OpenAI SDK · Python / TS
Use Chat Completions with /v1 in the Base URL.
Prepare
Set the environment variables and select a model supporting Chat Completions. Use https://api.neatrouter.com/v1 as Base URL without adding /chat/completions yourself.
Python
python -m pip install openaiimport os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["RELAY_API_KEY"],
base_url="https://api.neatrouter.com/v1",
)
response = client.chat.completions.create(
model=os.environ["RELAY_MODEL_ID"],
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)TypeScript
npm install openaiimport OpenAI from 'openai';
const client = new OpenAI({
apiKey: process.env.RELAY_API_KEY,
baseURL: "https://api.neatrouter.com/v1",
});
const response = await client.chat.completions.create({
model: process.env.RELAY_MODEL_ID!,
messages: [{ role: 'user', content: 'Hello' }],
});
console.log(response.choices[0].message.content);Select the protocol
These examples use Chat Completions. Responses is a separate protocol; confirm model and route support first. A method in the SDK does not establish platform availability. Keep the key on your server.
See the official Python and TypeScript SDK documentation.
Still have a question?
Support details have not been published.