Instructions to use moonshotai/Kimi-K3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use moonshotai/Kimi-K3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="moonshotai/Kimi-K3", trust_remote_code=True) messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("moonshotai/Kimi-K3", trust_remote_code=True, device_map="auto") - Inference
- HuggingChat
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use moonshotai/Kimi-K3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "moonshotai/Kimi-K3" # 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", "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
- SGLang
How to use moonshotai/Kimi-K3 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" \ --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", "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" \ --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", "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 with Docker Model Runner:
docker model run hf.co/moonshotai/Kimi-K3
Should I cancel my Claude subscription?
Yes
No, a $200 Claude Max subscription allows you usage limits that would cost up to $8.000 in API credits. No chinese model can compete with that amount of subsidization.
No, a $200 Claude Max subscription allows you usage limits that would cost up to $8.000 in API credits. No chinese model can compete with that amount of subsidization.
The "$8,000 value" is price-anchoring based on Anthropic’s monopoly over their own API insanely high and seriously NOT WORTH IT pricing. Even with a $200/month Max sub, you still hit strict 5-hour sliding windows and a 50% weekly cap on models like Fable which is the model that Kimi k3 aims to trade blows with.
Furthermore, because Chinese models like GLM, DeepSeek and Moonshot frequently release open weights, third-party hosting providers compete aggressively for the API users, driving API prices down toward raw compute cost. The token volume that costs $8,000 on Claude’s proprietary API can cost ~$250–$300 on competing open-weight infrastructure. Not to mention it gets cheaper over time as seen with deepseek v4 models and GLM 5.2.
(attached GLM 5.2 pricing example, originally $4.40 per million output tokens.)
No, a $200 Claude Max subscription allows you usage limits that would cost up to $8.000 in API credits. No chinese model can compete with that amount of subsidization.
The "$8,000 value" is price-anchoring based on Anthropic’s monopoly over their own API insanely high and seriously NOT WORTH IT pricing. Even with a $200/month Max sub, you still hit strict 5-hour sliding windows and a 50% weekly cap on models like Fable which is the model that Kimi k3 aims to trade blows with.
Furthermore, because Chinese models like GLM, DeepSeek and Moonshot frequently release open weights, third-party hosting providers compete aggressively for the API users, driving API prices down toward raw compute cost. The token volume that costs $8,000 on Claude’s proprietary API can cost ~$250–$300 on competing open-weight infrastructure. Not to mention it gets cheaper over time as seen with deepseek v4 models and GLM 5.2.
(attached GLM 5.2 pricing example, originally $4.40 per million output tokens.)
cope
your math doesnt make any sense.
the open weight infrastructure kimi k3 cost isnt even half of official kimi k3 pricing yet you claim an imaginary 40x cheaper price.
also interesting how you just created an account to defend this chinese model here.
