Gemini 3.5 Flash-Lite API Pricing Calculator

At Gemini 3.5 Flash-Lite's rates ($0.3 per 1M input tokens, $2.5 per 1M output), a call with 1,000 input and 500 output tokens costs $0.00155. At 10,000 requests a month, that workload runs $15.50. A heavier call — a 100,000-token prompt returning 2,000 tokens — costs $0.035.

Within Google Gemini's lineup, Gemini 3.5 Flash-Lite runs 5.2× the per-call cost of Gemini 2.5 Flash-Lite and 5.2× less than Gemini 3.1 Pro at this workload. It is priced identically to Gemini 2.5 Flash ($0.3 in / $2.5 out per 1M tokens) — for this calculator the two differ only in the model itself, not the bill.

Cache-read input is billed at $0.03 per 1M tokens — 90% below the standard input rate, so a long system prompt reused across calls mostly bills at the discounted rate.