Toggle navigation
shortly

Moonshot AI

Available in Shortly AI

Kimi K2 Thinking

Released November 6, 2025

ReasoningTool Use

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.

Try out now
Context window
216.1K tokens
Maximum output
216.1K tokens
Input pricing
$0.47/M
Output pricing
$2.00/M

Independent benchmark

LiveBench historical snapshot

65.6overall

Historical benchmark data from LiveBench, release 2025-12-23. Scores are pinned and are not fetched on page load.

Kimi K2 Thinking LiveBench category scores
CategoryScore
Reasoning63.486
Coding67.437
Agentic Coding38.333
Mathematics90.794
Data Analysis70.568
Language66.453
Instruction Following62.034

Benchmarks measure selected evaluation tasks and do not guarantee performance for every prompt or workflow.

FAQ

Similar AI models

Inkling SmallThinkingmachinesInkling-Small is a lighter-weight model with 12B active parameters, trained with a similar recipe, to Inkling that achieves strong performance with even lower cost and latency.Gemini 3.5 Flash LiteGoogleGemini 3.5 Flash Lite features upgraded agentic capabilities, making the model ideal for subagents in complex workflows.Gemini 3.6 FlashGoogleGemini 3.6 Flash delivers higher quality across coding, agentic workflows, and web development with reduced token consumption and fewer model calls compared to previous model iterations.

Available with one subscription

Start with Kimi K2 Thinking in Shortly AI

Keep your conversations, files and model choices together in one workspace.

Try Kimi K2 Thinking