ai-agents-azure-model-config-azure-openai-model-calls-produce-could-not-identif-ced0ee56

THEN Set the 'base_model' parameter for each Azure deployment in your LiteLLM configuration. For example, in the config file, specify the base model such as 'gpt-4' or 'gpt-35-turbo'. This enables accurate token tracking and cost calculation. The correct documentation is at https://docs.litellm.ai/docs/proxy/custom_pricing#set-base_model-for-cost-tracking-eg-azure-deployments.

litellm_config = {
    "model": "azure/gpt-4-deployment",
    "api_version": "2023-07-01-preview",
    "base_model": "gpt-4"
}