Instructions to use deepseek-ai/DeepSeek-R1-0528 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-R1-0528 with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-R1-0528", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-R1-0528", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-0528", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/DeepSeek-R1-0528 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-R1-0528"
# 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-R1-0528",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-R1-0528

SGLang

How to use deepseek-ai/DeepSeek-R1-0528 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-R1-0528" \
    --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-R1-0528",
		"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-R1-0528" \
        --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-R1-0528",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-R1-0528 with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-R1-0528
```

When will it be available via API

#27

by alexcardo - opened May 29, 2025

Discussion

alexcardo

May 29, 2025

Why this model is not available via the DeepSeek API platform?

owenqwenllmwine

May 29, 2025

Is on https://llm.vin for free

alexcardo

May 29, 2025

•

edited May 29, 2025

I want to try it via an API call, not via chat interface. I was unable to find any API keys after registration. And I also have a balance on my DeepSeek account. I'd rather use it via the official API. But looks like this feature won't be available in the foreseeable future.

owenqwenllmwine

May 29, 2025

llm.vin has a API, https://docs.llm.vin (no API key required)

alexcardo

May 29, 2025

•

edited May 29, 2025

llm.vin has a API, https://docs.llm.vin (no API key required)

Correct me if I'm dumb, it doesn't work, even with examples provided in the official documentation. As for the API keys (if I still want them), I was unable to find this menu item in the interface.

alex@M1 ~ % curl "https://api.llm.vin/v1/chat/compilations"
-H "Content-Type: application/json"
-d '{
"model": "grok-3-mini",
"messages": [
{
"role": "user",
"content": "Write a one-sentence bedtime story about a unicorn."
}
]
}'

Error

Cannot POST /v1/chat/compilations

alex@M1 ~ %

No matter, which model I use, I see the same error.

By the way, it's suspicious to be true for free..., especially, when it comes to Grok (proprietary model)

owenqwenllmwine

May 29, 2025

It was a typo in the documentation and is being fixed.

curl "https://api.llm.vin/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-3-mini",
    "messages": [
      {
        "role": "user",
        "content": "Write a one-sentence bedtime story about a unicorn."
      }
    ]
  }'

alexcardo

May 29, 2025

It was a typo in the documentation and is being fixed.

curl "https://api.llm.vin/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-3-mini",
    "messages": [
      {
        "role": "user",
        "content": "Write a one-sentence bedtime story about a unicorn."
      }
    ]
  }'

OMG, it really works! Thank you! Are you involved with this project?

owenqwenllmwine

May 29, 2025

Yes I am, glad to see its working now!

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