Follow the latest coverage, related explainers and connected technology stories.
Google has made its flagship Gemini 4 Argon model available to developers subscribed to the paid Gemini API plan, at an introductory price of $2 per million input tokens and $10 per million output tokens through November 30. The model combines input and output tokens within a single one-million-token budget, meaning that longer inputs reduce the space available for the response.
The article explains that modern AI models need knowledge of local decisions and constraints that are difficult to infer, not general guidance or lengthy procedural instructions. It presents a methodology for reviewing instruction files by retaining information that affects outcomes, deleting what tools enforce or models can discover, and moving rules to the appropriate scope.