{"slug": "kimi-k3-license", "title": "Kimi K3 License", "summary": "Moonshot AI has released Kimi-K3, an image-text-to-text model under a permissive license that allows use, modification, and commercial distribution, with support for Transformers, vLLM, SGLang, and Docker Model Runner. The model is available on Hugging Face and can be deployed via pipelines, direct loading, or containerized serving with OpenAI-compatible APIs.", "body_md": "Image-Text-to-Text\n\nTransformers\n\nSafetensors\n\nkimi_k3\n\nfeature-extraction\n\ncompressed-tensors\n\ncustom_code\n\n### Instructions to use moonshotai/Kimi-K3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.\n\n- Libraries\n[Transformers](/moonshotai/Kimi-K3?library=transformers)How to use moonshotai/Kimi-K3 with Transformers:\n\n``` python\n# Use a pipeline as a high-level helper\nfrom transformers import pipeline\n\npipe = pipeline(\"image-text-to-text\", model=\"moonshotai/Kimi-K3\", trust_remote_code=True)\npython\n# Load model directly\nfrom transformers import AutoModel\nmodel = AutoModel.from_pretrained(\"moonshotai/Kimi-K3\", trust_remote_code=True, device_map=\"auto\")\n```\n\n- Notebooks\n[Google Colab](/moonshotai/Kimi-K3/colab)[Kaggle](/moonshotai/Kimi-K3/kaggle)- Local Apps\n[Settings](/settings/local-apps) [vLLM](/moonshotai/Kimi-K3?local-app=vllm)How to use moonshotai/Kimi-K3 with vLLM:\n\n##### Install from pip and serve model\n\n```\n# Install vLLM from pip:\npip install vllm\n# Start the vLLM server:\nvllm serve \"moonshotai/Kimi-K3\"\n# Call the server using curl (OpenAI-compatible API):\ncurl -X POST \"http://localhost:8000/v1/completions\" \\\n\t-H \"Content-Type: application/json\" \\\n\t--data '{\n\t\t\"model\": \"moonshotai/Kimi-K3\",\n\t\t\"prompt\": \"Once upon a time,\",\n\t\t\"max_tokens\": 512,\n\t\t\"temperature\": 0.5\n\t}'\n```\n\n##### Use Docker\n\n```\ndocker model run hf.co/moonshotai/Kimi-K3\n```\n\n[SGLang](/moonshotai/Kimi-K3?local-app=sglang)How to use moonshotai/Kimi-K3 with SGLang:\n\n##### Install from pip and serve model\n\n```\n# Install SGLang from pip:\npip install sglang\n# Start the SGLang server:\npython3 -m sglang.launch_server \\\n    --model-path \"moonshotai/Kimi-K3\" \\\n    --host 0.0.0.0 \\\n    --port 30000\n# Call the server using curl (OpenAI-compatible API):\ncurl -X POST \"http://localhost:30000/v1/completions\" \\\n\t-H \"Content-Type: application/json\" \\\n\t--data '{\n\t\t\"model\": \"moonshotai/Kimi-K3\",\n\t\t\"prompt\": \"Once upon a time,\",\n\t\t\"max_tokens\": 512,\n\t\t\"temperature\": 0.5\n\t}'\n```\n\n##### Use Docker images\n\n```\ndocker run --gpus all \\\n    --shm-size 32g \\\n    -p 30000:30000 \\\n    -v ~/.cache/huggingface:/root/.cache/huggingface \\\n    --env \"HF_TOKEN=<secret>\" \\\n    --ipc=host \\\n    lmsysorg/sglang:latest \\\n    python3 -m sglang.launch_server \\\n        --model-path \"moonshotai/Kimi-K3\" \\\n        --host 0.0.0.0 \\\n        --port 30000\n# Call the server using curl (OpenAI-compatible API):\ncurl -X POST \"http://localhost:30000/v1/completions\" \\\n\t-H \"Content-Type: application/json\" \\\n\t--data '{\n\t\t\"model\": \"moonshotai/Kimi-K3\",\n\t\t\"prompt\": \"Once upon a time,\",\n\t\t\"max_tokens\": 512,\n\t\t\"temperature\": 0.5\n\t}'\n```\n\n[Docker Model Runner](/moonshotai/Kimi-K3?local-app=docker-model-runner)How to use moonshotai/Kimi-K3 with Docker Model Runner:\n\n```\ndocker model run hf.co/moonshotai/Kimi-K3\n```\n\n| Kimi K3 License | |\n| Copyright (c) 2026 Moonshot AI | |\n| Permission is hereby granted, free of charge, to any person (the \"Licensee\") | |\n| obtaining a copy of this software — including the model weights, parameters, | |\n| configuration