Connect Your AI Application

Replace YOUR_API_ENDPOINT with the endpoint from your Dashboard.

python

from openai import OpenAI

client = OpenAI(
    base_url="YOUR_API_ENDPOINT",  # Copy from Dashboard
    api_key="not-needed"
)

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3-0324",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

tips_and_updatesTips

checkThe API is OpenAI-compatible — any library that works with OpenAI will work with your GPU endpoint.
checkNo API key is needed for self-hosted models. Set api_key="not-needed".
checkYou can serve multiple agents from a single GPU endpoint simultaneously.
checkUse the Web Terminal in Dashboard if you need to customize the deployment.

Need help?

Documentation Contact Support