Kimi K3 是开放权重模型,而非开源模型。Moonshot AI 在 Hugging Face 上发布了该检查点(checkpoint),仓库名为 moonshotai/Kimi-K3,采用的是 Kimi K3 许可证。这是一份自定义许可证,没有 SPDX 标识符,也不在开放源代码促进会(Open Source Initiative)批准的列表之中。Hugging Face 上的模型卡片将许可证字段设置为“other”,名称为 kimi-k3 。如果您希望通过 API 调用该模型,而不是自行运行权重文件,我们将其作为 moonshotai/kimi-k3 提供。
本文涵盖许可证授予和要求的权限、检查点包含的内容,以及在 OpenRouter 上调用该模型的方法。
摘要
Kimi K3 是开放权重的。其权重是公开的,但 Kimi K3 许可证是 Moonshot AI 自行制定的文本,并未获得 OSI 批准。
该许可证默认授予使用、修改、分发和销售的权利。它在大规模应用时增加了两个条件:一项针对“模型即服务”(Model as a Service)的收入门槛,以及一项用户界面署名要求。
该检查点是一个拥有 2.8 万亿参数的混合专家(Mixture-of-Experts)模型,每个 token 有 1040 亿个活跃参数,以 MXFP4 格式存储。
在 OpenRouter 上,该模型的 ID 为 moonshotai/kimi-k3 。它接受文本、图像和视频输入,拥有 1,048,576 个 token 的上下文窗口,并支持推理力度调整、工具调用和结构化输出。没有 :free(免费)变体。
开放权重与开源的区别
订阅即表示您同意接收 OpenRouter 的新闻通讯:包括模型使用数据、产品更新和研究报告,频率约为每周一次。您可以通过每封电子邮件中的链接随时退订。请参阅我们的隐私政策 。
这两个术语回答的是不同的问题。
开放权重(Open-weight)意味着发布者发布了训练好的参数,以便您可以下载并检查它们。附加在这些参数上的许可证可以是发布者编写的任何文本。
开源(Open-source),正如开放源代码促进会所使用的术语那样,意味着许可证符合开源定义,并出现在 OSI 批准的列表中。Apache-2.0 和 MIT 等许可证拥有 SPDX 标识符,并位于该列表之中。
Kimi K3 符合第一个定义,但不符合第二个定义。
Kimi K3 许可证授予的权限
许可证文本将软件定义为模型权重、参数、配置文件、推理和训练代码以及相关文档。它免费授予使用、复制、修改、合并、发布、分发、再许可和销售软件副本的权利,以及运行、部署、微调并从其创建衍生作品的权利。
第 1 条设定了两个基本条件。您必须在所有副本或实质性部分中包含版权声明和许可声明,且您的使用必须符合适用的法律法规。
Kimi K3 许可证在大规模应用时的要求
两个额外的条件适用于超过特定阈值的情况。
模型即服务门槛。第 2 条将“模型即服务”定义为向第三方提供语言模型推理或微调访问权限,例如通过 API,使得第三方能够对输入、参数或训练数据行使有意义的控制权。该定义排除了模型能力嵌入到特定功能或工具中的最终用户产品,并排除了向由他人托管的模型转发请求的情况。如果您或您的任何关联公司运营“模型即服务”业务,且在任意连续 12 个月内总收入超过 2000 万美元,则在使用该软件或其衍生作品进行任何商业目的之前,必须与 Moonshot AI 签订单独协议。
用户界面署名。第 3 条适用于软件或衍生作品用于拥有超过 1 亿月活跃用户或每月超过 2000 万美元收入的商业产品或服务的情况。在这种情况下,该产品必须在其用户界面上显著显示“Kimi K3”。
豁免条款。第4条规定两种情况可免除上述两项条件限制。第一种是内部使用,定义为未将软件、其输出或其底层能力提供给第三方的使用行为。第二种是通过Moonshot AI的官方产品或认证推理合作伙伴进行的访问。
第5条为免责声明。该软件及其输出按“原样”提供,不提供任何形式的担保。
在基于该权重构建产品上线前,请务必阅读许可证条款。本文所述内容依据2026年9月11日发布的文本,不构成法律建议。
检查点包含的内容
以下数据来自Hugging Face模型卡片。
属性 数值
总参数量 2.8T
每令牌激活参数量 104B
专家网络 共896个,每令牌激活16个
注意力机制 Kimi Delta Attention 和 Attention Residuals
视觉编码器 MoonViT-V2,4.01亿参数
上下文长度 1,048,576 个令牌
