Home › Providers › Google Gemini
Google Gemini API pricing
Gemini Flash, Flash-Lite and Pro. 6 models priced per 1,000,000 tokens, verified October 2026. Cheapest: Gemini 3.5 Flash-Lite at $0.30 input. Most expensive: Gemini 3.1 Pro (Preview) at $12 output.
Google Gemini price table
| Model | Input | Cached | Cache write | Output | Context | Batch |
|---|---|---|---|---|---|---|
| Gemini 3.5 Flash-Lite | $0.30 | $0.03 | — | $2.50 | 1,000,000 | Yes |
| Gemini 3.8 Flash promo | $0.75 | $0.075 | — | $3.75 | 1,000,000 | Yes |
| Gemini 3.7 Flash promo | $0.75 | $0.075 | — | $3.75 | 1,000,000 | Yes |
| Gemini 3.5 Flash | $1.50 | $0.15 | — | $9 | 1,000,000 | Yes |
| Gemini 2.5 Pro | $1.25 | $0.125 | — | $10 | 1,000,000 | Yes |
| Gemini 3.1 Pro (Preview) | $2 | $0.20 | — | $12 | 1,000,000 | Yes |
How Google Gemini compares with other providers
| Provider | Models | Cheapest input | Cheapest output | Flagship output |
|---|---|---|---|---|
| OpenAI | 13 | $0.10 | $0.50 | $50 |
| Anthropic | 5 | $1 | $5 | $50 |
| Google Gemini | 6 | $0.30 | $2.50 | $12 |
| xAI Grok | 2 | $1.25 | $2.50 | $6 |
| DeepSeek | 2 | $0.30 | $1.20 | $3.96 |
Workload cost on Google Gemini
| Model | Support chat 1K reqs · 4K/600 | RAG + cache 1K reqs · 50K/1K | Nightly batch 10K reqs · 10K/2K |
|---|---|---|---|
| Gemini 3.5 Flash-Lite | $2.70 | $5.36 | $40 |
| Gemini 3.8 Flash | $5.25 | $10.91 | $75 |
| Gemini 3.7 Flash | $5.25 | $10.91 | $75 |
| Gemini 3.5 Flash | $11.40 | $23.31 | $165 |
| Gemini 2.5 Pro | $11 | $21.93 | $163 |
| Gemini 3.1 Pro (Preview) | $15.20 | $31.08 | $220 |
FAQ
What is the cheapest Google Gemini model?
Gemini 3.5 Flash-Lite at $0.30 per 1M input and $2.50 per 1M output tokens.
What is the most expensive Google Gemini model?
Gemini 3.1 Pro (Preview) at $2 per 1M input and $12 per 1M output tokens.
Does Google Gemini charge for prompt caching?
Yes. Cached reads are published per model; on this provider they range from $0.03 to $0.20 per 1M tokens.