Nemotron 3 Ultra (batch)
Open weightToolsNVIDIA · Released 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). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
It belongs to NVIDIA's open-weight Nemotron line, tuned for helpfulness and agents on top of leading open architectures.
Facts and pricing
- Provider
- NVIDIA
- Context window
- 512K tokens
- Input price
- 6.6 credits / 1M tokens ($0.60 raw)
- Output price
- 39.6 credits / 1M tokens ($3.60 raw)
- Vision (image input)
- No
- Tool calling
- Yes
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.
Try Nemotron 3 Ultra (batch) now
What Nemotron 3 Ultra (batch) is best for
- Everyday chat and drafting on an open-weight model with transparent lineage
- Very long documents and codebases: a 512K-token window fits entire books or repositories in one conversation
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Example prompts
Prompts that suit a open weight model like Nemotron 3 Ultra (batch):
- Draft a project update from these rough notes
- Explain how HTTPS works to a curious teenager
- Turn this list of features into a changelog entry
- Brainstorm objections to this proposal and how to answer them
NVIDIA family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Nemotron 3.5 Lightning | 1M | 0.88 | 2.2 | August 2026 |
| Nemotron 3.5 Lightning (free) | 1M | 0 | 0 | August 2026 |
| Nemotron 3.5 Content Safety (free) | 128K | 0 | 0 | June 2026 |
| Nemotron 3 Ultra | 512K | 6.6 | 39.6 | June 2026 |
| Nemotron 3 Ultra (batch) | 512K | 6.6 | 39.6 | June 2026 |
| Nemotron 3 Ultra (free) | 1M | 0 | 0 | June 2026 |
| Nemotron 3 Nano Omni (free) | 256K | 0 | 0 | April 2026 |
| Nemotron 3 Super (free) | 262K | 0 | 0 | March 2026 |
| Nemotron 3 Super | 1M | 0.93 | 4.4 | March 2026 |
| Nemotron 3 Nano 30B A3B (free) | 256K | 0 | 0 | December 2025 |
Frequently asked questions
- What is Nemotron 3 Ultra (batch)?
- Nemotron 3 Ultra (batch) is an AI model by NVIDIA. 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...
- How much does Nemotron 3 Ultra (batch) cost on Zeplik?
- Input tokens cost 6.6 credits per million and output tokens 39.6 credits per million (1 credit = $0.10; the raw provider rates are $0.60 and $3.60 per million). New accounts start with free credits.
- How long can a conversation with Nemotron 3 Ultra (batch) be?
- Nemotron 3 Ultra (batch) has a 512K-token context window (512,288 tokens), which covers the conversation plus any documents you attach.
- Does Nemotron 3 Ultra (batch) support images and tools?
- Nemotron 3 Ultra (batch) is text-only and supports tool calling.
Related models
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...
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...
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...
NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...
More you can do with Nemotron 3 Ultra (batch)
- 465 AI skillsReady-to-run expert methods for writing, data, code and more, each running on Nemotron 3 Ultra (batch) or any model you pick.
- 997 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.