Gemini API pricing in TokenCalculator covers Flash Lite, Flash, and Pro rows. Rates checked 12 Aug 2026. In-browser counts are Approx. Confirm with Google countTokens on the model you will call.
Google rates in TokenCalculator
Example cost uses 1000 input tokens and 500 output tokens. Rates checked 12 Aug 2026. Open a row to price your own prompt.
Google families
Treat the catalog as a map of product tiers, not a single price. Mini, nano, flash, and flagship rows exist so you can match quality to budget instead of paying frontier rates for classification.
- Flash Lite: lowest published Gemini rates for high volume.
- Flash: default Gemini for most interactive work.
- Pro: long context and harder jobs, including published tier changes on some rows.
Snapshot
| # | Model | Input / 1M | Output / 1M | Example |
|---|---|---|---|---|
| 1 | Gemini 1.5 Flash-8B | $0.037/1M | $0.150/1M | $0.000112 |
| 2 | Gemini 1.5 Flash | $0.075/1M | $0.300/1M | $0.000225 |
| 3 | Gemini 2.0 Flash-Lite | $0.075/1M | $0.300/1M | $0.000225 |
| 4 | Gemini 2.0 Flash | $0.100/1M | $0.400/1M | $0.0003 |
| 5 | Gemini 2.5 Flash-Lite | $0.100/1M | $0.400/1M | $0.0003 |
| 6 | Gemma 3 27B | $0.200/1M | $0.400/1M | $0.0004 |
| 7 | Gemini 3.1 Flash-Lite | $0.250/1M | $1.50/1M | $0.001 |
| 8 | Gemini 2.5 Flash | $0.300/1M | $2.50/1M | $0.00155 |
Levers that change the bill
- Long context windows, sometimes with a higher rate after a token threshold.
- Cached input when Google publishes a cache rate for that row.
- Flash versus Pro on the same prompt, because output rates diverge.
How to estimate in TokenCalculator
Pick the Google row that matches the API model id you deploy. Paste a real prompt, set expected output tokens, then scale by users and messages per day. Toggle cache or batch only when this catalog publishes those rates for that row.
Common mistakes
- Assuming AI Studio and Vertex list prices always match.
- Ignoring a long context tier after a large PDF lands in the prompt.
- Using a word heuristic for Gemini billing.
Frequently asked questions
Is this the official Google price list?
No. It is a curated snapshot with a checked date and a link to Google’s Gemini pricing page. Use the official page for contracts.
Why is my invoice different?
Token counts, output length, cache writes, batch jobs, and private discounts all move the invoice. Hold the prompt constant in the calculator, then compare to billed tokens from the provider export.