Kimi K2.6
Kimi K2.6 is a large language model made by MoonshotAI, added to the catalog on 20 Apr 2026. It has a context window of 262,144 tokens and costs $0.65 per 1M input tokens and $3.41 per 1M output tokens. It accepts text and images and produces text. Typical uses: end-to-end coding tasks, coding-driven UI/UX generation and multi-agent orchestration.
Price checked · source: OpenRouter
What Kimi K2.6 is
Kimi K2.6 is Moonshot AI’s multimodal model for coding and related workflows. It accepts text and images and produces text. The provider describes it as designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It also identifies complex end-to-end coding tasks in Python, Rust, and Go as a focus. Alongside these uses, Kimi K2.6 supports reasoning and tools, as well as structured outputs and response-format options. These features can support tool-enabled workflows and requests that specify a format for the response; the listed output modality remains text.
The model has a context window of 262,144 tokens and a maximum output of 235,929 tokens. It can take in substantial text and image input, with room for a long text response. This capacity suits requests that bring together extensive instructions, code, or other supplied context, including work that spans stages or involves coordination. Image input is relevant when visual material accompanies a UI/UX coding request, while text input supports written specifications and code-related prompts. Tool support fits workflows where tools are part of the task. Structured outputs and response formats can be useful when a task calls for a defined shape. Kimi K2.6 is oriented toward involved coding and reasoning work with multimodal input, including tasks in the programming languages named by its provider.
Key features
- Accepts text and image inputs and produces text
- Has a 262,144-token context window
- Supports reasoning and tools
- Supports structured outputs and response formats
- Designed for coding tasks in Python, Rust, and Go
Typical uses
- End-to-end coding tasks
- Coding-driven UI/UX generation
- Multi-agent orchestration
- Working with long coding specifications
- Reasoning over text and image inputs
Kimi K2.6 pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.65 |
| Output, per 1M tokens | $3.41 |
| Cached input read, per 1M tokens | $0.15 |
No price change since it was added on 20 Apr 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0013 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.019 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.026 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.103 |
Kimi K2.6 specifications
| Model id | moonshotai/kimi-k2.6 |
|---|---|
| Version | kimi-k2.6-20260420 |
| Context window | 262,144 tokensAbout 196,608 English words |
| Max output | 235,929 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 20 Apr 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 K2.6 yet.
Compare Kimi K2.6
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.