# Nvidia Nemotron Nano 9B V2

Nvidia Nemotron Nano 9B V2 is a language model from Nvidia with a 128K-token context window. Provider list price is $0.06 per million input tokens and $0.25 per million output; on Allocate you pay $0.064 and $0.27 with the 7% transaction fee. The weights are open under Custom license, so you can fine-tune it and own the result.

## Pricing

| | Provider list | On Allocate |
| --- | --- | --- |
| Input, per M tokens | $0.06 | $0.064 |
| Output, per M tokens | $0.25 | $0.27 |

Token usage bills at the provider list price plus the 7% transaction fee. Prices checked 2026-07-08.

## Facts

| Field | Value |
| --- | --- |
| Lab | Nvidia |
| Modality | Language |
| Context window | 128K tokens |
| License | Custom license |
| Open weights | Yes |
| Fine-tunable | Yes, on your data |
| Catalog id | nvidia/nvidia-nemotron-nano-9b-v2 |

## What a real workload costs

Take 1,000,000 requests a month at 1,200 input and 350 output tokens each: 1,200M input and 350M output tokens. At list prices that is 1,200 × $0.06 + 350 × $0.25 = $159.50 a month. Billed on Allocate it is $170.67 with the 7% transaction fee.

## Common questions

### How much does Nvidia Nemotron Nano 9B V2 cost per million tokens?

Provider list price is $0.06 per million input tokens and $0.25 per million output tokens. On Allocate you pay list plus the 7% transaction fee: $0.064 in and $0.27 out.

### What context window does Nvidia Nemotron Nano 9B V2 have?

131,072 tokens (128K). At roughly 0.75 words per token, that is about 98k words of English text per request.

### Can I fine-tune Nvidia Nemotron Nano 9B V2?

Yes. Nvidia Nemotron Nano 9B V2 is an open-weights model under the Custom license license. Read the license terms before fine-tuning for commercial use. On Allocate the trained weights stay inside your boundary and belong to you.

### How do I call Nvidia Nemotron Nano 9B V2 on Allocate?

Send nvidia/nvidia-nemotron-nano-9b-v2 in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.

---

[HTML page](https://allocate.network/models/nvidia-nvidia-nemotron-nano-9b-v2) · [Machine-readable catalog](https://allocate.network/catalog.json)