Following the tutorial on , instead of waiting the whole reasoning to be completed, you can stream intermediate tokens.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.activeloop.ai/",
api_key=os.getenv('ACTIVELOOP_TOKEN')
)
stream = client.chat.completions.create(
model="activeloop-l0",
messages=[{"role": "user", "content": "what is the AIME score of DeepSeek R1?"}],
stream=True,
)
for event in stream:
print(event)