LLMPrivate

NVIDIA Nemotron 3 Ultra

NVIDIA's flagship open-weights frontier model — a 550B-parameter hybrid Mamba-MoE architecture built for agentic reasoning, tool use, and long-context throughput.

Get API key
Provider
NVIDIA
Price
$0.63 in · $3.13 out / 1M
Context window
256K tokens
Released
June 4, 2026
License
OpenMDW-1.1

What is NVIDIA Nemotron 3 Ultra?

NVIDIA Nemotron 3 Ultra is a frontier-scale 550B-parameter (55B active) open-weights language model released in June 2026. It combines a hybrid Mamba-2, MoE, and Attention architecture with Multi-Token Prediction for efficient high-throughput agentic reasoning, native tool use, and long-context analysis.

Use it privately on Venice

On Venice, Nemotron 3 Ultra runs privately with zero retention of your prompts — no surveillance, no training data harvesting. You get native tool use, reasoning, and web search capabilities with the efficiency of an open-weights model, processed on Venice's permissionless infrastructure without a Big Tech account.

Private (zero retention)
No prompt training
TEE · hardware enclave
End-to-end encrypted

What can it do?

Strengths
  • Open weights under OpenMDW-1.1 — full checkpoints, training data, and recipes released for self-hosting and fine-tuning.
  • Frontier agentic performance with native tool use, reasoning, and web search support for complex multi-step workflows.
  • Hybrid Mamba-2 + MoE + Attention architecture with Multi-Token Prediction delivers up to ~6× higher inference throughput than comparable open LLMs.
  • Configurable reasoning budget via chat template (enable_thinking), letting you trade speed for depth per task.
  • Strong multilingual coverage across English, French, Spanish, Italian, German, Japanese, Korean, Hindi, Brazilian Portuguese, and Chinese.
  • Designed for up to 1M token context length and strong long-context RULER performance, with 256K available on Venice.
Limitations
  • Not uncensored — it carries safety alignment and will refuse certain requests, unlike fully uncensored models.
  • Massive hardware footprint for self-hostingBF16 requires 8× GB200/B200 or 16× H100, making local inference expensive.
  • Venice currently offers a 256K context window and fp8 quantization, which is below the native 1M context and BF16 precision.
  • Premium output pricing ($3.13/1M tokens) is higher than efficient rivals like DeepSeek V3.2.
  • As a cutting-edge MoE architecture, it may have less third-party tooling and framework support than standard dense transformers.

NVIDIA Nemotron 3 Ultra capabilities

How to use it via API

Venice exposes an OpenAI-compatible API. Swap your base URL and call nvidia-nemotron-3-ultra-550b-a55b.

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia-nemotron-3-ultra-550b-a55b",
    "messages": [{ "role": "user", "content": "Explain quantum tunneling simply." }]
  }'

Specifications

MakerNVIDIA Corporation
ReleasedJune 4, 2026
ArchitectureLatentMoE — Mamba-2 + MoE + Attention hybrid with Multi-Token Prediction (MTP)
Parameters550B total / 55B active
Open weightsYes — OpenMDW-1.1 license
Context window256K tokens
Max output32.768K tokens
CapabilitiesFunction calling, Reasoning, Web search
Privacy on VenicePrivate — zero retention
Available on Venice sinceJun 2026

Pricing

Billed per token on Venice: $0.63 per 1M input tokens and $3.13 per 1M output tokens.

Input / 1M tokens
$0.63
Output / 1M tokens
$3.13
Cached input / 1M
$0.19

New Venice accounts include a free daily allowance and 500 welcome credits — no credit card required.

NVIDIA Nemotron 3 Ultra vs alternatives

ModelPrice (Venice)Context windowOpen weightsBest for
NVIDIA Nemotron 3 Ultra$0.63 in · $3.13 out / 1M256K tokensYesAgentic reasoning & throughput
Kimi K2.6$0.75 in · $3.50 out / 1M256K tokensYesLong-context reasoning & coding
DeepSeek V3.2$0.33 in · $0.48 out / 1M160K tokensYesEfficiency & math/code
Claude Sonnet 4.6$3.60 in · $18 out / 1M1M tokensNoGeneral-purpose closed model

NVIDIA's most capable open-weights model — hybrid Mamba-MoE with configurable reasoning and native tool use.

What is it good for?

  • Long-running autonomous agents that plan, call tools, and maintain state across many turns.
  • High-stakes RAG over very long documents and legal or scientific corpora.
  • Multilingual reasoning and analysis across code, math, and science benchmarks.
  • Enterprise workflows requiring open weights and data sovereignty for compliance.
  • Code generation and review with extended context for large repositories.

Prompting tips

  • Toggle reasoning depth with the chat template (enable_thinking=True/False) depending on whether you need deep analysis or fast answers.
  • Leverage the 256K context window for large document RAG — feed full papers or codebases in a single prompt.
  • Use structured output (JSON schema) when building agents that need machine-readable tool arguments.
  • For multi-turn agent tasks, keep the conversation history concise to maximize available context for reasoning.

Frequently asked questions

NVIDIA Nemotron 3 Ultra is a 550B-parameter (55B active) open-weights frontier language model released in June 2026. It uses a hybrid Mamba-2, MoE, and Attention architecture with Multi-Token Prediction for high-throughput agentic reasoning, tool use, and long-context analysis.

Venice charges $0.63 per 1M input tokens and $3.13 per 1M output tokens. Cached input is $0.19 per 1M tokens. There is no subscription required — you pay per token with credits.

You can try it free on Venice — new accounts receive welcome credits and a daily free tier, with no credit card required. Continued use is billed per token in credits.

It is open weights under the OpenMDW-1.1 license. NVIDIA releases the base, post-trained, and quantized checkpoints along with training data and recipes, but it is not an open-source code project in the traditional sense.

Yes. On Venice it supports function calling, reasoning, and web search, plus structured JSON schema output for building agents and automated workflows.

Nemotron 3 Ultra emphasizes agentic throughput and configurable reasoning with a hybrid Mamba-MoE architecture. Kimi K2.6 is also open weights with strong long-context and coding skills. Choose Nemotron for complex multi-step agents and Kimi for deep coding tasks.

Venice currently hosts Nemotron 3 Ultra with a 256K token context window and up to 32,768 tokens max output. NVIDIA's native model supports up to 1M tokens for deployments with sufficient hardware.

Yes. The model supports a configurable reasoning mode via the chat template (enable_thinking=True/False), letting you control the depth of analysis and token usage per request.

No. It is a safety-aligned model and will refuse certain harmful or restricted requests. It is not uncensored, though Venice runs it privately without content monitoring or logging.

Related models

Run NVIDIA Nemotron 3 Ultra privately.

No prompt logging. No data used for training. Free to start — no credit card.

Room