prompt caching

Why are Azure AI Foundry Claude Opus CCU charges much higher than token estimates?

I'm trying to understand the billing for Claude Opus hosted through Microsoft Foundry on Azure. In one day, the usage report showed 359.52K input tokens, 434.39K output tokens,…

Why Is GPT-5.6 So Slow in Azure Foundry, and Is Prompt Caching Working?

GPT-5.6 in Azure Foundry has been extremely slow for me, especially when using the Responses API. Time to first token can be around a minute, making the model…

Is the Claude System Prompt Really That Long?

I've been hearing a lot about the Claude system prompt and I'm shocked at how massive it is. A token calculator claims it's over 24,000 tokens! I understand…