# GPT-3.5 Turbo (1106) vs GPT-6.1 Sol

GPT-6.1 Sol is one of OpenAI's newest models and GPT-3.5 Turbo (1106) an earlier one, so this is also what moving up costs or saves. GPT-3.5 Turbo (1106) is the cheaper of the 2: for the same tokens, 3 read for each 1 written, GPT-6.1 Sol costs 3.2 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/gpt-3-5-turbo-1106-vs-gpt-6-1-sol
- Makers: GPT-3.5 Turbo (1106) from OpenAI, GPT-6.1 Sol from OpenAI

## Price per million tokens, in US dollars

| | GPT-3.5 Turbo (1106) | GPT-6.1 Sol |
| --- | --: | --: |
| Input | $1 | $2 |
| Cached input | not listed | $0.10 |
| Cache write | not listed | $2.50 |
| Output | $2 | $10 |
| Blend, 3 read for each 1 written | $1.25 | $4 |
| Batch input | $1 | $1 |
| Batch output | $2 | $5 |
| Long prompt input (above 272K on GPT-6.1 Sol) | $1 | $4 |
| Long prompt output | $2 | $15 |
| Context window, tokens | not listed | 1.05M |
| Capability score (Epoch Capabilities Index; GPT-5 is 150) | not listed | 166 |
| Longest answer, tokens | not listed | 128K |

## 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 | GPT-3.5 Turbo (1106) | GPT-6.1 Sol |
| --- | --- | --: | --: |
| A chat question | 300, 500, 100 | $3.90 | $16.80 |
| A hard question, with thinking | 300, 1,400, 100 | $9.30 | $43.80 |
| A long report, summarised | 60,000, 2,000, 20 | $38.40 | $84.00 |
| A 40-turn agent task | 2,800,000, 40,000, 10 | $864 | $364 |
| A support bot's reply | 4,000, 300, 2,000 | $276 | $432 |
| Sort a message into a category | 250, 5, 50,000 | $390 | $825 |
| Read an invoice into fields | 1,500, 250, 1,000 | $60.00 | $165 |
| Review a pull request | 25,000, 4,500, 50 | $51.00 | $143 |

## Questions

### Which is cheaper, GPT-3.5 Turbo (1106) or GPT-6.1 Sol?

GPT-3.5 Turbo (1106) is cheaper: $1 per million tokens read and $2 per million written, against $2 and $10 on GPT-6.1 Sol. On a mix of 3 tokens read for each 1 written, GPT-6.1 Sol costs 3.2 times as much.

### Which is better, GPT-3.5 Turbo (1106) or GPT-6.1 Sol?

GPT-6.1 Sol scores 166 on the Epoch Capabilities Index, an independent score from Epoch AI that combines over 50 benchmarks (GPT-5 is 150). GPT-3.5 Turbo (1106) 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 GPT-3.5 Turbo (1106) and GPT-6.1 Sol?

At 2,000 replies a day, each reading 4,000 tokens (50 percent of them from cache) and writing 300, it costs $276 a month on GPT-3.5 Turbo (1106) and $432 on GPT-6.1 Sol: GPT-6.1 Sol costs 1.6 times as much for this job.

### What does an AI agent task cost on GPT-3.5 Turbo (1106) and GPT-6.1 Sol?

One 40-turn task that reads 2,800,000 tokens in all, 90 percent of them from cache, and writes 40,000, costs $2.88 on GPT-3.5 Turbo (1106) and $1.21 on GPT-6.1 Sol. At 10 tasks a day that is $864 and $364 a month.

### Does the same text take the same number of tokens on GPT-3.5 Turbo (1106) and GPT-6.1 Sol?

Yes, both are counted the same way: our lesson "How AI writes", 1,700 words long, is about 2,100 tokens on each.

### Is it cheaper to move from GPT-3.5 Turbo (1106) to GPT-6.1 Sol?

No, it costs more per token: GPT-6.1 Sol charges $2 per million tokens read and $10 written, against $1 and $2 on GPT-3.5 Turbo (1106), 3.2 times as much for the same tokens. It pays off only if better answers save more than that, for example in fewer retries.

### Can I pay less on GPT-3.5 Turbo (1106) and GPT-6.1 Sol for work that can wait?

Yes, on both. With a batch, where you collect the answers later instead of at once, GPT-3.5 Turbo (1106) costs $1 per million tokens read and $2 written, and GPT-6.1 Sol $1 and $5.

## Sources

- [OpenAI: API prices](https://developers.openai.com/api/docs/pricing)
- [Epoch Capabilities Index, by Epoch AI (CC BY 4.0)](https://epoch.ai/benchmarks/eci)

## Other comparisons

- [GPT-6.1 Sol vs GPT-6 Sol](https://tecyfy.com/prices/compare/gpt-6-1-sol-vs-gpt-6-sol.md)
- [GPT-5.6 Sol vs GPT-6.1 Sol](https://tecyfy.com/prices/compare/gpt-5-6-sol-vs-gpt-6-1-sol.md)
- [GPT-5.6 Terra vs GPT-6.1 Sol](https://tecyfy.com/prices/compare/gpt-5-6-terra-vs-gpt-6-1-sol.md)
- [GPT-5.6 Luna vs GPT-6.1 Sol](https://tecyfy.com/prices/compare/gpt-5-6-luna-vs-gpt-6-1-sol.md)
- [GPT-5.5 vs GPT-6.1 Sol](https://tecyfy.com/prices/compare/gpt-5-5-vs-gpt-6-1-sol.md)
- [GPT-5.5 pro vs GPT-6.1 Sol](https://tecyfy.com/prices/compare/gpt-5-5-pro-vs-gpt-6-1-sol.md)