Get started

Quickstart

Send your first OpenAI-compatible request to an InferX endpoint.

Before you begin

Sign in to the InferX Console and open the endpoint or model you want to use. Copy the API Base URL, Model Name, and API Key shown in Client Setup.

Send a request

InferX uses the OpenAI-compatible client interface. Install the standard Python client, set your API key, and point the client to InferX.

shell

pip install openai

inference.py

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["INFERX_API_KEY"],
    base_url="https://model.inferx.net/v1",
)

stream = client.chat.completions.create(
    model="YOUR_MODEL_ID",
    messages=[{"role": "user", "content": "Hello, InferX."}],
    stream=True,
)

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

Next steps

Understand endpoint setup →Deploy a model in the Console →Browse published models →