Kimi K2 Thinking vs Kimi K2.7 Code
Kimi K2 Thinking (MoonshotAI) and Kimi K2.7 Code (MoonshotAI) are listed at different prices. Kimi K2 Thinking costs less: $0.60 per 1M input tokens and $2.50 per 1M output tokens, against $0.60 and $3.00 for Kimi K2.7 Code. Both hold 262,144 tokens of context. Kimi K2.7 Code can write up to 235,929 tokens in one response, against 98,304 for Kimi K2 Thinking. Kimi K2 Thinking accepts text and produces text; Kimi K2.7 Code accepts text and images and produces text.
MoonshotAI: Kimi K2 Thinking accepts text and produces text, while MoonshotAI: Kimi K2.7 Code accepts text and images and produces text. Both support tools, structured outputs, response formats, and reasoning, with 262,144-token contexts; their output limits differ.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Kimi K2 Thinking | Kimi K2.7 Code |
|---|---|---|
| Maker | MoonshotAI | MoonshotAI |
| Added to catalog | 6 Nov 2025 | 12 Jun 2026 |
| Input, per 1M tokens | $0.60 | $0.60 |
| Output, per 1M tokens | $2.50 | $3.00 |
| Cached input read, per 1M | $0.15 | $0.12 |
| Context windowTokens | 262,144 | 262,144 |
| Max outputTokens | 98,304 | 235,929 |
| Accepts | 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 Thinking | Kimi K2.7 Code |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0011 | $0.0012 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.017 | $0.017 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.023 | $0.024 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.094 | $0.095 |
Which to choose
Choose Kimi K2 Thinking if
- Output tokens cost less: $2.50 against $3.00 per 1M
Choose Kimi K2.7 Code if
- Cached input costs less: $0.12 against $0.15 per 1M
- You need longer answers in one response: 235,929 tokens against 98,304
- It has to read images, which the other model does not
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.