Google · Direct API

Gemini 3.5 Flash pricing

Output prices include thinking tokens. Cache storage and grounding are billed separately.

DirectOfficial provider

Input$1.5per 1M tokens

Cached input$0.15per 1M tokens

Output$9per 1M tokens

Context1.05Mmaximum window

This is a first-party rate checked against the model provider's official pricing page.

ReasoningCaching

2,000 input + 500 output tokens$0.0075 / request