权重格式 MXFP4 权重、MXFP8 激活值、量化感知训练
许可证 Kimi K3 许可证
Hugging Face 仓库 moonshotai/Kimi-K3
模型卡片将Kimi K3描述为原生多模态模型,能够理解文本、图像和视频。卡片指出思维链功能始终启用,并包含一个 reasoning_effort 字段,可接受 low 、 high 和 max 值,默认值为 max 。对于多轮对话和工具调用,卡片声明必须将API返回的完整助手消息(包括推理内容和工具调用)通过 messages 参数传回。
卡片列出了三个已发布配置文件的本地部署方案:vLLM 、SGLang 和 TokenSpeed 。我们尚未对这些方案进行基准测试,本文也不涵盖自托管内容。2.8万亿参数的检查点需要多节点服务器硬件。如果您不具备此类硬件,使用托管API是运行该模型的途径。
如何在OpenRouter上调用Kimi K3
模型ID为 moonshotai/kimi-k3 。2026年9月11日的目录记录列出了以下属性。
属性 数值
输入模态 文本、图像、视频
输出模态 文本
上下文长度 1,048,576 个令牌
推理功能默认启用,effort值包括 low 、 high 、 max ,默认值为 max
支持的参数 tools 、 tool_choice 、 response_format 、 structured_outputs 、 reasoning 、 reasoning_effort 、 include_reasoning 、 max_tokens 、 temperature 、 top_p 、 top_k 、 seed 、 stop 、 logprobs 、 top_logprobs 、 logit_bias 、 frequency_penalty 、 presence_penalty 、 repetition_penalty 、 min_p
变体 moonshotai/kimi-k3:batch 用于批量API。无免费变体。
定价
我们不为该模型设定统一价格。每个提供商端点均列出其各自的提示词、补全和缓存读取价格,模型页面会显示当前价格表。2026年9月11日,目录中共有19个 moonshotai/kimi-k3 的端点。提示词价格范围为每百万令牌1.80美元至6.00美元,补全价格范围为每百万令牌9.01美元至22.50美元,缓存读取价格范围为每百万令牌0.21美元至0.60美元。Moonshot AI自有端点的价格为:提示词3.00美元、补全15.00美元、缓存读取0.30美元。最大输出长度也因端点而异,从16,384个令牌到943,718个令牌不等。
提供商端点在支持的参数方面也存在差异。2026年9月11日,有两个端点未列出 tools 支持,两个端点未列出 structured_outputs 支持。如果您的请求依赖于特定参数,请将 provider.require_parameters 设置为 true,以便我们仅将请求路由至支持请求中所有参数的端点。有关完整的路由控制选项,请参阅提供商选择部分。
推理功能
Kimi K3默认返回推理内容。通过我们的API,您可以使用 reasoning 对象来控制它。对于此模型,reasoning.effort 可接受 low 、 high 和 max 值。将 reasoning.exclude 设置为 true 可从响应中移除推理文本,同时模型仍会进行推理。将 reasoning.enabled 设置为 false 则要求端点跳过推理过程。
我们在2026年9月11日对 moonshotai/kimi-k3 运行了每种配置一次,使用的是简短的算术提示。默认、低和最大请求均返回了一个 reasoning 字段和一个包含答案的 reasoning_details 条目。exclude 请求返回了答案,但没有 reasoning 字段。enabled: false 请求没有返回 reasoning 字段,而是返回了一个更长的答案,在 content 字段中展示了其推理过程。模型卡片指出 thinking 始终处于启用状态,单次调用无法显示端点是停止了内部推理还是仅停止返回推理内容。请将 enabled: false 视为对端点的请求,而非保证。
对于多轮对话和工具调用,请在 messages 中将完整的 assistant 消息传回,包括 reasoning_details 和 tool_calls 。我们的推理指南涵盖了跨轮次保留推理内容的方法。
带有图像的示例请求
此请求发送图像和问题,要求高推理强度,并打印答案。它使用了 TypeScript SDK 。
