Python SDK Integration

When using the official OpenAI Python SDK, simply replace api_key, base_url, and model with CoreRouter information.

Installation

pip install openai

To read environment variables from a .env file, additionally install:

pip install python-dotenv

Basic Usage

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ["COREROUTER_API_KEY"],
    base_url="https://api.corerouter.cloud/v1",
)

completion = client.chat.completions.create(
    model="claude-sonnet-4-5",
    messages=[
        {"role": "user", "content": "Hello, please introduce yourself."}
    ],
)

print(completion.choices[0].message.content)

Streaming Output

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ["COREROUTER_API_KEY"],
    base_url="https://api.corerouter.cloud/v1",
)

stream = client.chat.completions.create(
    model="claude-sonnet-4-5",
    messages=[{"role": "user", "content": "Introduce CoreRouter in three sentences."}],
    stream=True,
)

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

Multi-Turn Conversation

messages = [
    {"role": "user", "content": "Hello"},
]

completion = client.chat.completions.create(
    model="claude-sonnet-4-5",
    messages=messages,
)

messages.append({
    "role": "assistant",
    "content": completion.choices[0].message.content,
})
messages.append({"role": "user", "content": "Please write a Python hello function."})

completion = client.chat.completions.create(
    model="claude-sonnet-4-5",
    messages=messages,
)

print(completion.choices[0].message.content)

Tool Calling

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get weather information for a specified city",
            "parameters": {
                "type": "object",
                "properties": {
                    "city": {"type": "string", "description": "City name"}
                },
                "required": ["city"],
            },
        },
    }
]

completion = client.chat.completions.create(
    model="claude-sonnet-4-5",
    messages=[{"role": "user", "content": "What's the weather like in Beijing?"}],
    tools=tools,
)

tool_calls = completion.choices[0].message.tool_calls
if tool_calls:
    print(tool_calls[0].function.name)
    print(tool_calls[0].function.arguments)

Tool calling availability depends on model capabilities. For Agents or coding tools, prioritize models marked as supporting Tool Calling / Coding Agent in the console.

Vision Understanding

completion = client.chat.completions.create(
    model="claude-sonnet-4-5",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {"url": "https://example.com/image.jpg"},
                },
            ],
        }
    ],
)

print(completion.choices[0].message.content)

Responses API

This example requires the Model ID to support Responses. Regular chat models may not work. If the current SDK doesn't have client.responses, upgrade the openai package first, or call directly following Responses API curl examples.

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ["COREROUTER_API_KEY"],
    base_url="https://api.corerouter.cloud/v1",
)

response = client.responses.create(
    model="responses-model-id",
    input="Introduce CoreRouter in three sentences.",
)

print(response.output_text)

Embeddings

result = client.embeddings.create(
    model="embedding-model-id",
    input=["First text segment", "Second text segment"],
)

print(len(result.data[0].embedding))

Using .env

Python doesn't automatically read .env files. You can either set Keys in system environment variables or use python-dotenv.

.env example:

COREROUTER_API_KEY=sk-xxxxxxxxxxxxxxxx
COREROUTER_BASE_URL=https://api.corerouter.cloud/v1
COREROUTER_MODEL=claude-sonnet-4-5

Code example:

from dotenv import load_dotenv
from openai import OpenAI
import os

load_dotenv()

client = OpenAI(
    api_key=os.environ["COREROUTER_API_KEY"],
    base_url=os.environ.get("COREROUTER_BASE_URL", "https://api.corerouter.cloud/v1"),
)

completion = client.chat.completions.create(
    model=os.environ.get("COREROUTER_MODEL", "claude-sonnet-4-5"),
    messages=[{"role": "user", "content": "Hello"}],
)

print(completion.choices[0].message.content)

Add .env to .gitignore; don't commit API Keys to repositories.

Error Handling

from openai import APIError, AuthenticationError, OpenAI
import os

client = OpenAI(
    api_key=os.environ["COREROUTER_API_KEY"],
    base_url="https://api.corerouter.cloud/v1",
)

try:
    completion = client.chat.completions.create(
        model="claude-sonnet-4-5",
        messages=[{"role": "user", "content": "Hello"}],
    )
    print(completion.choices[0].message.content)
except AuthenticationError:
    print("Invalid API Key, check Authorization configuration.")
except APIError as exc:
    print(f"API request failed: {exc.status_code} {exc.message}")