Gemini 3.6 Flash: Cut Agent Tokens With thinking_level

Google shipped Gemini 3.6 Flash on July 21, 2026, and the headline is not a benchmark score, it is the bill. This is the cheaper, more token-efficient Flash tier, tuned for agentic and coding work. Google says it burns about 17% fewer output tokens than 3.5 Flash on the Artificial Analysis Index, with reductions as high as 65% on some DeepSWE tasks, and it dropped the output price from $9 to $7.50 per million tokens while keeping input at $1.50.