Phala: Qwen3.8 27B Uncensored (Aggressive) is a efficient model from Phala with a 262K context window, supporting advanced reasoning. Priced at $0.000300/1K input, $0.0015/1K output.
Total Requests
12
Success Rate
100%
P50 Latency
43665ms
P95 Latency
728326ms
Selection Rate
0.0%
of eligible requests
Intelligence Score
45/100
from openai import OpenAI
client = OpenAI(
base_url="https://api.antbase.ai/v1",
api_key="YOUR_ANT_API_KEY",
)
response = client.chat.completions.create(
model="phala/phala/qwen3.8-27b-uncensored",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)