How much does Nemotron Nano 9B V2 (free) cost via API?

It's free: $0 per 1M input tokens and $0 per 1M output tokens from the provider. OpenKey's flat 3% fee applies to provider list price, and 3% of $0 is still $0, so there's no cost on either side.

What is Nemotron Nano 9B V2's context window?

It supports 128,000 tokens of context. That's enough to hold a long document or codebase in a single request. Within the OpenKey catalog, this context length is larger than only 12% of the 329 models listed, so it's on the smaller side relative to the full catalog despite being large in absolute terms.

Is Nemotron Nano 9B V2 free to use?

Yes. Both prompt and completion pricing are $0.00 per 1M tokens from the provider, and OpenKey passes that through with no markup since its 3% fee is calculated on provider price. It's one of 25 free models currently on OpenKey.

Does Nemotron Nano 9B V2 support tool calling and structured outputs?

Yes. Its supported parameters include `tools`, `tool_choice`, `response_format`, and `structured_outputs`, alongside standard controls like `temperature`, `top_p`, and `seed`. It also exposes `reasoning` and `include_reasoning` parameters, letting you turn step-by-step reasoning on or off per call.

What is Nemotron Nano 9B V2's knowledge cutoff?

NVIDIA lists a knowledge cutoff of March 31, 2025, for this model. It was released on OpenKey on September 5, 2025, so the training data is roughly five months old at launch.

Nemotron Nano 9B V2 (free)

nvidianemotron-nano-9b-v2:free

Free

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...

Try in playground Hugging Face ↗

Modalities: text → text
In / out per 1M: Free / Free
Context: 128K tokens
Added: Sep 5, 2025

Tokenizer: Other
Knowledge cutoff: Mar 31, 2025
Reasoning: optional

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokens	Provider	+ 3% fee	You pay
Input	Free	—	Free
Output	Free	—	Free

Providers

One company serves Nemotron Nano 9B V2 (free). Figures are each provider’s own list price per 1M tokens — your OpenKey price is in the card above.

Provider	Context	Input /M	Output /M
Nvidiabf16	128K	Free	Free

Provider list from the OpenRouter catalog, Jul 28, 2026. All providers

Supported parameters

include_reasoning
max_tokens
reasoning
response_format
seed
structured_outputs
temperature
tool_choice
tools
top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model nvidia/nemotron-nano-9b-v2:free.

curl Python TypeScript

curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer ***" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-nano-9b-v2:free",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="nvidia/nemotron-nano-9b-v2:free",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "nvidia/nemotron-nano-9b-v2:free",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

About Nemotron Nano 9B V2 (free)

Nemotron Nano 9B V2 is a 9B-parameter NVIDIA model built to handle both reasoning and non-reasoning tasks from a single checkpoint, with optional reasoning you can toggle per request via the `reasoning` and `include_reasoning` parameters. It carries a 128,000-token context window, takes text in and out, and supports tool calling and structured outputs. NVIDIA lists a knowledge cutoff of March 31, 2025, and it's served free on OpenKey.

It's free — $0 per 1M tokens for both prompt and completion, with no OpenKey fee to add since 3% of zero is zero. Its 128,000-token context window is larger than 12% of catalog models, which is a below-average rank for context length among the 329 models on OpenKey. Reasoning is optional rather than mandatory, so you can run it as a fast non-reasoning chat model or switch on reasoning per request. Several siblings, including Nemotron 3 Nano 30B A3B (free) and Nemotron 3 Super (free), also run at $0.

Questions

How much does Nemotron Nano 9B V2 (free) cost via API?: It's free: $0 per 1M input tokens and $0 per 1M output tokens from the provider. OpenKey's flat 3% fee applies to provider list price, and 3% of $0 is still $0, so there's no cost on either side.
What is Nemotron Nano 9B V2's context window?: It supports 128,000 tokens of context. That's enough to hold a long document or codebase in a single request. Within the OpenKey catalog, this context length is larger than only 12% of the 329 models listed, so it's on the smaller side relative to the full catalog despite being large in absolute terms.
Is Nemotron Nano 9B V2 free to use?: Yes. Both prompt and completion pricing are $0.00 per 1M tokens from the provider, and OpenKey passes that through with no markup since its 3% fee is calculated on provider price. It's one of 25 free models currently on OpenKey.
Does Nemotron Nano 9B V2 support tool calling and structured outputs?: Yes. Its supported parameters include `tools`, `tool_choice`, `response_format`, and `structured_outputs`, alongside standard controls like `temperature`, `top_p`, and `seed`. It also exposes `reasoning` and `include_reasoning` parameters, letting you turn step-by-step reasoning on or off per call.
What is Nemotron Nano 9B V2's knowledge cutoff?: NVIDIA lists a knowledge cutoff of March 31, 2025, for this model. It was released on OpenKey on September 5, 2025, so the training data is roughly five months old at launch.

More from NVIDIA

All NVIDIA models →

NVIDIA

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...

ctx 1M in $0.515 out $2.27

NVIDIAFree

Nemotron 3 Ultra (free)

ctx 1M in Free out Free

NVIDIAFree

Nemotron 3.5 Content Safety (free)

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...

ctx 128K in Free out Free

NVIDIAFree

Nemotron 3 Nano Omni (free)

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...

ctx 256K in Free out Free