11## Check Quota Availability Before Deployment
22
33Before deploying the accelerator, ** ensure sufficient quota availability** for the required model.
4- > ** For Global Standard | gpt-4 .1-mini - increase the capacity to at least 50K tokens for optimal performance.**
4+ > ** For Global Standard | gpt4 .1-mini - increase the capacity to at least 50K tokens for optimal performance.**
55
66### Login if you have not done so already
77```
@@ -11,7 +11,7 @@ azd auth login
1111
1212### 📌 Default Models & Capacities:
1313```
14- gpt-4 .1-mini:30, text-embedding-ada-002:45
14+ gpt4 .1-mini:30, text-embedding-ada-002:45
1515```
1616### 📌 Default Regions:
1717```
@@ -37,19 +37,19 @@ australiaeast, francecentral, japaneast, northcentralus, southcentralus, westus,
3737 ```
3838✔️ Check specific model(s) in default regions:
3939 ```
40- ./quota_check_params.sh --models gpt-4 .1-mini:30,text-embedding-ada-002:45
40+ ./quota_check_params.sh --models gpt4 .1-mini:30,text-embedding-ada-002:45
4141 ```
4242✔️ Check default models in specific region(s):
4343 ```
4444./quota_check_params.sh --regions eastus,westus
4545 ```
4646✔️ Passing Both models and regions:
4747 ```
48- ./quota_check_params.sh --models gpt-4 .1-mini:30 --regions eastus,westus
48+ ./quota_check_params.sh --models gpt4 .1-mini:30 --regions eastus,westus
4949 ```
5050✔️ All parameters combined:
5151 ```
52- ./quota_check_params.sh --models gpt-4 .1-mini:30,text-embedding-ada-002:45 --regions eastus,westus --verbose
52+ ./quota_check_params.sh --models gpt4 .1-mini:30,text-embedding-ada-002:45 --regions eastus,westus --verbose
5353 ```
5454
5555### ** Sample Output**
0 commit comments