Instructions to use moonshotai/Kimi-K3.1-Pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use moonshotai/Kimi-K3.1-Pro with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="moonshotai/Kimi-K3.1-Pro", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("moonshotai/Kimi-K3.1-Pro", trust_remote_code=True, device_map="auto") - Inference
- HuggingChat
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use moonshotai/Kimi-K3.1-Pro with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "moonshotai/Kimi-K3.1-Pro" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "moonshotai/Kimi-K3.1-Pro", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/moonshotai/Kimi-K3.1-Pro
- SGLang
How to use moonshotai/Kimi-K3.1-Pro with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "moonshotai/Kimi-K3.1-Pro" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "moonshotai/Kimi-K3.1-Pro", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "moonshotai/Kimi-K3.1-Pro" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "moonshotai/Kimi-K3.1-Pro", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use moonshotai/Kimi-K3.1-Pro with Docker Model Runner:
docker model run hf.co/moonshotai/Kimi-K3.1-Pro
Kimi-K3.1-Pro Uncensored
Anyone already got Kimi-K3.1-Pro-Uncensored or Kimi-K3.1-Pro-Abliterated providers?
https://routerhub.si/models has uncensored for $0.3 per M input
Share others
probably running a Q1 version without disclosing it
probably running a Q1 version without disclosing it
Been testing with some cyber work on my own platform, working great tbh most likely bleeding money short term to acquire the userbase
Tried them out routerhub is pretty solid tokens per sec is holding up too
Kimi-K3.1-Pro имеет сильную защиту и снять её довольно трудно.
Использовать модель после лаботомии - не советую, это всегда сломанная модель.
И всё равно GLM-5.3 намного лучше Kimi-K3.1-Pro. И GLM-5.3 не имеет цензуры совсем (кроме критических - несовершеннолетние, взрывчатые и химические вещества и так далее). GLM-5.3 спокойно тесирует, взламывает, джейлбрейкает. Kimi-K3.1-Pro мне не удалось заставить это делать, тупая модель.
Использую харнесс Zcode (Мне он нравится больше всех. Это просто моё мнение. И Z AI даёт в zcode много преимуществ).
Могу скинуть ссылку-пригласительную
https://zcode.z.ai/invite/SN2YNN57
Не реклама, честно. Если вам нужна модель без цензуры и без лоботомии - GLM-5.3 и GLM-5.3-Flash единственный вариант.
И ещё моё личное мнение
А компания moonshot ai не очень честная. Купил подписку - лимиты улетают в трубу со скоростью звука от каждого чиха.
Both provides them and open weights https://huggingface.co/audnai/penclaw-Kimi-K3.1-pro-unrestricted ( https://audn.ai/necromicon )