ModelPriceWatch.com
Last scan 2026-08-22 Models tracked 220 Providers 31 Cheapest paid Granite 4.0 H Micro $0.017/Mtok in Every price links to its source

NVIDIA Nemotron 3 Ultra

by Fireworks

Current mid tier open weights mid tier
Email me when NVIDIA Nemotron 3 Ultra gets cheaper

Today's price · per 1M tokens

Input

$0.600

per 1M tokens

Output

$2.40

per 1M tokens

Blended

$1.05

blended $/1M — 3:1 weighted input:output

Cached input

$0.120

20% of input — prompt caching

Source: official Fireworks pricing · read Jun 25, 2026 MODELPRICEWATCH.COM · 2026-08-22

Price receipt

We read Fireworks's own pricing page on Aug 9, 2026 and found NVIDIA Nemotron 3 Ultra (Preview) listed with a price on the same row — that read is where the number above comes from. We keep the page text we read; its content hash is 4f5353269c.

NVIDIA Nemotron 3 Ultra is available on 2 hosts. See the full cheapest-first comparison on the consolidated NVIDIA Nemotron 3 Ultra page →

Overview

NVIDIA Nemotron 3 Ultra (preview) on Fireworks. $0.60/$2.40 per 1M.

Run it yourself

Deploy this open model on rented GPUs

Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.

RunPod →
Rent GPUs by the second and serve any open-weight model yourself.
Novita AI →
Serverless open-model inference billed per token — no GPU ops.
Vast.ai →
GPU marketplace — rent spot/on-demand GPUs cheaply and serve any open-weight model.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.

Capabilities

struck through = not supported
Input 1/5
Text ✓ Image Audio Video PDF
Output 1/5
Text ✓ Image Audio Video Embedding
Features 4/9
Prompt caching ✓ Reasoning ✓ Coding Fast inference Long context ✓ Open weights ✓ Multimodal Web search Realtime

Benchmark performance

accuracy % · higher is better
Percentile vs all tracked models 38.9th5 independent measurements
Percentile per $/Mtok 37

We hold no per-benchmark accuracy scores for this model yet, so it has no accuracy average. That is a gap in our coverage, not a sign the model is untested — independent evaluators often publish a composite index for a new model long before releasing its per-benchmark numbers. The percentile above is its standing across the independent composites below.

Independent composite scores
  • AA Intelligence Index: 38.3 (Artificial Analysis composite across reasoning, knowledge and coding evals)
  • AA Agentic Index: 27.5 (Tool use, planning, autonomy)
  • AA-Omniscience Index: -0.4 (−100–100)
  • GDPval-AA v2: 1163 ELO (Real-world work tasks, human baseline = 1000)
  • LMSYS Chatbot Arena: 1426.1 ELO (Human preference)
How it stacks up
  • Ranks #90 of 161 comparably-measured models by percentile score, across 5 independent measurements
  • Ranks #63 of 161 comparably-tested models by normalized performance per dollar

Source: Artificial Analysis · updated Jun 29, 2026 · See full rankings →

Specifications

Provider
Fireworks
Context window
128K tokens
Modality
text
Parameters
Proprietary
Open source
Yes — open weights available
Released
Jan 1, 2026
Status
Current
Last updated
Jun 25, 2026
Tags
open-weightsmid-tierreasoningcaching

Availability verified: Aug 9, 2026 — listed on Fireworks's own page

Try on Fireworks Official pricing page