Update model-benchmarks.md

Author: ssalgadodev

articles/ai-studio/concepts/model-benchmarks.md

@@ -73,7 +73,7 @@ This approach uses the following default parameters for benchmarking:
 
 | Parameter | Value | Applies to |
 |-----------|-------|----------------|
-| Region | East US/East US2 | [Serverless APIs](../how-to/model-catalog-overview.md#serverless-apis-with-pay-as-you-go-billing) and [Azure OpenAI](/azure/ai-services/openai/overview) |
+| Region | East US/East US2 | [Serverless APIs](../how-to/model-catalog-overview.md#serverless-api-pay-per-token-billing) and [Azure OpenAI](/azure/ai-services/openai/overview) |
 | Tokens per minute (TPM) rate limit | 30k (180 RPM based on Azure OpenAI) <br> N/A (serverless APIs) | For Azure OpenAI models, selection is available for users with rate limit ranges based on deployment type (standard, global, global standard, and so on.) <br> For serverless APIs, this setting is abstracted. |
 | Number of requests | 128 | Serverless APIs, Azure OpenAI |
 | Prompt/Context length | Moderate length | Serverless APIs, Azure OpenAI |
@@ -181,4 +181,4 @@ The different indexes are calculated as follows:
 ## Related content
 
 - [How to benchmark models in Azure AI Studio](../how-to/benchmark-model-in-catalog.md)
-- [Model catalog and collections in Azure AI Studio](../how-to/model-catalog-overview.md)
+- [Model catalog and collections in Azure AI Studio](../how-to/model-catalog-overview.md)