OpenAI Python SDK - SnapGen

Install the official SDK.

pip install openai

Set base_url to the SnapGen OpenAI-compatible endpoint.

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxx",
    base_url="https://api.snapgen.org/v1",
)

response = client.chat.completions.create(
    model="gpt-6.1-sol",
    messages=[
        {"role": "user", "content": "Give me one API reliability tip."}
    ],
)

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

To stream, pass stream=True and iterate over the returned events.

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxx",
    base_url="https://api.snapgen.org/v1",
)

stream = client.chat.completions.create(
    model="gpt-6.1-sol",
    messages=[{"role": "user", "content": "Say hello in three words."}],
    stream=True,
)

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

Use Responses

The same client supports Responses:

response = client.responses.create(
    model="gpt-6.1-sol",
    input="Give me one API reliability tip.",
    reasoning={"effort": "medium"},
    max_output_tokens=2048,
)

print(response.output_text)

See Chat Completions and Responses for request options, streaming, and tools.