Kimi K2 Thinking

Kimi K2 Thinking is an advanced open-source thinking model by Moonshot AI. It can execute up to 200 – 300 sequential tool calls without human interference, reasoning coherently across hundreds of steps to solve complex problems. Built as a thinking agent, it reasons step by step while using tools, achieving state-of-the-art performance on Humanity's Last Exam (HLE), BrowseComp, and other benchmarks, with major gains in reasoning, agentic search, coding, writing, and general capabilities.

ReasoningToolsCache

Context 216.1K·Max out 216.1K

Quickstart

import { streamText } from 'ai';
import { createOpenAICompatible } from '@ai-sdk/openai-compatible';

const blackbox = createOpenAICompatible({
  name: 'blackbox',
  apiKey: process.env.BLACKBOX_API_KEY!,
  baseURL: 'https://api.blackbox.ai/v1',
});

const result = streamText({
  model: blackbox('blackboxai/moonshotai/kimi-k2-thinking'),
  prompt: 'Why is the sky blue?',
});

for await (const chunk of result.textStream) {
  process.stdout.write(chunk);
}

Specs & pricing

Input $/M: 0.47
Output $/M: 2
Context window: 216.1K
Max output: 216.1K
Supported parameters: —

Related models

Model	Type	Context	Input $/M
Kimi K2.7 Code	Text	262.1K	0.95
Kimi K2 Instruct	Text	131.1K	0.57
Kimi K2.5	Text	262.1K	0.6
Kimi K2.6	Text	262K	0.95
Kimi K2.7 Code High Speed	Text	262.1K	1.90