# Kimi K2.7 Code vs Kimi K3

Kimi K3 is one of Moonshot AI's newest models and Kimi K2.7 Code an earlier one, so this is also what moving up costs or saves. Kimi K2.7 Code is the cheaper of the 2: for the same tokens, 3 read for each 1 written, Kimi K3 costs 3.5 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/kimi-k2-7-code-vs-kimi-k3
- Makers: Kimi K2.7 Code from Moonshot AI, Kimi K3 from Moonshot AI

## Price per million tokens, in US dollars

| | Kimi K2.7 Code | Kimi K3 |
| --- | --: | --: |
| Input | $0.95 | $3 |
| Cached input | $0.19 | $0.30 |
| Cache write | not listed | $3 |
| Output | $4 | $15 |
| Blend, 3 read for each 1 written | $1.7125 | $6 |
| Batch input | not listed | not listed |
| Batch output | not listed | not listed |
| Context window, tokens | 262K | 1.05M |
| Capability score (Epoch Capabilities Index; GPT-5 is 150) | 150 | 157 |
| Longest answer, tokens | not listed | not listed |

## 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 | Kimi K2.7 Code | Kimi K3 |
| --- | --- | --: | --: |
| A chat question | 300, 500, 100 | $6.86 | $25.20 |
| A hard question, with thinking | 300, 1,400, 100 | $17.65 | $65.70 |
| A long report, summarised | 60,000, 2,000, 20 | $39.00 | $126 |
| A 40-turn agent task | 2,800,000, 40,000, 10 | $271 | $659 |
| A support bot's reply | 4,000, 300, 2,000 | $209 | $666 |
| Sort a message into a category | 250, 5, 50,000 | $386 | $1,238 |
| Read an invoice into fields | 1,500, 250, 1,000 | $72.75 | $248 |
| Review a pull request | 25,000, 4,500, 50 | $62.63 | $214 |

## Questions

### Which is cheaper, Kimi K2.7 Code or Kimi K3?

Kimi K2.7 Code is cheaper: $0.95 per million tokens read and $4 per million written, against $3 and $15 on Kimi K3. On a mix of 3 tokens read for each 1 written, Kimi K3 costs 3.5 times as much.

### Which is better, Kimi K2.7 Code or Kimi K3?

On the Epoch Capabilities Index, an independent score from Epoch AI that combines over 50 benchmarks, Kimi K3 scores 157 and Kimi K2.7 Code 150, above the top of the range of doubt around Kimi K2.7 Code's score (GPT-5 is 150). One score is an average; test both on your own work before you switch.

### What does a support bot cost a month on Kimi K2.7 Code and Kimi K3?

At 2,000 replies a day, each reading 4,000 tokens (50 percent of them from cache) and writing 300, it costs $209 a month on Kimi K2.7 Code and $666 on Kimi K3: Kimi K3 costs 3.2 times as much for this job.

### What does an AI agent task cost on Kimi K2.7 Code and Kimi K3?

One 40-turn task that reads 2,800,000 tokens in all, 90 percent of them from cache, and writes 40,000, costs 90 cents on Kimi K2.7 Code and $2.20 on Kimi K3. At 10 tasks a day that is $271 and $659 a month.

### Which has the larger context window, Kimi K2.7 Code or Kimi K3?

Kimi K3, with 1.05M tokens against 262K on Kimi K2.7 Code. 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 Kimi K2.7 Code and Kimi K3?

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 Kimi K2.7 Code to Kimi K3?

No, it costs more per token: Kimi K3 charges $3 per million tokens read and $15 written, against $0.95 and $4 on Kimi K2.7 Code, 3.5 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 Kimi K2.7 Code and Kimi K3 for work that can wait?

Not with a batch price: neither maker's price page lists one for these models. A cache still lowers the price of text the model reads again.

## Sources

- [Moonshot AI: API prices](https://platform.kimi.ai/docs/pricing/chat)
- [Epoch Capabilities Index, by Epoch AI (CC BY 4.0)](https://epoch.ai/benchmarks/eci)

## Other comparisons

- [Kimi K2.7 Code Highspeed vs Kimi K3](https://tecyfy.com/prices/compare/kimi-k2-7-code-highspeed-vs-kimi-k3.md)
- [Kimi K2.6 vs Kimi K3](https://tecyfy.com/prices/compare/kimi-k2-6-vs-kimi-k3.md)
- [GPT-6 Astra vs Kimi K3](https://tecyfy.com/prices/compare/gpt-6-astra-vs-kimi-k3.md)
- [GPT-6.1 Sol vs Kimi K3](https://tecyfy.com/prices/compare/gpt-6-1-sol-vs-kimi-k3.md)
- [GPT-6 Luna vs Kimi K3](https://tecyfy.com/prices/compare/gpt-6-luna-vs-kimi-k3.md)
- [Claude Fable 5.1 vs Kimi K3](https://tecyfy.com/prices/compare/claude-fable-5-1-vs-kimi-k3.md)