AiCostCompare

Nemotron 3 Ultra

by NVIDIA · nvidia/nemotron-3-ultra-550b-a55b · #203 cheapest of 325 paid models

Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol

Pricing

Input

$0.60

per 1M tokens

Output

$3.60

per 1M tokens

Blended (3:1)

$1.35

3 input : 1 output

Cache read

$0.20

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for Nemotron 3 Ultra with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$1.35$0.0648
50%$1.20$0.0448−31%
90%$1.08$0.0288−56%

*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.

What a request costs

WorkloadInput tokensOutput tokensCost / requestCost / 1K requests
Short chat message500300$0.00138$1.38
Document summary8,0001,000$0.0084$8.40
Codebase question (RAG)30,0002,000$0.0252$25.20
Long-context analysis150,0005,000$0.108$108.00

Performance

Intelligence Index

37.8

AA composite quality

Coding Index

49.3

Math Index

Agentic Index

27.4

Output speed

median

Time to first token

median

Time to first answer

after reasoning tokens

Design Arena Elo

CategoryElo
Website1,127
UI components1,182
Data viz1,148
SVG1,127
3D1,190
Game dev1,186
Code categories1,156
ASCII art1,118

Specs

Context window

512K

tokens

Max output

tokens

Input modalities

text

Tokenizer

Other