Python SDK

SDKMAX is fully OpenAI-compatible, so you can use the official openai Python package directly — no separate SDKMAX SDK needed.

Install

pip install openai

Initialize the client

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-key",          # created in the SDKMAX console
    base_url="https://api.sdkmax.com/v1",
)

Prefer environment variables

export OPENAI_API_KEY="sk-your-key"
export OPENAI_BASE_URL="https://api.sdkmax.com/v1"

With these set, client = OpenAI() works with no hardcoded secrets.

Chat completions

resp = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain SDKMAX's core capabilities."},
    ],
)
print(resp.choices[0].message.content)

Streaming

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Write a short poem about an AI gateway."}],
    stream=True,
)
for chunk in stream:
    delta = chunk.choices[0].delta.content or ""
    print(delta, end="", flush=True)

Switching models

Just change the model parameter — everything else stays the same:

for model in ["gpt-4o", "claude-opus-4-8", "deepseek-chat"]:
    resp = client.chat.completions.create(
        model=model,
        messages=[{"role": "user", "content": "What's 1+1?"}],
    )
    print(model, "->", resp.choices[0].message.content)

Embeddings

resp = client.embeddings.create(
    model="text-embedding-3-small",
    input="SDKMAX is an enterprise AI gateway",
)
print(len(resp.data[0].embedding))

Generating images

resp = client.images.generate(
    model="dall-e-3",
    prompt="A cat riding a motorcycle through a cyberpunk city",
    size="1024x1024",
)
print(resp.data[0].url)

See Images API.

Error handling

The openai library maps SDKMAX's 4xx/5xx responses to the corresponding exception types:

from openai import APIStatusError, RateLimitError

try:
    client.chat.completions.create(model="gpt-4o", messages=[...])
except RateLimitError:
    # 429: quota exhausted or rate-limited — back off and retry
    ...
except APIStatusError as e:
    # any other 4xx/5xx; e.status_code / e.message help with debugging
    print(e.status_code, e.message)

Full error code reference: Error Codes.

Async usage

import asyncio
from openai import AsyncOpenAI

client = AsyncOpenAI(api_key="sk-your-key", base_url="https://api.sdkmax.com/v1")

async def main():
    resp = await client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": "Hello"}],
    )
    print(resp.choices[0].message.content)

asyncio.run(main())