Nemotron 3 Super
Access Nemotron 3 Super through one API key. NVIDIA's free model.
NVIDIA's free open-source model. 120B parameters with mixture-of-experts, completely free to use.
No credit card required. Takes 30 seconds.
2,400+
Developers
1.2M+
API calls served
100+
Endpoints
$0.01
Per call
Yep, that's it.
Try it live
Send a message and see Nemotron 3 Super respond in real time.
Maximum tokens in the response.
Real-time tokens
Context Window
262K tokens
Max Output
262K tokens
Input Price
$0.00 / 1M tokens
Output Price
$0.00 / 1M tokens
Strengths
Offered at no token cost, $0.00 input and output, making it ideal for experimentation and cost-sensitive workloads.
An openly released NVIDIA model, offering transparency and freedom from closed-model lock-in.
Supports a 262,144-token context window with up to 262,144 output tokens, generous for long inputs and outputs.
A 120B-parameter mixture-of-experts model handling a broad range of text tasks across reasoning and generation.
Quick start
Copy this snippet and start making calls with Nemotron 3 Super.
const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
method: 'POST',
headers: {
'x-api-key': 'YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "nvidia/nemotron-3-super-120b-a12b:free",
"messages": [
{
"role": "user",
"content": "Explain API gateways in 2 sentences."
}
],
"maxTokens": 256
}),
});
const { data } = await res.json();
console.log(data.message.content);Why use Nemotron 3 Super through YepAPI?
Nemotron 3 Super API: NVIDIA's free open-source model
Nemotron 3 Super is NVIDIA's free, open-source 120B mixture-of-experts model, offering a generous 262K context window at no token cost. YepAPI serves it through one OpenAI-compatible endpoint.
Your single YepAPI key also reaches DeepSeek, Claude, Grok, Gemini, and more, plus SEO, SERP, and scraping endpoints, so a free model can sit alongside your paid models and data tools.
What is Nemotron 3 Super?
Nemotron 3 Super is NVIDIA's free, open-source large language model, a 120-billion-parameter mixture-of-experts (MoE) design. The MoE architecture activates only part of the network per token, giving large-model capability with efficient inference. It offers a 262,144-token context window and up to 262,144 output tokens, both unusually generous, and handles general-purpose reasoning and text generation across many tasks. Its defining feature is that it is free to use at $0.00 per token, combined with NVIDIA's open release, which makes it ideal for experimentation, prototyping, and cost-sensitive production where you want capable output without per-token cost.
Build with Nemotron 3 Super via YepAPI
Call YepAPI's OpenAI-compatible /v1/ai/chat endpoint with any OpenAI client. Set the base URL, add your key, and set the model string to Nemotron 3 Super; your existing chat-completion code works unchanged. Switching models is one string. Because the same key reaches the whole catalog, you can default to this free model for development and high-volume work, then route specific tasks to paid models when you need them, all from a single integration.
Nemotron 3 Super API pricing — free, $0.00 per 1M tokens
Nemotron 3 Super is free: $0.00 per 1M input tokens and $0.00 per 1M output tokens. There is no per-token charge for either direction, which makes it a natural default for prototyping, testing, and high-volume tasks where keeping costs at zero matters. You still get a 262K context window and large output ceiling, so the free tier is genuinely capable rather than a stripped-down trial.
Nemotron 3 Super for free experimentation and prototyping
Because it costs nothing per token, Nemotron 3 Super is the obvious choice for building and iterating, testing prompts, prototyping agents, and running high-volume or background tasks without watching a meter. The MoE 120B design and 262K context make it capable enough for real general-purpose work, and the open-source nature appeals to teams that want transparency. It is a strong free baseline you can keep on the same key as your paid models.
Try Nemotron 3 Super free
Nemotron 3 Super is free to call, and new YepAPI accounts also get $5 in credit with no card required for the rest of the catalog. Sign up, set the model string, and start sending requests immediately, then compare it against paid models on the same key whenever you need more capability.
Start generating in 30 seconds
$5 free credit on signup. No credit card required. Pay per call.
What developers say
“Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.”
“One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.”
“The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.”
Frequently asked questions
NVIDIA's free open-source model. 120B parameters with mixture-of-experts, completely free to use.
Input tokens cost $0.00 per 1M tokens and output tokens cost $0.00 per 1M tokens through YepAPI. No monthly minimums — you only pay for what you use.
Sign up for a free API key, then send requests to the /v1/ai/chat endpoint.
Nemotron 3 Super supports a 262K token context window with up to 262K output tokens per request.
Ready to use Nemotron 3 Super?
$5 free credit on signup. No credit card required. Pay per call.
Explore more models
GPT-4o Mini
OpenAIAccess GPT-4o Mini through one API key. Fast, cheap, and OpenAI-compatible.
GPT-4o
OpenAIAccess GPT-4o through one API key. Flagship reasoning and multimodal capabilities.
Claude Sonnet 4
AnthropicAccess Claude Sonnet 4 through one API key. Anthropic's best balance of speed and intelligence.