Instructions to use deepseek-ai/DeepSeek-V3.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-V3.2 with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V3.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V3.2", dtype="auto")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use deepseek-ai/DeepSeek-V3.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-V3.2"
# 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-V3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-V3.2

SGLang

How to use deepseek-ai/DeepSeek-V3.2 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-V3.2" \
    --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-V3.2",
		"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-V3.2" \
        --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-V3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-V3.2 with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-V3.2
```

Fail to access DeepSeek-V3.2 through Claude Code

by tttggc - opened Dec 1, 2025

Discussion

tttggc

Dec 1, 2025

•

edited Dec 1, 2025

I try to use this amazing model in Claude Code. However, it seems that the base url as official website offers: https://api.deepseek.com/v3.2_speciale_expires_on_20251215 is wrong. I get error code: API Error: 404 status code (no body). This is my Claude Code configuration:

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.deepseek.com/v3.2_speciale_expires_on_20251215",
    "ANTHROPIC_AUTH_TOKEN": "${My key}",
    "API_TIMEOUT_MS": "3000000",
    "CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": "1",
    "ANTHROPIC_MODEL": "deepseek-reasoner",
    "ANTHROPIC_SMALL_FAST_MODEL": "deepseek-reasoner",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "deepseek-reasoner",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "deepseek-reasoner",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "deepseek-reasoner"
  },
  "enabledPlugins": {
    "document-skills@anthropic-agent-skills": true
  }
}

How can I fix it. I can't wait to experience it in Claude Code.

DingzhenPearl

Dec 1, 2025

v3.2_speciale is tuned just for reasoning, not agentic work

xiezirock

Dec 1, 2025

{
"env": {
"ANTHROPIC_AUTH_TOKEN": "sk-key",
"ANTHROPIC_BASE_URL": "https://api.deepseek.com/anthropic",
"ANTHROPIC_DEFAULT_HAIKU_MODEL": "deepseek-reasoner",
"ANTHROPIC_DEFAULT_OPUS_MODEL": "deepseek-reasoner",
"ANTHROPIC_DEFAULT_SONNET_MODEL": "deepseek-reasoner",
"ANTHROPIC_MODEL": "deepseek-reasoner",
"CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": 1
}
} this will work.

observerw

Dec 2, 2025

The v3.2_speciale_expires_on_20251215 endpoint is an OpenAI-format endpoint, so it cannot be used by claude code.

You can use https://api.deepseek.com/anthropic for claude-compatible endpoint, but it can only access DeepSeek-V3.2 model, not DeepSeek-V3.2-Speciale.

blueflamecome

Mar 17

url:https://api.deepseek.com/anthropic

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