OpenAI SDK

The official OpenAI SDK can call OpenModel's Responses API through client.responses.create. This guide covers only the Responses protocol; OpenModel does not provide the Chat Completions API or other OpenAI API endpoints.

Installation

pip install openai

Configuration

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.openmodel.ai/v1",
    api_key="om-your-api-key",
)

Node.js

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://api.openmodel.ai/v1",
  apiKey: "om-your-api-key",
})

Environment Variables

You can also configure the SDK using environment variables, which keeps credentials out of your source code:

export OPENAI_BASE_URL="https://api.openmodel.ai/v1"
export OPENAI_API_KEY="om-your-api-key"

Then initialize the client without explicit parameters:

from openai import OpenAI

client = OpenAI()  # Reads from environment variables

Model Names

Choose a model from the dynamic model data in the Console and make sure its supported_protocols includes responses. Use the model name exactly as shown. For example:

gpt-5.4

Examples

Basic Response

from openai import OpenAI

client = OpenAI(
    base_url="https://api.openmodel.ai/v1",
    api_key="om-your-api-key",
)

response = client.responses.create(
    model="gpt-5.4",
    input="Explain quantum computing in simple terms.",
)

print(response.output_text)

Streaming

from openai import OpenAI

client = OpenAI(
    base_url="https://api.openmodel.ai/v1",
    api_key="om-your-api-key",
)

stream = client.responses.create(
    model="gpt-5.4",
    input="Write a short story about a robot learning to paint.",
    stream=True,
)

for event in stream:
    if hasattr(event, "delta") and event.delta:
        print(event.delta, end="", flush=True)
print()

Multi-Turn Conversation

from openai import OpenAI

client = OpenAI(
    base_url="https://api.openmodel.ai/v1",
    api_key="om-your-api-key",
)

response = client.responses.create(
    model="gpt-5.4",
    instructions="You are a helpful math tutor.",
    input=[
        {
            "role": "user",
            "content": "What is the derivative of x^3?",
        },
        {
            "role": "assistant",
            "content": "The derivative of x^3 is 3x^2.",
        },
        {
            "role": "user",
            "content": "What about the integral?",
        },
    ],
)

print(response.output_text)

Tool Use (Function Calling)

from openai import OpenAI

client = OpenAI(
    base_url="https://api.openmodel.ai/v1",
    api_key="om-your-api-key",
)

tools = [
    {
        "type": "function",
        "name": "get_weather",
        "description": "Get the current weather for a location.",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "City and country, e.g. 'Tokyo, Japan'",
                },
            },
            "required": ["location"],
        },
    },
]

response = client.responses.create(
    model="gpt-5.4",
    input="What's the weather like in San Francisco?",
    tools=tools,
)

for item in response.output:
    if item.type == "function_call":
        print(f"Function: {item.name}")
        print(f"Arguments: {item.arguments}")

Async Usage (Python)

import asyncio
from openai import AsyncOpenAI

client = AsyncOpenAI(
    base_url="https://api.openmodel.ai/v1",
    api_key="om-your-api-key",
)

async def main():
    response = await client.responses.create(
        model="gpt-5.4",
        input="Hello!",
    )
    print(response.output_text)

asyncio.run(main())

Error Handling

The OpenAI SDK raises typed exceptions that you can catch and handle:

from openai import OpenAI, APIConnectionError, APIStatusError, APITimeoutError

client = OpenAI(
    base_url="https://api.openmodel.ai/v1",
    api_key="om-your-api-key",
)

try:
    response = client.responses.create(
        model="gpt-5.4",
        input="Hello!",
    )
except APIConnectionError:
    print("Connection failed. Check your network.")
except APITimeoutError:
    print("Request timed out.")
except APIStatusError as e:
    print(f"API error {e.status_code}: {e.message}")

For comprehensive error handling patterns, see Error Handling.

Next Steps

Streaming — Real-time streaming responses
Error Handling — Robust error handling patterns
Rate Limits — Understanding and handling rate limits
API Reference — Complete Responses API documentation

OpenAI SDK

On this page