模型即服务(Model as a Service)通道。第2节将模型即服务定义为通过API等方式向第三方提供语言模型推理或微调访问,使第三方能够对输入、参数或训练数据行使有意义的控制。该定义不包括将模型功能嵌入特定功能或工具中的最终用户产品,也不包括向他人托管的模型转发请求。如果您或您的任何关联公司运营模型即服务业务,并且在连续12个月内的总收入超过2000万美元,您必须在将软件或其衍生品用于任何商业目的之前,与Moonshot AI签署单独协议。
Kimi K2:https://huggingface.co/moonshotai/Kimi-K2-Instruct/blob/main/LICENSE 和 Kimi K2.5:https://huggingface.co/moonshotai/Kimi-K2.5/blob/main/LICENSE 使用修改后的 MIT 许可证。每个都在 MIT 中添加了一条条款,要求月活跃用户超过 1 亿或月收入超过 2000 万美元的商业产品在用户界面上显著显示模型名称。Kimi K3 许可证保留了该归属条款,并增加了模型即服务(MaaS)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。
不。Kimi K3 是开放权重的。Moonshot AI 在 Hugging Face 上根据 Kimi K3 许可证发布了权重,该许可证是自定义许可,不在开源倡议批准列表中。该许可证授予广泛的使用、修改、分发和销售模型的权利,但在收入和用户数量达到阈值时有两个条件。
两个。如果您或您的附属机构运营模型即服务业务,并且在任意连续 12 个月内总收入超过 2000 万美元,您在商业使用前需要与 Moonshot AI 签署单独协议。如果基于该模型构建的商业产品月活跃用户超过 1 亿或月收入超过 2000 万美元,则其用户界面必须显著显示 Kimi K3。内部使用以及通过 Moonshot AI 的官方产品或认证推理合作伙伴访问不受上述两项条件限制。
向 https://openrouter.ai/api/v1/chat/completions 发送聊天完成请求,使用模型 ID moonshotai/kimi-k3。该端点接受文本、图像和视频输入,返回文本,并支持 reasoning、tools 和 structured output 参数。
不。目录中列出了 moonshotai/kimi-k3,以及针对 Batch API 的单独条目 moonshotai/kimi-k3:batch。两者都不是免费的。定价由供应商确定,因此请查看模型页面:https://openrouter.ai/moonshotai/kimi-k3 获取当前价格。
模型使用数据、产品更新和研究报告。每周发送一封电子邮件。
Kimi K3 is open-weight, not open-source. Moonshot AI published the checkpoint on Hugging Face as moonshotai/Kimi-K3:https://huggingface.co/moonshotai/Kimi-K3 under the Kimi K3 License:https://huggingface.co/moonshotai/Kimi-K3/blob/main/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:https://openrouter.ai/moonshotai/kimi-k3.
This post covers what the license grants and requires, what the checkpoint contains, and how to call the model on OpenRouter.
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:https://opensource.org/osd and appears on the OSI approved list:https://opensource.org/licenses. Licenses like Apache-2.0:https://spdx.org/licenses/Apache-2.0.html and MIT:https://spdx.org/licenses/MIT.html have SPDX identifiers and are on that list.
Kimi K3 meets the first definition and not the second.
The license text:https://huggingface.co/moonshotai/Kimi-K3/blob/main/LICENSE 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.
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.
The figures below are from the Hugging Face model card:https://huggingface.co/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:https://recipes.vllm.ai/moonshotai/Kimi-K3, SGLang:https://docs.sglang.io/cookbook/autoregressive/Moonshotai/Kimi-K3, and TokenSpeed:https://lightseek.org/tokenspeed/recipes/models#kimi-k3. 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.
The model ID is moonshotai/kimi-k3 . The catalog record on 2026-09-11 listed these properties.
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:https://openrouter.ai/moonshotai/kimi-k3 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:https://openrouter.ai/docs/guides/routing/provider-selection for the full set of routing controls.
Kimi K3 returns reasoning by default. Through our API you control it with the reasoning object:https://openrouter.ai/docs/guides/best-practices/reasoning-tokens. 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:https://openrouter.ai/docs/guides/best-practices/reasoning-tokens#preserving-reasoning.
This request sends an image and a question, asks for high reasoning effort, and prints the answer. It uses the TypeScript SDK:https://openrouter.ai/docs/client-sdks/typescript.
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:https://openrouter.ai/docs/guides/overview/multimodal/image-understanding and video input in video input:https://openrouter.ai/docs/guides/overview/multimodal/videos.
The model record lists tools , tool_choice , response_format , and structured_outputs . Tool definitions follow the shape in tool calling:https://openrouter.ai/docs/guides/features/tool-calling. JSON Schema responses follow structured outputs:https://openrouter.ai/docs/guides/features/structured-outputs. Because support for these parameters varies by endpoint, set provider.require_parameters to true when the request depends on them.
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:https://openrouter.ai/docs/guides/best-practices/prompt-caching for how caching works per provider.
Kimi K2:https://huggingface.co/moonshotai/Kimi-K2-Instruct/blob/main/LICENSE and Kimi K2.5:https://huggingface.co/moonshotai/Kimi-K2.5/blob/main/LICENSE 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.
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.
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.
Yes. The checkpoint is published at moonshotai/Kimi-K3:https://huggingface.co/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.
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.
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:https://openrouter.ai/moonshotai/kimi-k3 for the current rates.
Model usage data, product updates, and research reports. One email each week.