Fw Nemotron 3 Ultra
FW-Nemotron-3-Ultra-NVFP4Pricing
List prices at Azure AI Foundry, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.66 | $2.64 | |
| Cached input 80% off input | $0.13 | 80% off input |
What it costs a month
At Azure AI Foundry list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$348
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$285
- Coding agent1,000 requests a day, 40K in / 2K out, cached$505
- Overnight batch20,000 requests a day, 4K in / 0.4K out$2,218
Where to run it
1 host serve Fw Nemotron 3 Ultra. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Azure AI FoundryCloud FW-Nemotron-3-Ultra-NVFP4 | $0.66 / $2.64 | FW-Nemotron-3-Ultra-NVFP4 |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Features
- Prompt caching
- Open weights
- License: NVIDIA Open Model LicenseRuntimes: TGI, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Azure AI Foundry.
Smaller NVIDIA models
No cheaper NVIDIA model keeps its key capabilities.
Other frontier labs
- 26% less
- 60% less
- 83% less
- 83% less
Open-weight picks
- 24% less
- 26% less
- 31% less
- 41% less
Call it
Using Azure AI Foundry's API.
from litellm import completion
response = completion(
model="azure_ai/FW-Nemotron-3-Ultra-NVFP4",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Fw Nemotron 3 Ultra cost?
On Azure AI Foundry, Fw Nemotron 3 Ultra costs $0.66 per million input tokens and $2.64 per million output tokens. Cached input costs $0.13 per million tokens.
Which APIs offer Fw Nemotron 3 Ultra?
Fw Nemotron 3 Ultra runs on 1 API: Azure AI Foundry.
What is Fw Nemotron 3 Ultra's context window?
262K tokens, with up to 262K tokens in one reply.
Is Fw Nemotron 3 Ultra being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Fw Nemotron 3 Ultra?
Models that cost less and keep most of what it can do: Gemini 3.5 Flash Lite on Google AI Studio (26% less), GPT-5.4 Nano on OpenAI (60% less) and Motif 3 on ai& (24% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Fw Nemotron 3 Ultra's API model id?
Use FW-Nemotron-3-Ultra-NVFP4 with Azure AI Foundry.
Sources
Raw catalog entry for FW-Nemotron-3-Ultra-NVFP4 on Azure AI Foundry
{
"cache_read_input_token_cost": 1.3e-7,
"input_cost_per_token": 6.6e-7,
"litellm_provider": "azure_ai",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 0.00000264,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supported_modalities": [
"text"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_pdf_input": false,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
}