import { OpenRouter } from '@openrouter/sdk' ;
const openRouter = new OpenRouter ({
apiKey: process.env. OPENROUTER_API_KEY ?? '' ,
});
const result = await openRouter.chat. send ({
chatRequest: {
model: 'moonshotai/kimi-k3' ,
messages: [
{
role: 'user' ,
content: [
{
type: 'image_url' ,
imageUrl: { url: 'https://example.com/screenshot.png' },
},
{
type: 'text' ,
text: 'Summarize this screenshot and list the open questions.' ,
},
],
},
],
reasoning: {
effort: 'high' ,
},
stream: false ,
},
});
if (result instanceof ReadableStream ) {
throw new Error ( 'Expected a non-streaming response' );
}
console. log (result.choices[ 0 ].message.content);
我们在2026年9月11日使用一张公开照片运行了等效请求。端点返回了对图像的一句话描述、一个 reasoning 字段,以及一个 usage 对象,其中包含96个提示令牌、119个补全令牌和87个推理令牌。图像输入涵盖在图像理解中,视频输入涵盖在视频输入中。
模型记录列出了 tools 、 tool_choice 、 response_format 和 structured_outputs 。工具定义遵循工具调用中的结构。JSON Schema 响应遵循结构化输出。由于这些参数的支持情况因端点而异,当请求依赖于它们时,请将 provider.require_parameters 设置为 true 。
提示缓存
2026年9月11日列出的所有 moonshotai/kimi-k3 端点均显示了 cache-read 价格。当请求命中提供者的提示缓存时,缓存的提示令牌将按该端点的 cache-read 费率计费,而非其提示费率,并且响应会在 usage.prompt_tokens_details.cached_tokens 中报告这些令牌。有关每个提供者如何工作的缓存机制,请参阅提示缓存。
早期的 Kimi 版本
Kimi K2 和 Kimi K2.5 使用修改后的 MIT 许可证。它们在 MIT 基础上各增加了一条条款,要求月活跃用户超过1亿或月收入超过2000万美元的商业产品必须在用户界面上显著显示模型名称。Kimi K3 许可证保留了该署名条款,并增加了“模型即服务”的收入门槛。
我们的目录还列出了 moonshotai/kimi-k2.6 、 moonshotai/kimi-k2.7-code 、 moonshotai/kimi-k2.5 、 moonshotai/kimi-k2-thinking 和 moonshotai/kimi-k2 。本文仅涵盖 Kimi K3 。
常见问题解答
Kimi K3 是开源的吗?
不是。Kimi K3 是开放权重模型。Moonshot AI 在 Hugging Face 上以 Kimi K3 许可证发布了权重,这是一种自定义许可证,不在开放源代码促进会批准的列表中。该许可证授予广泛的使用、修改、分发和销售模型的权限,但有两个适用于收入和用户数量阈值的条件。
Kimi K3 许可证允许什么?
该许可证授予使用、复制、修改、合并、发布、分发、再许可和销售模型副本的权利,以及运行、部署、微调并创建衍生作品的权利。您必须在软件副本中保留版权声明和许可声明,并遵守适用法律。
Kimi K3 许可证增加了哪些条件?
二、如果您或您的关联方运营“模型即服务”业务,且在任意连续12个月内的累计收入超过2000万美元,则在商业使用前需与Moonshot AI另行签订协议。如果基于该模型构建的商业产品拥有超过1亿月活跃用户或每月收入超过2000万美元,其用户界面必须显著展示“Kimi K3”。内部使用以及通过Moonshot AI官方产品或经认证的推理合作伙伴进行的访问可豁免上述两项要求。
我可以下载Kimi K3的权重吗?
