Kimi K2.5
Kimi K2.5 is a large language model made by MoonshotAI, added to the catalog on 27 Jan 2026. It has a context window of 262,144 tokens and costs $0.50 per 1M input tokens and $2.50 per 1M output tokens. It accepts text and images and produces text. Typical uses: generate text from visual inputs, enhance applications with reasoning capabilities and create interactive visual coding solutions.
Price checked · source: OpenRouter
What Kimi K2.5 is
Kimi K2.5, released on January 27, 2026, is a cutting-edge multimodal model from MoonshotAI. With a context length of 262,144, it processes both text and images to generate text outputs. This model excels in general reasoning, visual coding, and utilizing a self-directed agent swarm paradigm. Built on the foundations of Kimi K2 and enhanced with extensive pretraining over 15 trillion mixed visual and text tokens, it offers robust performance for various applications. Whether you're looking to integrate visual elements into your projects or leverage advanced reasoning capabilities, Kimi K2.5 provides a versatile solution for developers and researchers alike.
Key features
- Multimodal input: text and images
- High context length of 262,144
- Strong performance in reasoning tasks
- Self-directed agent swarm paradigm
- Built on 15T mixed visual and text tokens
Typical uses
- Generate text from visual inputs
- Enhance applications with reasoning capabilities
- Create interactive visual coding solutions
- Utilize agentic tool-calling in projects
Kimi K2.5 pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.50 |
| Output, per 1M tokens | $2.50 |
| Cached input read, per 1M tokens | $0.15 |
No price change since it was added on 27 Jan 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0010 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.015 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.020 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.079 |
Kimi K2.5 specifications
| Model id | moonshotai/kimi-k2.5 |
|---|---|
| Version | kimi-k2.5-0127 |
| Context window | 262,144 tokensAbout 196,608 English words |
| Max output | 235,929 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 27 Jan 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.
Write a short essay
RUN20 Nov 2026Write 150 words on how AI might positively upend work, leisure and creativity
AI promises to liberate humanity from drudgery while amplifying our creative potential. In work, intelligent automation will eliminate repetitive tasks, potentially enabling four-day workweeks while humans focus on strategy, empathy, and complex problem-solving. Leisure transforms as AI curates personalized experiences and manages logistics, granting genuine restoration rather than passive consumption. Most profoundly, AI democratizes creativity. Generative tools lower technical barriers, allowing anyone to compose music, code applications, or visualize concepts instantly. Rather than replacing human imagination, AI serves as a collaborative partner—handling execution while humans provide direction, meaning, and emotional resonance. This symbiosis suggests a future where work becomes more human, leisure more fulfilling, and creativity more accessible than ever before.
Compare Kimi K2.5
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.