Connect your tools
Python SDK
Practical guidance for using NeonAPI.
Install and configure
python -m pip install openai
export NEON_API_KEY="YOUR_API_KEY"Chat Completions
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["NEON_API_KEY"],
base_url="https://neon-api.com/v1",
)
result = client.chat.completions.create(
model="YOUR_MODEL_ID",
messages=[{"role": "user", "content": "Hello"}],
)
print(result.choices[0].message.content)Responses
For a model that supports Responses, use the same client and call client.responses.create(model="YOUR_MODEL_ID", input="Hello"). Read result.output_text from the returned response.
Set an application timeout appropriate to the model. Inspect the SDK's retry configuration before adding another retry loop, especially for billable generation requests.