可以。检查点已发布在Hugging Face上的moonshotai/Kimi-K3仓库中。这是一个拥有2.8万亿参数的混合专家模型,采用MXFP4格式存储,每个令牌激活1040亿参数。
如何在OpenRouter上调用Kimi K3?
向https://openrouter.ai/api/v1/chat/completions发送聊天完成请求,模型ID为moonshotai/kimi-k3。该端点接受文本、图像和视频输入,返回文本,并支持推理、工具调用和结构化输出参数。
OpenRouter上有Kimi K3的免费版本吗?
没有。目录中列出了moonshotai/kimi-k3以及用于Batch API的独立moonshotai/kimi-k3:batch条目。两者均非免费。定价由各个提供商设定,因此请查看模型页面以获取当前费率。
Kimi K3 is open-weight, not open-source. Moonshot AI published the checkpoint on Hugging Face as moonshotai/Kimi-K3 under the Kimi K3 License , a custom license that has no SPDX identifier and is not on the Open Source Initiative approved list. The Hugging Face model card sets the license field to other with the name kimi-k3 . If you want to call the model through an API instead of running the weights yourself, we serve it as moonshotai/kimi-k3 .
This post covers what the license grants and requires, what the checkpoint contains, and how to call the model on OpenRouter.
Summary
Kimi K3 is open-weight. The weights are public, but the Kimi K3 License is Moonshot AI’s own text and is not OSI-approved.
The license grants use, modification, distribution, and sale by default. It adds two conditions at scale, a Model as a Service revenue gate and a user-interface attribution requirement.
The checkpoint is a 2.8 trillion parameter mixture-of-experts model with 104 billion active parameters per token, stored in MXFP4.
On OpenRouter the model ID is moonshotai/kimi-k3 . It accepts text, image, and video input, has a 1,048,576-token context window, and supports reasoning effort, tool calling, and structured outputs. There is no :free variant.
Open-weight versus open-source
By subscribing you agree to receive the OpenRouter newsletter: model usage data, product updates, and research reports, about one email a week. Unsubscribe anytime via the link in every email. See our Privacy Policy .
The two terms answer different questions.
Open-weight means the publisher released the trained parameters so you can download and inspect them. The license attached to those parameters can be any text the publisher writes.
Open-source, as the Open Source Initiative uses the term, means the license meets the Open Source Definition and appears on the OSI approved list . Licenses like Apache-2.0 and MIT have SPDX identifiers and are on that list.
Kimi K3 meets the first definition and not the second.
What the Kimi K3 License grants
The license text defines the software as the model weights, parameters, configuration files, inference and training code, and associated documentation. It grants, free of charge, the rights to use, copy, modify, merge, publish, distribute, sublicense, and sell copies of the software, and to run, deploy, fine-tune, and create derivative works from it.
Section 1 sets two baseline conditions. You must include the copyright notice and the permission notice in all copies or substantial portions of the software, and your use must comply with applicable laws and regulations.
What the Kimi K3 License requires at scale
Two further conditions apply above specific thresholds.
Model as a Service gate. Section 2 defines Model as a Service as giving a third party access to language model inference or fine-tuning, for example through an API, in a way that lets the third party exercise meaningful control over the inputs, parameters, or training data. The definition excludes end-user products where model capabilities are embedded within specific features or harnesses, and it excludes relaying requests to models hosted by others. If you or any of your affiliates operate a Model as a Service business, and your aggregate revenue exceeds 20 million US dollars over any consecutive 12 months, you must enter into a separate agreement with Moonshot AI before using the software or its derivatives for any commercial purpose.
User-interface attribution. Section 3 applies when the software or a derivative is used in a commercial product or service with more than 100 million monthly active users or more than 20 million US dollars in monthly revenue. In that case the product must prominently display “Kimi K3” on its user interface.
Exemptions. Section 4 exempts two cases from both conditions. The first is internal use, defined as use that does not make the software, its outputs, or its underlying capabilities available to third parties. The second is access through Moonshot AI’s official products or certified inference partners.
