> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gpuhub.com/llms.txt
> Use this file to discover all available pages before exploring further.

# DeepSeek-V3.2

> Use DeepSeek-V3.2 through AI Gateway with an OpenAI-compatible chat completions API.

`DeepSeek-V3.2` is available through the OpenAI-compatible chat completions API. It is suitable for general chat, coding assistance, knowledge tasks, and application backends that need an OpenAI-compatible interface.

<Note>
  Create or copy your API key from the console before calling the API. Use the model unit price displayed in the console as the source of truth.
</Note>

## Endpoint

| Compatibility     | Base URL                        |
| ----------------- | ------------------------------- |
| OpenAI-compatible | `https://llm.gpuhub.com/api/v1` |

## curl

```bash theme={null}
curl --location --request POST "https://llm.gpuhub.com/api/v1/chat/completions" \
  --header "Authorization: Bearer $API_KEY" \
  --header "Content-Type: application/json" \
  --data-raw '{
    "model": "DeepSeek-V3.2",
    "messages": [
      {
        "role": "user",
        "content": "Hello! Please summarize the following technical document."
      }
    ],
    "stream": true
  }'
```

## Python

```python theme={null}
# Install the SDK first if needed:
# pip install openai

from openai import OpenAI

client = OpenAI(
    base_url="https://llm.gpuhub.com/api/v1",
    api_key="YOUR_API_KEY",
)

stream = client.chat.completions.create(
    model="DeepSeek-V3.2",
    messages=[
        {"role": "user", "content": "Hello! Please summarize the following technical document."}
    ],
    stream=True,
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")
```

## Use with Cherry Studio

To use this model in Cherry Studio, configure the matching provider type and add the model name shown on this page. See [Cherry Studio](/ai-gateway/ides-agents/cherry-studio) for setup details.