Kimi K2 Turbo

moonshotai

A massive 1T parameter MoE model (32B active) optimized for agentic capabilities, tool use, reasoning, and code synthesis. Achieved strong benchmark results in coding and reasoning tasks.

Try Now

Capabilities

Tool Use

Example Use Cases

Agentic workflows

Code synthesis

Reasoning tasks

Technical Specifications

Context Window

256,000 tokens

Max Output

16,384 tokens

Cache Miss Cost

$2.40 per 1M tokens

Non-Reasoning Cost

$10 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Poor tool calling capabilities and hallucinates web searches

Recommended Replacement

Kimi K2.5