Section 5 is the warranty disclaimer. The software and its outputs are provided as is, without warranty of any kind.
Read the license before you ship a product built on the weights. This post describes the text as published on 2026-09-11 and is not legal advice.
What the checkpoint contains
The figures below are from the Hugging Face model card .
Fact Value
Total parameters 2.8T
Activated parameters per token 104B
Experts 896 total, 16 activated per token
Attention Kimi Delta Attention and Attention Residuals
Vision encoder MoonViT-V2, 401M parameters
Context length 1,048,576 tokens
Weight format MXFP4 weights, MXFP8 activations, quantization-aware trained
License Kimi K3 License
Hugging Face repository moonshotai/Kimi-K3
The model card describes Kimi K3 as a native multimodal model that understands text, images, and video. It lists thinking as always enabled, with a reasoning_effort field that accepts low , high , and max , defaulting to max . For multi-turn conversations and tool calls, the card states that the complete assistant message returned by the API, including reasoning content and tool calls, must be passed back in messages .
The card lists three local serving stacks with published recipes, vLLM , SGLang , and TokenSpeed . We have not benchmarked these stacks and this post does not cover self-hosting. A 2.8 trillion parameter checkpoint requires multi-node serving hardware. If you do not have that hardware, a hosted API is the way to run the model.
How to call Kimi K3 on OpenRouter
The model ID is moonshotai/kimi-k3 . The catalog record on 2026-09-11 listed these properties.
Property Value
Input modalities text, image, video
Output modality text
Context length 1,048,576 tokens
Reasoning enabled by default, efforts low , high , max , default max
Supported parameters tools , tool_choice , response_format , structured_outputs , reasoning , reasoning_effort , include_reasoning , max_tokens , temperature , top_p , top_k , seed , stop , logprobs , top_logprobs , logit_bias , frequency_penalty , presence_penalty , repetition_penalty , min_p
Variants moonshotai/kimi-k3:batch for the Batch API . No :free variant.
Pricing
We do not set one price for the model. Each provider endpoint lists its own prompt, completion, and cache-read price, and the model page shows the current table. On 2026-09-11 the catalog had 19 endpoints for moonshotai/kimi-k3 . Prompt prices ranged from $1.80 to $6.00 per million tokens, completion prices from $9.01 to $22.50 per million tokens, and cache-read prices from $0.21 to $0.60 per million tokens. Moonshot AI’s own endpoint listed $3.00 prompt, $15.00 completion, and $0.30 cache read. Maximum output length also varied by endpoint, from 16,384 tokens to 943,718 tokens.
Provider endpoints also differ in which parameters they support. On 2026-09-11, two endpoints did not list tools and two did not list structured_outputs . If your request depends on a parameter, set provider.require_parameters to true so we only route to endpoints that support every parameter in the request. See provider selection for the full set of routing controls.
Reasoning
Kimi K3 returns reasoning by default. Through our API you control it with the reasoning object . reasoning.effort accepts low , high , and max for this model. reasoning.exclude set to true removes the reasoning text from the response while the model still reasons. reasoning.enabled set to false asks the endpoint to skip reasoning.
We ran each configuration once against moonshotai/kimi-k3 on 2026-09-11 with a short arithmetic prompt. The default, low , and max requests each returned a reasoning field and one reasoning_details entry with the answer. The exclude request returned the answer with no reasoning fields. The enabled: false request returned no reasoning fields and a longer answer that showed its working in the content field. The model card says thinking is always enabled, and a single call cannot show whether the endpoint stopped internal reasoning or only stopped returning it. Treat enabled: false as a request to the endpoint, not a guarantee.
For multi-turn conversations and tool calls, pass the complete assistant message back in messages , including reasoning_details and tool_calls . Our reasoning guide covers preserving reasoning across turns .
