... bills were consistently 3 4 our estimates. We started digging. Turns out the token price card is the tip of the iceberg: Reasoning models like o3 and DeepSeek R1 generate internal chain-of-thought tokens billed at full output rate often 5 10 the visible response. Nothing on the pricing page tells you this upfront. GPT-4 tiles a 1024 1024 image into ~765 tokens before it reads your prompt. Send 10 images in a conversation, and your "cheap" chat ... ... call isn't cheap anymore. GPT-4o Realtime charges $100/1M audio input tokens vs