMBEDDING_KEY")
@@ -108,7 +108,7 @@ def assets(path):
 def is_chat_model():
     if (
         "gpt-4" in AZURE_OPENAI_MODEL_NAME.lower()
-        or AZURE_OPENAI_MODEL_NAME.lower() in ["gpt-35-turbo-4k", "gpt-4.1-mini"]
+        or AZURE_OPENAI_MODEL_NAME.lower() in ["gpt-35-turbo-4k", "gpt4.1-mini"]
     ):
         return True
     return False

src/test_app.py

@@ -48,7 +48,7 @@ def test_is_chat_model_with_gpt35_turbo_4k():
 
 
 def test_is_chat_model_with_gpt35_turbo_16k():
-    with patch("app.AZURE_OPENAI_MODEL_NAME", "gpt-4.1-mini"):
+    with patch("app.AZURE_OPENAI_MODEL_NAME", "gpt4.1-mini"):
         assert is_chat_model() is True
 
 
@@ -291,7 +291,7 @@ def test_stream_with_data_azure_success():
     with patch("requests.Session.post") as mock_post:
         mock_response = MagicMock()
         mock_response.iter_lines.return_value = [
-            b'data: {"id":"1","model":"gpt-4.1-mini","created":1736397875,"object":"extensions.chat.completion.chunk","choices":[{"index":0,"delta":{"context":{"messages":[{"role":"tool","content":"hello","end_turn":false}]}},"end_turn":false,"finish_reason":"None"}]}'
+            b'data: {"id":"1","model":"gpt4.1-mini","created":1736397875,"object":"extensions.chat.completion.chunk","choices":[{"index":0,"delta":{"context":{"messages":[{"role":"tool","content":"hello","end_turn":false}]}},"end_turn":false,"finish_reason":"None"}]}'
         ]
         mock_response.headers = {"apim-request-id": "test-request-id"}
         mock_post.return_value.__enter__.return_value = mock_response
@@ -381,7 +381,7 @@ def test_stream_with_data_azure_error():
         #     body = mock_body
         mock_response = MagicMock()
         mock_response.iter_lines.return_value = [
-            b'data: {"id":"1","model":"gpt-4.1-mini","created":1736397875,"object":"extensions.chat.completion.chunk","choices":[{"index":0,"delta":{"context":{"messages":[{"role":"tool","content":"hello","end_turn":false}]}},"end_turn":false,"finish_reason":"None"}]}'
+            b'data: {"id":"1","model":"gpt4.1-mini","created":1736397875,"object":"extensions.chat.completion.chunk","choices":[{"index":0,"delta":{"context":{"messages":[{"role":"tool","content":"hello","end_turn":false}]}},"end_turn":false,"finish_reason":"None"}]}'
         ]
         mock_response.headers = {"apim-request-id": "test-request-id"}
         mock_post.return_value.__enter__.return_value = mock_response