Gemini Pro API Pricing: Gemini 2.5 Pro and 3.1 Pro
Google publishes official API prices for 2 Gemini Pro models: Gemini 3.1 Pro Preview and Gemini 2.5 Pro. Input costs from $1.25 to $2 and output from $10 to $12 per 1M tokens. The lowest output price is Gemini 2.5 Pro at $10; the highest is Gemini 3.1 Pro Preview at $12. These prices were checked by hand on the Gemini API pricing page (ai.google.dev) on Oct 10, 2026.
Prices checked Oct 10, 2026
Models
2
Lowest output / 1M
$10
Gemini 2.5 Pro
Unit
Per 1M tokens
Prices checked
Oct 10, 2026
Gemini Pro API prices by model
Official prices per 1 million tokens from Google's pricing page (source, checked Oct 10, 2026). Open a model for every provider and plan we track.
| Model | Input | Output | Cached input | Context window |
|---|---|---|---|---|
| Gemini 3.1 Pro Preview | $2 | $12 | $0.20 | — |
| Gemini 2.5 Pro | $1.25 | $10 | $0.125 | — |
Pricing notes
- Prompts over 200K tokens cost more: Gemini 3.1 Pro Preview $4 input and $18 output, Gemini 2.5 Pro $2.50 input and $15 output per 1M tokens.
- Output prices include thinking tokens. Context caching also charges $4.50 per 1M tokens per hour of storage.
- Batch and Flex requests cost half: Gemini 2.5 Pro $0.625 input and $5 output per 1M tokens.
- Gemini 2.5 Pro has a free tier in Google AI Studio; Gemini 3.1 Pro Preview has no free tier.
Gemini Pro API pricing FAQ
How much does the Gemini Pro API cost?
Google's official API charges from $1.25 to $2 per 1M input tokens and from $10 to $12 per 1M output tokens across the 2 models listed here. Prices checked Oct 10, 2026.
What is the cheapest Gemini Pro API model?
Gemini 2.5 Pro has the lowest output price: $1.25 per 1M input tokens and $10 per 1M output tokens.
Is cached input cheaper on the Gemini Pro API?
Yes. 2 of the 2 models listed here have a lower cached-input price. For example, Gemini 3.1 Pro Preview charges $0.20 per 1M cached input tokens instead of $2.
Related pricing
BiWu.Ai lists public API prices from official pricing pages for reference and does not sell API access. Long-context, batch and priority rates can differ, and prices can change without notice. Check Google's pricing page before you build on it.