Nemotron Nano 9B V2 (free)
Fast and lightToolsNVIDIA · Released September 2025 · Knowledge cutoff March 2025
NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...
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
- 128K tokens
- Input price
- 0 credits / 1M tokens ($0 raw)
- Output price
- 0 credits / 1M tokens ($0 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 Nano 9B V2 (free) now
What Nemotron Nano 9B V2 (free) is best for
- High-volume everyday tasks where speed and cost matter: summaries, drafts, quick questions
- Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows
Example prompts
Prompts that suit a fast and light model like Nemotron Nano 9B V2 (free):
- Summarize this article in five bullet points
- Rewrite this email to be shorter and friendlier
- Give me ten name ideas for a hiking newsletter
- Translate this paragraph to Spanish and keep the tone
NVIDIA family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Nemotron 3.5 Content Safety (free) | 128K | 0 | 0 | June 2026 |
| Nemotron 3 Ultra (free) | 1M | 0 | 0 | June 2026 |
| Nemotron 3 Ultra | 1M | 5.5 | 24.2 | June 2026 |
| Nemotron 3 Nano Omni (free) | 256K | 0 | 0 | April 2026 |
| Nemotron 3 Super (free) | 1M | 0 | 0 | March 2026 |
| Nemotron 3 Super | 1M | 0.88 | 5.0 | March 2026 |
| Nemotron 3 Nano 30B A3B (free) | 256K | 0 | 0 | December 2025 |
| Nemotron 3 Nano 30B A3B | 262K | 0.55 | 2.2 | December 2025 |
| Nemotron Nano 12B 2 VL (free) | 128K | 0 | 0 | October 2025 |
| Llama 3.3 Nemotron Super 49B V1.5 | 131K | 4.4 | 4.4 | October 2025 |
Frequently asked questions
- What is Nemotron Nano 9B V2 (free)?
- Nemotron Nano 9B V2 (free) is an AI model by NVIDIA. NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...
- How much does Nemotron Nano 9B V2 (free) cost on Zeplik?
- Input tokens cost 0 credits per million and output tokens 0 credits per million (1 credit = $0.10; the raw provider rates are $0 and $0 per million). New accounts start with free credits.
- How long can a conversation with Nemotron Nano 9B V2 (free) be?
- Nemotron Nano 9B V2 (free) has a 128K-token context window (128,000 tokens), which covers the conversation plus any documents you attach.
- Does Nemotron Nano 9B V2 (free) support images and tools?
- Nemotron Nano 9B V2 (free) is text-only and supports tool calling.
Related models
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...
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...