GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.
from openai import OpenAI
client = OpenAI(
api_key="$CK_KEY",
base_url="https://conduit-api.aurixel.ai/v1",
)
resp = client.chat.completions.create(
model="gpt-5.4-mini",
messages=[{"role": "user", "content": "Hi!"}],
)
print(resp.choices[0].message.content)Reasoning effort supported
Append -low / -medium / -high / -xhigh to the model name and the gateway sets the reasoning_effort parameter automatically.