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 Now256,000 tokens
16,384 tokens
$0.02 per 1M tokens
$0.10 per 1M tokens
Poor tool calling capabilities and hallucinates web searches
Minimum plan required
$0 per month