Model overview
The middle rung of Google's range charges $1.50 per million input tokens and $9 per million output — exactly five times the Lite tier's input rate and 3.6 times its output rate, yet a quarter below the Pro preview's $2 input and $12 output. That asymmetry is the argument for gemini-3-5-flash: moving up from Lite multiplies the prompt bill fivefold but the generation bill by less than four, while moving up to Pro adds only a third on both meters. All three rungs declare the same reasoning, tool calling, multimodal input and context caching, so nothing is gained or lost on features. Cached input costs $0.15, a tenth of the standard rate, and Google bills cache storage separately per token-hour.
Billing conditions: Standard paid text price. Google bills cache storage separately per token-hour; that storage charge is not represented as a cache-write token rate.
- Context window
- 0 tokens
- Knowledge cutoff
- —
- Price last verified
- First observed
Descriptions, capabilities, and tariffs come from the linked source. First-party prices take priority; OpenRouter fallbacks are labelled.