模型广场

选择模型后可复制配置给 AI，也可以快速测试当前连接延迟。

重置筛选

全部 6文本 6图像 0音频 0视频 0

kimi-k2-instruct

文本文本

Moonshot

Instruction-tuned for agent workflows with reliable tool calling and multilingual coding.

上下文: 131K
输入 / 1M tokens: $0.574
输出 / 1M tokens: $2.3
缓存读 / 1M: $0.115
缓存写 / 1M: $0

ReasoningCodingTask AutomationAgent

kimi-k2-thinking

文本文本

Moonshot

Open-source thinking model built for long-horizon reasoning and hundreds of sequential tool calls across autonomous research, coding, and agent workflows.

上下文: 262K
输入 / 1M tokens: $0.6
输出 / 1M tokens: $2.5
缓存读 / 1M: $0.15
缓存写 / 1M: $0

ReasoningChain of ThoughtComplex PlanningAgent

kimi-k2.5

文本图像视频文本

Moonshot

Top Chinese-English bilingual. Strong long context.

上下文: 262K
输入 / 1M tokens: $0.6
输出 / 1M tokens: $3.011
缓存读 / 1M: $0.15
缓存写 / 1M: $0.718

ChineseBilingual

kimi-k2.6

文本图像视频文本

Moonshot

Latest multimodal model in the K2 series, built for long-horizon coding, code-driven UI/UX generation, and multi-agent orchestration.

上下文: 256K
输入 / 1M tokens: $0.8939
输出 / 1M tokens: $3.7131
缓存读 / 1M: $0.34
缓存写 / 1M: $1.1174

Vision

kimi-k2.7-code

文本视频图像文本

Moonshot

Coding-focused variant in the Kimi K2 family. Accepts text and image inputs, with reasoning on by default. Suited for long-horizon coding and agentic workflows.

上下文: 262K
输入 / 1M tokens: $0.95
输出 / 1M tokens: $4
缓存读 / 1M: $0.19
缓存写 / 1M: $1.1174

CodingAgent CodingChain of Thought

kimi-k3

文本图像文本

Moonshot

A multimodal reasoning model for complex coding, knowledge work, and long-running agent tasks. It works across large codebases, calls tools, and debugs, using images, logs, and test output to refine its output.

上下文: 1M
输入 / 1M tokens: $3
输出 / 1M tokens: $15
缓存读 / 1M: $0.3
缓存写 / 1M: $0

CodingReasoningVisionFrontier

需要完整模型清单或企业接入方案？进入控制台