# Claude Sonnet 4.5 vs Gemini 2.5 Pro

Gemini 2.5 Pro is the cheaper of the 2: for the same tokens, 3 read for each 1 written, Claude Sonnet 4.5 costs 1.7 times as much. Below are both price lists, what 8 everyday jobs cost a month on each, and how many tokens the same text takes on each, which can change the answer.

- Page, with a calculator for your own job: https://tecyfy.com/prices/compare/claude-sonnet-4-5-vs-gemini-2-5-pro
- Makers: Claude Sonnet 4.5 from Anthropic, Gemini 2.5 Pro from Google

## Price per million tokens, in US dollars

| | Claude Sonnet 4.5 | Gemini 2.5 Pro |
| --- | --: | --: |
| Input | $3 | $1.25 |
| Cached input | $0.30 | $0.125 |
| Cache write | $3.75 | not listed |
| Output | $15 | $10 |
| Blend, 3 read for each 1 written | $6 | $3.4375 |
| Batch input | $1.50 | not listed |
| Batch output | $7.50 | not listed |
| Long prompt input (above 200K on Gemini 2.5 Pro) | $3 | $2.50 |
| Long prompt output | $15 | $15 |
| Context window, tokens | 200K | 1.05M |
| Capability score (Epoch Capabilities Index; GPT-5 is 150) | 147 | not listed |
| Longest answer, tokens | 64K | 66K |

## The same text, counted by each maker

Our lesson "How AI writes" (https://tecyfy.com/learn/how-ai-works/how-ai-writes), about 1,700 words of English:

- Claude Sonnet 4.5: about 2,100 to 3,600 tokens. Anthropic does not publish its tokenizer. It says Claude 4.7 and later produce about 30 percent more tokens for the same text than earlier models, and an independent test counted TypeScript at 1.73 times OpenAI's figure. The range runs from OpenAI's count to 1.75 times it.
- Gemini 2.5 Pro: about 2,200 tokens. Google does not publish the Gemini tokenizer. Its rule is that a token is about 4 characters, so the count is the characters divided by 4.

## What 8 everyday jobs cost a month on each

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

| Job | Tokens in, out, runs a day | Claude Sonnet 4.5 | Gemini 2.5 Pro |
| --- | --- | --: | --: |
| A chat question | 300, 500, 100 | $25.20 | $16.13 |
| A hard question, with thinking | 300, 1,400, 100 | $65.70 | $43.13 |
| A long report, summarised | 60,000, 2,000, 20 | $126 | $57.00 |
| A 40-turn agent task | 2,800,000, 40,000, 10 | $659 | $320 |
| A support bot's reply | 4,000, 300, 2,000 | $666 | $345 |
| Sort a message into a category | 250, 5, 50,000 | $1,238 | $544 |
| Read an invoice into fields | 1,500, 250, 1,000 | $248 | $131 |
| Review a pull request | 25,000, 4,500, 50 | $214 | $114 |

## Questions

### Which is cheaper, Claude Sonnet 4.5 or Gemini 2.5 Pro?

Gemini 2.5 Pro is cheaper: $1.25 per million tokens read and $10 per million written, against $3 and $15 on Claude Sonnet 4.5. On a mix of 3 tokens read for each 1 written, Claude Sonnet 4.5 costs 1.7 times as much.

### Which is better, Claude Sonnet 4.5 or Gemini 2.5 Pro?

Claude Sonnet 4.5 scores 147 on the Epoch Capabilities Index, an independent score from Epoch AI that combines over 50 benchmarks (GPT-5 is 150). Gemini 2.5 Pro has no independent score yet, so the only fair test is to run the same 10 tasks on both.

### What does a support bot cost a month on Claude Sonnet 4.5 and Gemini 2.5 Pro?

At 2,000 replies a day, each reading 4,000 tokens (50 percent of them from cache) and writing 300, it costs $666 a month on Claude Sonnet 4.5 and $345 on Gemini 2.5 Pro: Claude Sonnet 4.5 costs 1.9 times as much for this job.

### What does an AI agent task cost on Claude Sonnet 4.5 and 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 $2.20 on Claude Sonnet 4.5 and $1.07 on Gemini 2.5 Pro. At 10 tasks a day that is $659 and $320 a month.

### Which has the larger context window, Claude Sonnet 4.5 or Gemini 2.5 Pro?

Gemini 2.5 Pro, with 1.05M tokens against 200K on Claude Sonnet 4.5. The window holds your instructions, the files you attach, the conversation so far and the answer, all at once.

### Does the same text take the same number of tokens on Claude Sonnet 4.5 and Gemini 2.5 Pro?

No. Our lesson "How AI writes", 1,700 words long, is about 2,100 to 3,600 tokens on Claude Sonnet 4.5 and about 2,200 on Gemini 2.5 Pro. Each maker cuts text its own way, and every extra token is paid for at the model's price.

### Can I pay less on Claude Sonnet 4.5 and Gemini 2.5 Pro for work that can wait?

On Claude Sonnet 4.5 only: with a batch, where you collect the answers later, it costs $1.50 per million tokens read and $7.50 written. Google's price page lists no batch price for Gemini 2.5 Pro.

## Sources

- [Anthropic: API prices](https://platform.claude.com/docs/en/about-claude/pricing)
- [Google: API prices](https://ai.google.dev/gemini-api/docs/pricing)
- [Epoch Capabilities Index, by Epoch AI (CC BY 4.0)](https://epoch.ai/benchmarks/eci)

## Other comparisons

- [Claude Fable 5.1 vs Claude Sonnet 4.5](https://tecyfy.com/prices/compare/claude-fable-5-1-vs-claude-sonnet-4-5.md)
- [Claude Opus 5.5 vs Claude Sonnet 4.5](https://tecyfy.com/prices/compare/claude-opus-5-5-vs-claude-sonnet-4-5.md)
- [Claude Sonnet 4.5 vs Claude Sonnet 5.5](https://tecyfy.com/prices/compare/claude-sonnet-4-5-vs-claude-sonnet-5-5.md)
- [Claude Haiku 5.5 vs Claude Sonnet 4.5](https://tecyfy.com/prices/compare/claude-haiku-5-5-vs-claude-sonnet-4-5.md)
- [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)