Using Nemotron 3 Ultra on Fireworks AI
Implementation guide · Nemotron 3 · NVIDIA AI
Fireworks AI exposes Nemotron 3 Ultra through model ID accounts/fireworks/models/nemotron-3-ultra-nvfp4. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-10-17. Next refresh: weekly.
Quick Start
- 1
- 2Use the Fireworks AI SDK or REST API to call
accounts/fireworks/models/nemotron-3-ultra-nvfp4— see the documentation for request format. - 3
Code Examples
pip install openaiFIREWORKS_API_KEYaccounts/fireworks/models/nemotron-3-ultra-nvfp4Fireworks model IDs use "accounts/fireworks/models/{model-name}" format, e.g. "accounts/fireworks/models/llama4-scout-instruct-basic" or "accounts/fireworks/models/deepseek-r1".
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["FIREWORKS_API_KEY"],
base_url="https://api.fireworks.ai/inference/v1"
)
response = client.chat.completions.create(
model="accounts/fireworks/models/nemotron-3-ultra-nvfp4",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Pricing on Fireworks AI
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.60 |
| Output tokens | $2.40 |
Capabilities
About Nemotron 3 Ultra
NVIDIA's open frontier-reasoning model (550B total / 55B active MoE, hybrid Transformer-Mamba). Highest Artificial Analysis Intelligence Index for any US open model (score: 48). 300+ tokens/second. 1M-token context. Announced at Computex 2026. Pricing: ~$0.60/$2.60 per 1M tokens (provider median); free tier on some providers.