files, inference and training code, and associated documentation | |\n| (collectively, the \"Software\") — to deal in the Software without restriction. | |\n| This includes, without limitation, the rights to use, copy, modify, merge, | |\n| publish, distribute, sublicense, and/or sell copies of the Software; to run, | |\n| deploy, fine-tune, or otherwise modify the Software and create derivative works | |\n| from it; and to permit persons to whom the Software is furnished to do so, in | |\n| each case subject to the following conditions: | |\n| 1. The above copyright notice and this permission notice shall be included in | |\n| all copies or substantial portions of the Software. Licensee's use of the | |\n| Software must comply with applicable laws and regulations. | |\n| 2. \"Model as a Service\" means giving a third party access to language model | |\n| inference or fine-tuning (e.g., via API) in a manner that allows such third | |\n| party to exercise meaningful control over the inputs, parameters, or training | |\n| data. This does not include (a) end-user products with model capabilities solely | |\n| embedded within specific features or harnesses, or (b) mere relaying of requests | |\n| to models hosted by others. | |\n| If the Licensee or any of its affiliates operates a Model as a Service business, | |\n| and the aggregate revenue of the Licensee and its affiliates exceeds 20 million | |\n| US dollars (or the equivalent in other currencies) in total over any consecutive | |\n| 12 months, the Licensee must enter into a separate agreement with Moonshot AI | |\n| before using the Software or its derivative works for any commercial purpose. | |\n| 3. If the Software (or any derivative works thereof) is used for any of the | |\n| Licensee's commercial products or services that have more than 100 million | |\n| monthly active users, or more than 20 million US dollars (or equivalent in other | |\n| currencies) in monthly revenue, \"Kimi K3\" must be prominently displayed on the | |\n| user interface of such product or service. | |\n| 4. The requirements set forth in Sections 2 and 3 do not apply to: (a) internal | |\n| use of the Software, defined as any use that does not make the Software, its | |\n| outputs, or its underlying capabilities available to third parties; or (b) any | |\n| use of the Software accessed through Moonshot AI's official products or | |\n| certified inference partners. | |\n| 5. THE SOFTWARE AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” | |\n| BASIS, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT | |\n| LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE | |\n| AND NONINFRINGEMENT. IN NO EVENT SHALL MOONSHOT AI OR ITS AFFILIATES OR | |\n| COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER | |\n| IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN | |\n| CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. | |\n| For any questions regarding this license, please contact <license@moonshot.ai>. |", "url": "https://wpnews.pro/news/kimi-k3-license", "canonical_source": "https://huggingface.co/moonshotai/Kimi-K3/blob/main/LICENSE", "published_at": "2026-07-27 15:13:26+00:00", "updated_at": "2026-07-27 15:22:49.884093+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-tools", "ai-infrastructure"], "entities": ["Moonshot AI", "Kimi-K3", "Hugging Face", "Transformers", "vLLM", "SGLang", "Docker Model Runner"], "alternates": {"html": "https://wpnews.pro/news/kimi-k3-license", "markdown": "https://wpnews.pro/news/kimi-k3-license.md", "text": "https://wpnews.pro/news/kimi-k3-license.txt", "jsonld": "https://wpnews.pro/news/kimi-k3-license.jsonld"}}