DeepSeek V4 Pro is a efficient model from Featherless with a 262K context window. Available through ANT's unified API.
Total Requests
810
Success Rate
15.31%
P50 Latency
1481ms
P95 Latency
179375ms
Selection Rate
4.2%
of eligible requests
Intelligence Score
54/100
ANT selects DeepSeek V4 Pro for 4.2% of eligible requests with a median response time of 1481ms.
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="featherless/deepseek-ai/DeepSeek-V4-Pro",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)