impulse

Nemotron 3 Ultra

Open weights
API id nemotron-3-ultra-nvfp4
Input / 1M
$0.60
at Fireworks AI
Output / 1M
$2.40
at Fireworks AI
Context window
262K
tokens
Max output
33K
tokens per reply
Hosts
1
2 listings
Released
-
date not published

Pricing

List prices at Fireworks AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.60$2.40
Cached input
80% off input
$0.12
Priority
25% more
$0.75$3.00

What it costs a month

At Fireworks AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$317
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$259
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$461
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$2,016
Use your own numbers

Where to run it

1 host serve Nemotron 3 Ultra. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Fireworks AIInference
nemotron-3-ultra-nvfp4
$0.60 / $2.40
Show 1 more listings: regions, snapshots and variants
Fireworks AI
Alias
nemotron-3-ultra-nvfp4
$0.60 / $2.40

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
Open weights
License: NVIDIA Open Model License
Runtimes: 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 Fireworks AI.

Smaller NVIDIA models

No cheaper NVIDIA model keeps its key capabilities.

Other frontier labs

  • Gemini 3.5 Flash Lite
    Google · on Google AI Studio
    $0.30 / $2.50
    Has every key capability
    19% less
  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    56% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    81% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    81% less

Open-weight picks

  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    18% less
  • DeepSeek V4 Pro
    DeepSeek · on CLF AI Gateway
    $0.528 / $1.58
    Has every key capability
    25% less
  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    35% less
  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    39% less

Call it

Using Fireworks AI's API.

Python
from litellm import completion

response = completion(
    model="fireworks_ai/nemotron-3-ultra-nvfp4",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Nemotron 3 Ultra cost?

On Fireworks AI, Nemotron 3 Ultra costs $0.60 per million input tokens and $2.40 per million output tokens. Cached input costs $0.12 per million tokens.

Which APIs offer Nemotron 3 Ultra?

Nemotron 3 Ultra runs on 1 API: Fireworks AI.

What is Nemotron 3 Ultra's context window?

262K tokens, with up to 33K tokens in one reply.

Is Nemotron 3 Ultra being retired?

It has been retired: Fireworks AI retired it on 7 Nov 2026.

What are cheaper alternatives to Nemotron 3 Ultra?

Models that cost less and keep most of what it can do: Gemini 3.5 Flash Lite on Google AI Studio (19% less), GPT-5.4 Nano on OpenAI (56% less) and GLM 5.3 on CLF AI Gateway (18% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Nemotron 3 Ultra's API model id?

Use nemotron-3-ultra-nvfp4 with Fireworks AI.

Sources

Raw catalog entry for nemotron-3-ultra-nvfp4 on Fireworks AI
{
  "cache_read_input_token_cost": 1.2e-7,
  "cache_read_input_token_cost_priority": 1.5e-7,
  "deprecation_date": "2026-11-07",
  "deprecation_source": "https://docs.fireworks.ai/api-reference/list-models.md",
  "input_cost_per_token": 6e-7,
  "input_cost_per_token_priority": 7.5e-7,
  "litellm_provider": "fireworks_ai",
  "max_input_tokens": 262144,
  "max_output_tokens": 32768,
  "mode": "chat",
  "output_cost_per_token": 0.0000024,
  "output_cost_per_token_priority": 0.000003,
  "source": "https://api.fireworks.ai/v1/serverless/models?format=nested",
  "successor_model": "Nemotron Super VL",
  "supports_function_calling": true,
  "supports_mid_conversation_system": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_tool_choice": true,
  "supports_vision": false
}