Kimi K2.6 vs Kimi K2.7 Code
Kimi K2.6 (MoonshotAI) and Kimi K2.7 Code (MoonshotAI) are listed at different prices. Kimi K2.7 Code costs less: $0.60 per 1M input tokens and $3.00 per 1M output tokens, against $0.65 and $3.41 for Kimi K2.6. Both hold 262,144 tokens of context. Both accept text and images and produce text.
MoonshotAI: Kimi K2.6 and MoonshotAI: Kimi K2.7 Code both accept text and images, produce text, and support tools, structured outputs, response formats, and reasoning, with 262,144-token contexts and 235,929-token output limits. K2.6 highlights coding-driven UI/UX and multi-agent orchestration; K2.7 Code focuses on programming tasks over long contexts.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Kimi K2.6 | Kimi K2.7 Code |
|---|---|---|
| Maker | MoonshotAI | MoonshotAI |
| Added to catalog | 20 Apr 2026 | 12 Jun 2026 |
| Input, per 1M tokens | $0.65 | $0.60 |
| Output, per 1M tokens | $3.41 | $3.00 |
| Cached input read, per 1M | $0.15 | $0.12 |
| Context windowTokens | 262,144 | 262,144 |
| Max outputTokens | 235,929 | 235,929 |
| Accepts | image, text | image, text |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | Yes |
| Reasoning effort control | No | No |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | Kimi K2.6 | Kimi K2.7 Code |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0013 | $0.0012 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.019 | $0.017 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.026 | $0.024 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.103 | $0.095 |
Which to choose
Choose Kimi K2.6 if
No row of the table favours Kimi K2.6. The difference, if there is one, is in the answers it writes: try it on your own task.
Kimi K2.6 detailsChoose Kimi K2.7 Code if
- Input tokens cost less: $0.60 against $0.65 per 1M
- Output tokens cost less: $3.00 against $3.41 per 1M
- Cached input costs less: $0.12 against $0.15 per 1M
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.