AI cost calculator
Gemini API pricing calculator
Your monthly Gemini API bill at Google's list price, today and after the scheduled increases. Gemini 4 Argon costs $2 per million input tokens and $10 per million output tokens until November 30, 2026, then $4 and $20.
Your inputs
Result
$2,130 a month on Gemini 4 Argon
$7.10 per 1,000 requests.
- Cost per request
- $0.0071
- Cost per 1,000 requests
- $7.10
- Per month
- $2,130
- Per year
- $25,560
- Saved by prompt caching
- $570.00 a monthagainst the same requests with no cache hits
- From 2026-12-01
- $4,260 a monthGoogle list price rises on that date
- Cheapest Google model for this workload
- Gemini 3.8 Flash$810.00 a month
Worked examples
Each row is the calculator run on the inputs shown, with every other input at its default.
| Workload | Model | Requests a day | Tokens in / out | Per month |
|---|---|---|---|---|
| Support chatbot | Gemini 4 Argon | 5,000 | 3,000 / 300 | $751.50 |
| Support chatbot on 3.8 Flash | Gemini 3.8 Flash | 5,000 | 3,000 / 300 | $293.63 |
| Document summaries on 3.8 Flash | Gemini 3.8 Flash | 1,000 | 20,000 / 800 | $540.00 |
| Long documents on 3.1 Pro | Gemini 3.1 Pro Preview | 500 | 250,000 / 2,000 | $8,790 |
| Coding agent on Argon | Gemini 4 Argon | 2,000 | 60,000 / 2,000 | $2,244 |
How it is calculated
Gemini bills input, cached input and output tokens at a price per million tokens. The calculator shows the monthly cost at today's price and, for models with a scheduled change, at the new price too.
Google lists two price rises: Gemini 4 Argon goes from $2 / $10 to $4 / $20 per million tokens on December 1, 2026, and Gemini 3.8 Flash from $0.75 / $3.75 to $1.50 / $7.50 on January 1, 2027. Cached input doubles on the same dates.
Gemini 3.1 Pro charges more for prompts over 200,000 tokens ($4 input and $18 output instead of $2 and $12). The calculator applies that when your input per request is over the threshold.
Prices are the paid tier of the Gemini Developer API. Vertex AI, batch mode and context-cache storage fees are priced separately and are not included. Gemini 3.6 Flash and 3.5 Flash-Lite are left out until their prices are checked by hand.
Questions
How much does the Gemini API cost?
Per million tokens: Gemini 3.8 Flash is $0.75 input and $3.75 output, Gemini 4 Argon is $2 and $10, and Gemini 3.1 Pro is $2 and $12 for prompts up to 200,000 tokens.
Is Gemini getting more expensive?
Google lists Gemini 4 Argon at $4 / $20 from December 1, 2026 and Gemini 3.8 Flash at $1.50 / $7.50 from January 1, 2027. Pick either model above to see your bill before and after.
Is there a free tier?
The Gemini Developer API has a free tier with rate limits for some models. This calculator uses paid-tier prices, which apply to production traffic.
Gemini vs Claude vs GPT: which is cheapest?
For the same tokens, Gemini 4 Argon, Claude Sonnet 5.5 and GPT-6.1 Sol all cost $2 / $10 per million today; Argon doubles in December. The grey bars in the chart show those models for your workload.
Sources
- Google: Gemini Developer API pricing, checked 2026-10-29
Prices and plans change. This page was last checked on 2026-10-29. The data is open: llm-prices.json (CC BY 4.0).