# Gemini 3.8 Flash vs Kimi K2.6

Gemini 3.8 Flash is the cheaper of the 2: for the same tokens, 3 read for each 1 written, Kimi K2.6 costs 1.1 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/gemini-3-8-flash-vs-kimi-k2-6
- Makers: Gemini 3.8 Flash from Google, Kimi K2.6 from Moonshot AI

## Price per million tokens, in US dollars

| | Gemini 3.8 Flash | Kimi K2.6 |
| --- | --: | --: |
| Input | $0.75 | $0.95 |
| Cached input | $0.075 | $0.16 |
| Cache write | not listed | not listed |
| Output | $3.75 | $4 |
| Blend, 3 read for each 1 written | $1.50 | $1.7125 |
| Batch input | not listed | not listed |
| Batch output | not listed | not listed |
| Context window, tokens | 1.05M | 262K |
| Capability score (Epoch Capabilities Index; GPT-5 is 150) | 157 | 151 |
| Longest answer, tokens | 66K | not listed |

Gemini 3.8 Flash: Until 31 December 2026. From 1 January 2027 it is $1.50 in, $7.50 out and $0.15 cached.

## 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:

- Gemini 3.8 Flash: 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.
- Kimi K2.6: about 2,100 tokens. Counted with the tokenizer Moonshot AI publishes with Kimi K3, the model its API serves.

## 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 | Gemini 3.8 Flash | Kimi K2.6 |
| --- | --- | --: | --: |
| A chat question | 300, 500, 100 | $6.30 | $6.86 |
| A hard question, with thinking | 300, 1,400, 100 | $16.43 | $17.65 |
| A long report, summarised | 60,000, 2,000, 20 | $31.50 | $39.00 |
| A 40-turn agent task | 2,800,000, 40,000, 10 | $165 | $249 |
| A support bot's reply | 4,000, 300, 2,000 | $166 | $205 |
| Sort a message into a category | 250, 5, 50,000 | $309 | $386 |
| Read an invoice into fields | 1,500, 250, 1,000 | $61.88 | $72.75 |
| Review a pull request | 25,000, 4,500, 50 | $53.44 | $62.63 |

## Questions

### Which is cheaper, Gemini 3.8 Flash or Kimi K2.6?

Gemini 3.8 Flash is cheaper: $0.75 per million tokens read and $3.75 per million written, against $0.95 and $4 on Kimi K2.6. On a mix of 3 tokens read for each 1 written, Kimi K2.6 costs 1.1 times as much.

### Which is better, Gemini 3.8 Flash or Kimi K2.6?

On the Epoch Capabilities Index, an independent score from Epoch AI that combines over 50 benchmarks, Gemini 3.8 Flash scores 157 and Kimi K2.6 151, above the top of the range of doubt around Kimi K2.6'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 Gemini 3.8 Flash and Kimi K2.6?

At 2,000 replies a day, each reading 4,000 tokens (50 percent of them from cache) and writing 300, it costs $166 a month on Gemini 3.8 Flash and $205 on Kimi K2.6: Kimi K2.6 costs 1.2 times as much for this job.

### What does an AI agent task cost on Gemini 3.8 Flash and Kimi K2.6?

One 40-turn task that reads 2,800,000 tokens in all, 90 percent of them from cache, and writes 40,000, costs 55 cents on Gemini 3.8 Flash and 83 cents on Kimi K2.6. At 10 tasks a day that is $165 and $249 a month.

### Which has the larger context window, Gemini 3.8 Flash or Kimi K2.6?

Gemini 3.8 Flash, with 1.05M tokens against 262K on Kimi K2.6. 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 Gemini 3.8 Flash and Kimi K2.6?

No. Our lesson "How AI writes", 1,700 words long, is about 2,200 tokens on Gemini 3.8 Flash and about 2,100 on Kimi K2.6. Each maker cuts text its own way, and every extra token is paid for at the model's price.

### Can I pay less on Gemini 3.8 Flash and Kimi K2.6 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

- [Google: API prices](https://ai.google.dev/gemini-api/docs/pricing)
- [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

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