Moonshot: kimi-k2.5

kimi-k2.5
262.1K context262.1K outReasoningToolsVisionVideoCacheStructured
Released Jan 27, 2026Knowledge cutoff 2025Updated Jan 27, 2026

Kimi-k2.5 is Moonshot AI's most versatile and intelligent flagship multimodal model to date. Built with a native multimodal architecture, it deeply integrates visual understanding, logical reasoning, code generation, and Agent task processing capabilities. Compared to its predecessor, K2, the k2.5 model marks a significant breakthrough in Agent automation, supporting over 300 steps of complex tool calling for autonomous data crawling, code execution, and in-depth research report writing. Its unique dual-mode design ("Thinking" and "Non-thinking") allows the model to perform long-horizon reasoning for complex logic while maintaining ultra-fast response speeds for standard conversational tasks.

Mode chatTokenizer OtherQuantization int4moonshotai/Kimi-K2.5

Pricing

Input price
$0.72/ 1M tokens
Output price
$3.60/ 1M tokens
Context window 262.1K tokensCompatible endpoints openai, anthropicVendor 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 providersNot sent by default
include_reasoningAll providers-
logit_biasSome providers-
logprobsSome providers-
max_tokensAll providers-
min_pSome providers-
presence_penaltySome providersNot sent by default
reasoningAll providers-
repetition_penaltySome providersNot sent by default
response_formatAll providers-
seedSome providers-
stopSome providers-
structured_outputsSome providers-
temperatureSome providersNot sent by default
tool_choiceAll providers-
toolsAll providers-
top_kSome providersNot sent by default
top_logprobsSome providers-
top_pSome providersNot sent by default

Frequently asked questions

Similar models