Moonshot: kimi-k2-0905:free

kimi-k2-0905:free
262.1K context262.1K outToolsParallel toolsStructuredSystem msg
Released Sep 4, 2025Knowledge cutoff 2024Updated Sep 4, 2025

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, 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. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.

Mode chatTokenizer Othermoonshotai/Kimi-K2-Instruct-0905

Pricing

Input price
$0.00/ 1M tokens
Output price
$0.00/ 1M tokens
Context window 131.1K tokensCompatible endpoints openaiVendor Moonshot

Performance

Loading performance data...

Usage & Ranking

Loading usage...

Supported parameters

All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.

ParameterProvidersDefault
frequency_penaltySome providers-
max_tokensAll providers-
presence_penaltySome providers-
repetition_penaltySome providers-
response_formatAll providers-
seedAll providers-
stopAll providers-
structured_outputsAll providers-
temperatureAll providers-
tool_choiceAll providers-
toolsAll providers-
top_kSome providers-
top_pAll providers-

Frequently asked questions

Similar models