# Gemini 2.5 Pro API pricing

Gemini 2.5 Pro is an earlier Google model, still sold. It costs $1.25 per million tokens it reads and $10 per million it writes, $3.44 on a mix of 3 read for each 1 written. Google's newest models are Gemini 4 Argon, Gemini 3.8 Flash and Gemini 3.5 Flash-Lite. Below are every price Google lists for it, and what 8 everyday jobs cost a month on it.

- Page: https://tecyfy.com/prices/gemini-2-5-pro
- Maker: Google

## Price per million tokens, in US dollars

| | Price |
| --- | --: |
| Input | $1.25 |
| Cached input | $0.125 |
| Cache write | not listed |
| Output | $10 |
| Blend, 3 read for each 1 written | $3.44 |
| Batch input | not listed |
| Batch output | not listed |
| Long prompt input (over 200K tokens) | $2.50 |
| Long prompt output | $15 |
| Context window, tokens | 1.05M |
| Longest answer, tokens | 66K |
| Capability score (Epoch Capabilities Index; GPT-5 is 150) | not scored |

## What 8 everyday jobs cost a month

Each job at its usual runs a day, for 30 days, at the standard price.

| Job | Tokens in, out, runs a day | A run | A month |
| --- | --- | --: | --: |
| A chat question | 300, 500, 100 | 0.54 cents | $16.13 |
| A hard question, with thinking | 300, 1,400, 100 | 1.4 cents | $43.13 |
| A long report, summarised | 60,000, 2,000, 20 | 9.5 cents | $57.00 |
| A 40-turn agent task | 2,800,000, 40,000, 10 | $1.07 | $320 |
| A support bot's reply | 4,000, 300, 2,000 | 0.57 cents | $345 |
| Sort a message into a category | 250, 5, 50,000 | 0.036 cents | $544 |
| Read an invoice into fields | 1,500, 250, 1,000 | 0.44 cents | $131 |
| Review a pull request | 25,000, 4,500, 50 | 7.6 cents | $114 |

## Questions

### How much does Gemini 2.5 Pro cost?

Gemini 2.5 Pro costs $1.25 per million input tokens, the text it reads, and $10 per million output tokens, the text it writes, thinking included. On a mix of 3 tokens read for each 1 written, that is $3.44 per million.

### How much does cached input cost on Gemini 2.5 Pro?

Text Gemini 2.5 Pro reads again from the cache costs $0.125 per million tokens, against $1.25 the first time. Google lists no separate price for writing to the cache.

### Does Gemini 2.5 Pro have a batch price?

Not on Google's price page, which lists no batch price for Gemini 2.5 Pro. The cache still lowers the price of text it reads again.

### Does a long prompt cost more on Gemini 2.5 Pro?

Yes. Once a prompt passes 200K tokens, the whole request costs $2.50 per million tokens read and $15 per million written, against $1.25 and $10 below that.

### What is the context window of Gemini 2.5 Pro?

Gemini 2.5 Pro holds 1.05M tokens at once, about 1,600 pages of English text, and writes up to 66K tokens in one answer. The window holds your instructions, the files you attach, the conversation so far and the answer.

### How good is Gemini 2.5 Pro?

Epoch AI has no independent score for Gemini 2.5 Pro yet. Run the same 10 tasks of your own on it and on a model you know, and compare the answers and the bills.

### Should I still use Gemini 2.5 Pro?

It is still sold, so it keeps working, but Google's newest models are Gemini 4 Argon, Gemini 3.8 Flash and Gemini 3.5 Flash-Lite. Compare its price with theirs below, and run your own tasks on the newer model before you move.

### What does a support bot cost a month on Gemini 2.5 Pro?

At 2,000 replies a day, each reading 4,000 tokens (50 percent of them from cache) and writing 300, a support bot costs 0.57 cents a reply on Gemini 2.5 Pro, $345 a month.

### What does an AI agent task cost on Gemini 2.5 Pro?

One 40-turn task that reads 2,800,000 tokens in all, 90 percent of them from cache, and writes 40,000, costs $1.07 on Gemini 2.5 Pro. At 10 tasks a day that is $320 a month.

## Sources

- [Google: API prices](https://ai.google.dev/gemini-api/docs/pricing)
- Every model's prices as [JSON](https://tecyfy.com/prices.json) or [CSV](https://tecyfy.com/prices.csv), free to use

## Compare

- [Gemini 2.5 Pro vs Gemini 4 Argon](https://tecyfy.com/prices/compare/gemini-2-5-pro-vs-gemini-4-argon.md)
- [Gemini 2.5 Pro vs Gemini 3.8 Flash](https://tecyfy.com/prices/compare/gemini-2-5-pro-vs-gemini-3-8-flash.md)
- [Gemini 2.5 Pro vs Gemini 3.5 Flash-Lite](https://tecyfy.com/prices/compare/gemini-2-5-pro-vs-gemini-3-5-flash-lite.md)
- [Gemini 2.5 Pro vs GPT-4o](https://tecyfy.com/prices/compare/gemini-2-5-pro-vs-gpt-4o.md)
- [Gemini 2.5 Pro vs GPT-4.1](https://tecyfy.com/prices/compare/gemini-2-5-pro-vs-gpt-4-1.md)
- [Claude Sonnet 4.5 vs Gemini 2.5 Pro](https://tecyfy.com/prices/compare/claude-sonnet-4-5-vs-gemini-2-5-pro.md)

## Google's other models

- [Gemini 4 Argon](https://tecyfy.com/prices/gemini-4-argon.md)
- [Gemini 3.8 Flash](https://tecyfy.com/prices/gemini-3-8-flash.md)
- [Gemini 3.5 Flash-Lite](https://tecyfy.com/prices/gemini-3-5-flash-lite.md)
- [Gemini 3.6 Flash](https://tecyfy.com/prices/gemini-3-6-flash.md)
- [Gemini 3.1 Pro Preview](https://tecyfy.com/prices/gemini-3-1-pro-preview.md)
- [Gemini 3.1 Flash-Lite](https://tecyfy.com/prices/gemini-3-1-flash-lite.md)
- [Gemini 3 Flash Preview](https://tecyfy.com/prices/gemini-3-flash-preview.md)
- [Gemini 2.5 Flash](https://tecyfy.com/prices/gemini-2-5-flash.md)
- [Gemini 2.5 Flash-Lite](https://tecyfy.com/prices/gemini-2-5-flash-lite.md)