Kimi K3: API price, context window and how to connect
Kimi K3 by Moonshot AI: $0.239 per million input tokens, $11.936 per million output tokens, a 1.05M-token window. What it is good for, what to compare it with and how to connect it in SKILLOK.
In this article
In short#
Moonshot AI's open multimodal reasoning model with 2.8 trillion parameters. Suited to complex code, knowledge work and long agentic tasks.
Specifications#
| Provider | Moonshot AI |
| Released | 2026-07-16 |
| Context window | 1.05M tokens |
| Accepts | text, images, video |
| Answers with | text |
| Reasoning mode | yes |
| Tool calling | yes |
| Open weights | yes |
| Identifier | moonshotai/kimi-k3 |
Price#
| Per 1M tokens | In dollars |
|---|---|
| Input (question, context) | $0.239 |
| Output (answer) | $11.936 |
For reference: a conversation of 20 questions of ~500 tokens and answers of ~800 tokens costs about $0.193. Models in reasoning mode spend more tokens on an answer than the text shows: the reasoning is paid for too.
What it is good for#
- Complex code
- Long agentic tasks
- Flagship-level open weights
Similar models#
Catalog models with the same kind of output, closest in the price of a typical request.
| Model | Input | Output | Window | Price |
|---|---|---|---|---|
| GPT-6.1 Sol | $2 | $10 | 1.05M | about the same |
| GPT-6.1 Sol Pro | $2 | $10 | 1.05M | about the same |
| Claude Sonnet 5.5 | $2 | $10 | 1M | about the same |
| Gemini 4 Argon | $2 | $10 | 1.05M | about the same |
| GLM 5.3 Prime | $2.8 | $8.8 | 1M | about the same |
Other Moonshot AI models#
How to connect in SKILLOK#
Kimi K3 works through OpenRouter: add an OpenRouter key in Settings → AI and pick the moonshotai/kimi-k3 model. It then becomes available in Space AI, in tasks and to the repository agent. In detail — Connecting a model in SKILLOK.
Where the data comes from#
Prices, the context window and capabilities come from the public OpenRouter catalog as of 2026-10-19. A provider may change the price — the exact figure is always on the model's OpenRouter page.
Was this helpful?