Kimi K2.7 Code
Kimi K2.7 Code is a large language model made by MoonshotAI, added to the catalog on 12 Jun 2026. It has a context window of 262,144 tokens and costs $0.60 per 1M input tokens and $3.00 per 1M output tokens. It accepts text and images and produces text. Typical uses: end-to-end programming tasks, programming with long contextual inputs and coding requests that include image input.
Price checked · source: OpenRouter
What Kimi K2.7 Code is
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI’s Kimi K2 family. It is described as being built for end-to-end programming tasks over long contexts. It accepts text and images and produces text. Its description identifies it as a native multimodal mixture-of-experts model. Image input is supported alongside text, while the output remains textual. Its stated focus is software-related work with long contexts, rather than a specified programming language or framework.
The model supports reasoning, tools, structured outputs, and response-format controls. The facts do not name particular tools or schemas. It has a context limit of 262,144 tokens and a maximum output of 235,929 tokens. The context limit describes how much input it can accommodate in one context, while the output limit sets the stated ceiling for generated text. These limits are relevant when a programming request includes extensive instructions or source material and calls for a long textual response. Image input can be included where relevant, although the provider facts do not specify image tasks or formats. The description positions it for end-to-end programming tasks, with reasoning and tool support available for applications built around those tasks. The catalog does not list specific supported programming languages, file types, or tool integrations, so those details are not defined by the available description.
Key features
- Coding-focused model for end-to-end programming tasks
- Accepts text and image input; produces text
- 262,144-token context and up to 235,929 output tokens
- Supports tools, reasoning, structured outputs, and response formats
Typical uses
- End-to-end programming tasks
- Programming with long contextual inputs
- Coding requests that include image input
- Generating structured text responses
- Tool-supported programming workflows
Kimi K2.7 Code pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.60 |
| Output, per 1M tokens | $3.00 |
| Cached input read, per 1M tokens | $0.12 |
No price change since it was added on 12 Jun 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0012 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.017 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.024 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.095 |
Kimi K2.7 Code specifications
| Model id | moonshotai/kimi-k2.7-code |
|---|---|
| Version | kimi-k2.7-code-20260612 |
| Context window | 262,144 tokensAbout 196,608 English words |
| Max output | 235,929 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 12 Jun 2026 |
| Input types | text, image |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Kimi K2.7 Code yet.
Compare Kimi K2.7 Code
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.