Skip to main content
The official OpenAI SDK is designed to allow overriding base_url, so it is fully compatible with OpenPAI — no need to swap libraries.

​
Python

pip install openai

from openai import OpenAI

client = OpenAI(
    api_key="sk-XXXXXXXXXXXXXXXX",
    base_url="https://openp.ai/v1",
)

# Chat
resp = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{"role": "user", "content": "hello"}],
)

# Streaming
stream = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{"role": "user", "content": "tell a story"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

# Embeddings
emb = client.embeddings.create(
    model="text-embedding-3-small",
    input=["hello world"],
)

# Image generation
img = client.images.generate(
    model="dall-e-3",
    prompt="a panda",
    size="1024x1024",
)

​
Node.js / TypeScript

npm install openai

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPENPAI_API_KEY!,
  baseURL: "https://openp.ai/v1",
});

const resp = await client.chat.completions.create({
  model: "gpt-5.5",
  messages: [{ role: "user", content: "hello" }],
});

​
Go

github.com/sashabaranov/go-openai: 
import "github.com/sashabaranov/go-openai"

cfg := openai.DefaultConfig("sk-XXXXXXXXXXXXXXXX")
cfg.BaseURL = "https://openp.ai/v1"
client := openai.NewClientWithConfig(cfg)

resp, _ := client.CreateChatCompletion(ctx,
    openai.ChatCompletionRequest{
        Model: "gpt-5.5",
        Messages: []openai.ChatCompletionMessage{
            {Role: openai.ChatMessageRoleUser, Content: "hello"},
        },
    })

​
Java

com.openai:openai-java: 
import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .apiKey(System.getenv("OPENPAI_API_KEY"))
    .baseUrl("https://openp.ai/v1")
    .build();

​
Environment variables

The OpenAI SDK reads the following environment variables by default — configuring via environment variables is recommended: 
export OPENAI_API_KEY=sk-XXXXXXXXXXXXXXXX
export OPENAI_BASE_URL=https://openp.ai/v1
Then your code needs no explicit arguments: 
from openai import OpenAI
client = OpenAI()  # reads the environment variables automatically

​
Notes

  • Timeouts: long-context / reasoning models may require raising the client timeout to 5-10 minutes.
  • Retries: OpenPAI already retries upstream failures at the gateway, so the client can disable its own retries (max_retries=0) or keep them as a fallback.
  • Beta features: whether certain OpenAI Beta endpoints (Assistants API, Threads) are supported is subject to console announcements.