Loading…
Loading…
NVIDIA Nemotron 3 Super is a hybrid MoE model with leading accuracy for multi-agent applications and specialized agentic AI systems. By NVIDIA, on GridPup at $0.60 per million input tokens and $1.81 per million output tokens, paid from your GridPup balance per request. No subscription.
| A 1,000-word answer to a 200-word question | $0.0026 |
|---|---|
| 1,000 such answers | $2.58 |
| Summarising a 50-page document (25,000 words) in 500 words | $0.021 |
GridPup's API speaks OpenAI's format: use any OpenAI SDK with the base URL https://api.gridpup.com/v1/ai and a GridPup API key with Also use AI models. The answer tells you what it cost. More in the API docs.
from openai import OpenAI
client = OpenAI(base_url="https://api.gridpup.com/v1/ai", api_key="gp_live_…")
r = client.chat.completions.create(
model="@cf/nvidia/nemotron-3-120b-a12b",
messages=[{"role": "user", "content": "Explain a KV cache in two sentences."}],
)
print(r.choices[0].message.content)
print("cost:", r.usage.cost_usd, "USD")base_url to https://api.gridpup.com/v1/ai and the model to @cf/nvidia/nemotron-3-120b-a12b.