NVIDIA: Nemotron 3 Ultra (free) is a efficient model from OpenRouter with a 1M context window, supporting function calling. Available for free through ANT routing.
Total Requests
8
Success Rate
100%
P50 Latency
9595ms
P95 Latency
56443ms
Selection Rate
0.2%
of eligible requests
Intelligence Score
49/100
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="nvidia/nemotron-3-ultra-550b-a55b:free",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)