nvidia/nemotron-3-nano-30b-a3b

$0.05

Input / 1M

$0.20

Output / 1M

262K

Context

—

Speed

Capabilities

json_modetools

Use nemotron-3-nano-30b-a3b via Relay

Configure the model alias in YAML, then call it from Python.

YAML

# models.yaml
version: 1
models:
  nemotron:
    target: nvidia/nemotron-3-nano-30b-a3b
    credential: $env.NVIDIA_API_KEY

Python

from relay import Hub

async with Hub.from_yaml("models.yaml") as hub:
    resp = await hub.chat(
        "nemotron",
        messages=[{"role": "user", "content": "Hello"}],
    )
    print(resp.text, resp.cost_usd)

pip install ai5labs-relay · full docs on GitHub

Compare with

vs groq/llama-3.3-70b-versatile vs anthropic/claude-haiku-4-5 vs mistral/mistral-large-latest vs openai/gpt-4o-mini