Last refreshed 2026-10-17. Next refresh: weekly.
Why use Nemotron 3 Ultra on Fireworks AI?
Fireworks AI offers Nemotron 3 Ultra with pay-as-you-go pricing at $0.60/1M input tokens. Fireworks AI offers a generative AI platform as a service, focusing on rapid product iteration and cost-efficient AI deployment.
Compare Nemotron 3 Ultra across 8 providers to find the best fit for your use caseInput / 1M
$0.60
Output / 1M
$2.40
Cache
read $0.12
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install openaiAuth
export FIREWORKS_API_KEY=...Call
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["FIREWORKS_API_KEY"],Model ID
accounts/fireworks/models/nemotron-3-ultra-nvfp4Request example
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)Gotchas
- Use provider model ID "accounts/fireworks/models/nemotron-3-ultra-nvfp4", not the LLMReference slug "nemotron-3-ultra".
- Fireworks model IDs use "accounts/fireworks/models/{model-name}" format, e.g. "accounts/fireworks/models/llama4-scout-instruct-basic" or "accounts/fireworks/models/deepseek-r1".
- The examples expect FIREWORKS_API_KEY; rename it only if your application config maps the new variable.
Compare Nemotron 3 Ultra Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| OpenRouter | — | — |
| DeepInfra | $0.50 | $2.20 |
| Baseten API | $0.60 | $2.40 |
| Venice AI | $0.63 | $3.13 |
| Fireworks AI | $0.60 | $2.40 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.60 |
| Output tokens | $2.40 |
Capabilities
ReasoningJSON / Tool use
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.
Get Started
Model Specs
Released2026-06-04
Parameters550B
Context1M
ArchitectureMixture of Experts