Llama 3.3 70B (Venice) is a capable model from Venice with a 131K context window, supporting function calling. Priced at $0.000700/1K input, $0.0028/1K output.
Total Requests
1
P50 Latency
1713ms
P95 Latency
1713ms
Selection Rate
0.0%
of eligible requests
Intelligence Score
32/100
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="venice/llama-3.3-70b",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)