Included in the repo are the two python scripts to test the APIM-AOAI configuration for two different apps.
Also included is the main APIM policy and the accompanying policy fragments.
- Smart load balancing for OpenAI endpoints and Azure API Management: https://github.com/andredewes/apim-aoai-smart-loadbalancing
- Azure OpenAI APIM Enterprise Logging: https://github.com/andredewes/apim-aoai-smart-loadbalancing
- Open AI Cost Gateway Pattern: https://github.com/ThePreston/Custom-Rate-Limiter-API
- Azure OpenAI Model Pricing (Pay-as-you-go): https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/#pricing
- Azure OpenAI Service quotas and limits: https://learn.microsoft.com/en-us/azure/ai-services/openai/quotas-limits