You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.

Kimi K2 Thinking is a reasoning model from moonshotai. It works with text and documents, accepts images, and calls external functions. A 262,144-token context allows keeping a large repository, technical specifications, or a collection of files in the dialogue, making the model convenient for code, analytics, and agentic scenarios.

The output limit is 235,929 tokens per response. This is enough for a voluminous technical document, a large code module, or a detailed analysis with calculations. In practice, the length depends on the task and your prompt: if you need the maximum, explicitly ask for a detailed and complete answer.

Yes, this is a key feature of the thinking version: before answering, the model builds a chain of reasoning and only then provides the result. This mode significantly helps with math, logic, code debugging, and multi-step tasks where a correct answer is more important than a fast one.

Yes. The model supports function calling and structured JSON output, so it can be connected to your tools, databases, and external services. In BotHub, this is available via a unified OpenAI-compatible API — you can switch models without rewriting the integration.

Images and documents — yes, they can be sent as input along with text: analyze a screenshot, diagram, table, or file. Audio and video support is not noted in our data. Image or sound generation does not apply to this model — the output is text only.

There are no separate language benchmarks in our data, so we won't promise anything specific — it's easier to test the model on your task, especially since you can switch to another one in BotHub with one click. Access from Russia is without VPN, payment in rubles.