Google Cloud / Gemini API Pricing & Token Economics
Google's Gemini ecosystem delivers native 1M+ token context windows capable of processing hours of audio, video frames, and massive code repositories. Gemini 3.8 Flash emits cached input reads at $0.075/1M, while Gemini 3.1 Pro provides tiered pricing with long-context multipliers for prompts exceeding 200,000 tokens.
Gemini 3.8 Flash delivers a 90% read discount on cache hits ($0.075/1M cached reads). Storage incurs $0.50/1M tokens/hour promo fee through Dec 31, 2026 ($1.00/1M/hr standard).
Standard API execution rules. Refer to individual endpoint rate limits for asynchronous processing.
Gemini 3.1 Pro prompts > 200,000 tokens incur a 2.0x input multiplier ($4.00/1M) and a 1.5x output multiplier ($18.00/1M) on the entire request.
Active Google Cloud / Gemini Models(5 models verified)
All 39 Models →| Model | Context | Input / 1M | Cached / 1M | Output / 1M | Batch Discount | Actions |
|---|---|---|---|---|---|---|
Gemini 3.8 Flash gemini-3.8-flash-001 | 1.05M | $0.75 | $0.075 | $3.75 | 50% off | Specs → |
Gemini 3.1 Pro Preview gemini-3.1-pro-preview | 1.05M | $2.00 | $0.20 | $12.00 | 50% off | Specs → |
Gemini 2.5 Flash-Lite gemini-2.5-flash-lite-001 | 1.05M | $0.10 | $0.01 | $0.40 | 50% off | Specs → |
Gemini 2.5 Flash gemini-2.5-flash | 1.05M | $0.30 | $0.03 | $2.50 | 50% off | Specs → |
Gemini 3.8 Pro gemini-3.8-pro-001 | 1.05M | $4.00 | $0.40 | $18.00 | 50% off | Specs → |
Calculate your monthly Google Cloud / Gemini bill
Simulate prompt caching hit rates, batch discounts, and output token costs with zero server logging.