Example request with an image
This request sends an image and a question, asks for high reasoning effort, and prints the answer. It uses the TypeScript SDK .
import { OpenRouter } from '@openrouter/sdk' ;
const openRouter = new OpenRouter ({
apiKey: process.env. OPENROUTER_API_KEY ?? '' ,
});
const result = await openRouter.chat. send ({
chatRequest: {
model: 'moonshotai/kimi-k3' ,
messages: [
{
role: 'user' ,
content: [
{
type: 'image_url' ,
imageUrl: { url: 'https://example.com/screenshot.png' },
},
{
type: 'text' ,
text: 'Summarize this screenshot and list the open questions.' ,
},
],
},
],
reasoning: {
effort: 'high' ,
},
stream: false ,
},
});
if (result instanceof ReadableStream ) {
throw new Error ( 'Expected a non-streaming response' );
}
console. log (result.choices[ 0 ].message.content);
We ran an equivalent request with a public photograph on 2026-09-11. The endpoint returned a one-sentence description of the image, a reasoning field, and a usage object with 96 prompt tokens, 119 completion tokens, and 87 reasoning tokens. Image input is covered in image understanding and video input in video input .
The model record lists tools , tool_choice , response_format , and structured_outputs . Tool definitions follow the shape in tool calling . JSON Schema responses follow structured outputs . Because support for these parameters varies by endpoint, set provider.require_parameters to true when the request depends on them.
Prompt caching
Every moonshotai/kimi-k3 endpoint on 2026-09-11 listed a cache-read price. When a request hits the provider’s prompt cache, the cached prompt tokens are billed at that endpoint’s cache-read rate rather than its prompt rate, and the response reports them in usage.prompt_tokens_details.cached_tokens . See prompt caching for how caching works per provider.
Earlier Kimi releases
Kimi K2 and Kimi K2.5 use a modified MIT license. Each adds one clause to MIT that requires commercial products with more than 100 million monthly active users or more than 20 million US dollars in monthly revenue to prominently display the model name on the user interface. The Kimi K3 License keeps that attribution clause and adds the Model as a Service revenue gate.
Our catalog also lists moonshotai/kimi-k2.6 , moonshotai/kimi-k2.7-code , moonshotai/kimi-k2.5 , moonshotai/kimi-k2-thinking , and moonshotai/kimi-k2 . This post covers Kimi K3 only.
FAQ
Is Kimi K3 open source?
No. Kimi K3 is open-weight. Moonshot AI published the weights on Hugging Face under the Kimi K3 License, a custom license that is not on the Open Source Initiative approved list. The license grants broad rights to use, modify, distribute, and sell the model, with two conditions that apply at revenue and user-count thresholds.
What does the Kimi K3 License allow?
The license grants the rights to use, copy, modify, merge, publish, distribute, sublicense, and sell copies of the model, and to run, deploy, fine-tune, and create derivative works. You must keep the copyright and permission notices in copies of the software and comply with applicable law.
What conditions does the Kimi K3 License add?
Two. If you or your affiliates operate a Model as a Service business and your aggregate revenue exceeds 20 million US dollars over any consecutive 12 months, you need a separate agreement with Moonshot AI before commercial use. If a commercial product built on the model has more than 100 million monthly active users or more than 20 million US dollars in monthly revenue, its user interface must prominently display Kimi K3. Internal use and access through Moonshot AI’s official products or certified inference partners are exempt from both.
Can I download the Kimi K3 weights?
Yes. The checkpoint is published at moonshotai/Kimi-K3 on Hugging Face. It is a 2.8 trillion parameter mixture-of-experts model stored in MXFP4, with 104 billion parameters active per token.
How do I call Kimi K3 on OpenRouter?
Send a chat completion request to https://openrouter.ai/api/v1/chat/completions with the model ID moonshotai/kimi-k3 . The endpoint accepts text, image, and video input, returns text, and supports the reasoning , tools , and structured output parameters.
Is there a free variant of Kimi K3 on OpenRouter?
No. The catalog lists moonshotai/kimi-k3 and a separate moonshotai/kimi-k3:batch entry for the Batch API. Neither is free. Pricing is set per provider, so check the model page for the current rates.
首次收录 · 2026-09-25 · 9.95 分