Kimi K2 Turbo

moonshotai

Kimi K2 Turbo is a large-scale Mixture-of-Experts language model featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. Extremely fast variant of Kimi K2.

Try Now

Capabilities

Tool Use

Technical Specifications

Context Window

256,000 tokens

Max Output

16,384 tokens

Input Cost

$0.02 per 1M tokens

Output Cost

$0.10 per 1M tokens

⚠️ Deprecated

Deprecated on

Reason

Poor tool calling capabilities and hallucinates web searches

Recommended Replacement

Kimi K2 Thinking Turbo

Availability

Free

Minimum plan required

$0 per month

Also available in these plans

Plus
$20/mo
Pro
$100/mo
Super
$200/mo