Hoodgen
Sign in
NvidiaReasoningReleased 4 June 2026

Nemotron 3 Ultra pricing, context and benchmark

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).

Chat with Nemotron 3 Ultra
262K
Input context
183K
Output context
$0.5
Official input
$2.2
Official output
n/a
AA index
01 · Model Overview

Everything that matters, in one table

Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.

ModelNemotron 3 Ultra
Model IDnvidia/nemotron-3-ultra-550b-a55b
ProviderNvidia
Release date4 June 2026
StatusGenerally available
Input context262,144 tokens
Output context182,520 tokens
Official input pricing$0.5 per 1M tokens
Official output pricing$2.2 per 1M tokens
Cache read pricingNot published
Market input pricing$0.4 per 1M (cheapest route)
Market output pricing$1.76 per 1M (cheapest route)
Highest route pricing$0.625 in, $3.125 out per 1M
Input modalitiestext
Output modalitiestext
Reasoning controlNot exposed
Tool supportText generation only
TokenizerOther
Provider routes5 endpoints
Artificial Analysis indexNot published
SpeedNot published
Knowledge cutoffNot publicly stated

Input and output support

ModalityInputOutputBilled at
Text✓ yes✓ yes$0.5 in
Imagenononot supported
Audionononot supported
Videonononot supported
File (PDF)nononot supported
02 · Overview

What is Nemotron 3 Ultra?

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...

Nemotron 3 Ultra carries a 262K token window, uses the Other tokenizer and is served by Nvidia. On Hoodgen it sits in the Reasoning tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.

03 · Release

Release and what changed from the previous version

Released4 June 2026
PropertyNemotron 3 Super (free)Nemotron 3 UltraChange
Released20262026Same release window
Context1.05M262KChanged
Max outputn/a183KChanged
Input priceFree$0.5Higher
Output priceFree$2.2Higher
Input modalitiestexttextUnchanged
AA indexn/an/aNewer benchmark run
07 · Use cases

What can you do with Nemotron 3 Ultra?

Debugging and root cause
Multi file failures where the model has to hold a causal chain before answering.
Architecture and planning
Design docs, migration plans and trade off analysis over long context.
Data analysis
Spreadsheets and logs read in one pass, then summarised with the numbers quoted back.
Agentic coding
Repo wide changes that need plan, edit and verify loops.
09 · Pricing

Nemotron 3 Ultra pricing

Official pricing

List price
$0.5 / 1M in
$2.2 / 1M out
  • 262K context
  • text input
Cheapest route
$0.4 / 1M in
$1.76 / 1M out
  • 5 routes on OpenRouter
  • What Hoodgen routes to first
  • Same model, lower bill
Highest route
$0.625 / 1M in
$3.125 / 1M out
  • Priority or premium tier
  • Best under load
  • Use for latency critical calls

Market pricing, every route

ProviderTierInputOutputCache readUptime 24h
DeepInfraflex$0.4$1.76$0.08100.0%
DeepInfrastandard$0.5$2.2$0.199.9%
BaseTenstandard$0.6$2.4$0.12100.0%
BaseTenstandard$0.6$2.4$0.12100.0%
Venicestandard$0.625$3.125$0.18899.9%

API pricing and cost calculator

RatePer callTotalCredits
Cheapest route$0.0068$3.403231
List price$0.0133$6.656318
Highest route$0.0172$8.598165
10 · Developers

API and developer information

Model IDnvidia/nemotron-3-ultra-550b-a55b
Endpointhttps://openrouter.ai/api/v1/chat/completions
Parametersprompt and max_tokens
StreamingYes, server sent events
Modality stringtext->text
Max prompt tokens262,144
Max completion tokens182,520
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3-ultra-550b-a55b",
    "messages": [{ "role": "user", "content": "Summarise this document." }],
    "max_tokens": 1024
  }'
11 · Limitations

Model limitations

Text only outputIt cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals.
Output cap182,520 tokens per request. Long deliverables have to be chunked.
Benchmarks not publishedArtificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here.
Knowledge cutoffThe provider does not state a fixed cutoff for every release. Verify very recent events against search.
12 · Comparison

Nemotron 3 Ultra vs other Nvidia models

ModelContextInput /1MOutput /1MAA indexReleased
Nemotron 3 Ultra262K$0.5$2.2n/a2026
Nemotron 3.5 Lightning (free)1MFreeFreen/a2026
Nemotron 3 Super (free)1.05MFreeFreen/a2026
Nemotron 3 Ultra (free)1MFreeFreen/a2026
13 · Privacy

Privacy and data policy

  • On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
  • Requests route through OpenRouter to Nvidia and are covered by that provider's API terms.
  • Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ

Nemotron 3 Ultra questions, answered

Nemotron 3 Ultra is a reasoning model from Nvidia, released 4 June 2026. NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).
✦

Start chatting with Nemotron 3 Ultra

Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.

Open Chat, it is freeCompare all models