Instructions to use deepseek-ai/DeepSeek-V4-Pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-V4-Pro with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V4-Pro")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V4-Pro")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V4-Pro")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use deepseek-ai/DeepSeek-V4-Pro with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-V4-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": "deepseek-ai/DeepSeek-V4-Pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-V4-Pro

SGLang

How to use deepseek-ai/DeepSeek-V4-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 "deepseek-ai/DeepSeek-V4-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": "deepseek-ai/DeepSeek-V4-Pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "deepseek-ai/DeepSeek-V4-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": "deepseek-ai/DeepSeek-V4-Pro",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-V4-Pro with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-V4-Pro
```

ds现在真的是拉完了，全面落后

#90

by RealBar - opened 13 days ago

Discussion

RealBar

13 days ago

还在跟opus4.5比呢？现在可是26年了喂！

使用下来，实际效果全面落后kimi 2.6！！！！

现在无比期待kimi 3的发布

yswness

13 days ago

老哥别急，人家比的是opus 4.6

yiweigang

13 days ago

还在跟opus4.5比呢？现在可是26年了喂！

使用下来，实际效果全面落后kimi 2.6！！！！

现在无比期待kimi 3的发布

眼睛瞎了吗，人家比的明明是 Opus-4.6 Max

mactavish91

13 days ago

kimi就是营销比不过

FEIMENG

13 days ago

rage bait，别管它

basesssssp

13 days ago

🤡

2025carry

13 days ago

你有本事也拉一个

jackz990

13 days ago

所以你看文档没？

gabira

12 days ago

还在跟opus4.5比呢？现在可是26年了喂！

使用下来，实际效果全面落后kimi 2.6！！！！

现在无比期待kimi 3的发布

文档看不懂可以开网页翻译。
另，开源精神值得肯定。

Xxuanm

12 days ago

This comment has been hidden (marked as Off-Topic)

swz128

12 days ago

🤡

jianPro

12 days ago

怎么大模型圈也有你这种拉踩dog，滚回手机圈

luxiangyu

12 days ago

How can DeepSeek be considered behind? It's important to know that DeepSeek has always been focused on pursuing AGI, unlike Sam Altman who claims to pursue AGI but actually focuses on commercialization. Their aspirations are different.
Since the release of R1 in January 2025, DeepSeek has consistently contributed to the development of large models through open-source initiatives, continuously exploring the upper limits of large model capabilities from multiple dimensions.
As observers, let's not make superficial judgments.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment