Kimi K2.6

Moonshot AI

Kimi's latest and most intelligent model. Next-generation native multimodal architecture with breakthroughs in long-horizon coding, instruction compliance, and self-correction. Handles text, image, and video input across thinking and non-thinking modes, with a 262K context window and 252K output capacity for complex multimodal and agent workflows.

Try Now

Capabilities

Thinking

Tool Use

Image Input

Technical Specifications

Context Window

262,144 tokens

Max Output

252,144 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$0.95

Non-Reasoning Output

$4

Cache Read Input

$0.16

Tool Costs (per 1K calls)

Web Search

$15

Code Execution

$0.19