Kimi K2 Thinking

Moonshot AI

A thinking model built on the Kimi K2 foundation with general agentic and reasoning capabilities, specializing in deep reasoning tasks. With a 262K context window, it combines chain-of-thought reasoning with tool calling for complex problem-solving. Supports automatic context caching, ToolCalls, JSON Mode, Partial Mode, and internet search.

Try Now

Capabilities

Thinking

Tool Use

Technical Specifications

Context Window

262,144 tokens

Max Output

262,144 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$0.60

Non-Reasoning Output

$2.50

Cache Read Input

$0.15

Tool Costs (per 1K calls)

Web Search

$15

Code Execution

$0.19

Legacy

Made legacy on

Reason

Superseded by Kimi K2.5

Recommended Replacement

Kimi K2.5