Nemotron 3 Super

NVIDIA's free open model. 120B parameters with 12B active — completely free to use with a 262K context window.

POST/v1/ai/chat

$0.01/call

Overview

NVIDIA's free open model. 120B parameters with 12B active — completely free to use with a 262K context window.

Property	Value
Model ID	`nvidia/nemotron-3-super`
Context Window	262,144 tokens
Max Output	8,192 tokens
Input Price	$0.00 / 1M tokens
Output Price	$0.00 / 1M tokens

Usage

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',
    messages: [{ role: 'user', content: 'Explain the concept of GPU parallelism in deep learning.' }],
  }),
});
const { data } = await res.json();
console.log(data.message.content);

curl -X POST https://api.yepapi.com/v1/ai/chat \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "nvidia/nemotron-3-super", "messages": [{"role": "user", "content": "Explain the concept of GPU parallelism in deep learning."}]}'

Request Body

Parameter	Type	Required	Description	Default
`model`	`string`	Yes	Model ID (e.g. `nvidia/nemotron-3-super`)	—
`messages`	`Message[]`	Yes	Array of `{ role, content }` objects	—
`maxTokens`	`number`	No	Maximum tokens in the response	Model default
`temperature`	`number`	No	Sampling temperature (0.0–2.0)	`1.0`
`topP`	`number`	No	Nucleus sampling threshold	`1.0`
`frequencyPenalty`	`number`	No	Penalize repeated tokens	`0`
`presencePenalty`	`number`	No	Penalize tokens already present	`0`
`stream`	`boolean`	No	Enable SSE streaming	`false`

Info

All AI models use the /v1/ai/chat endpoint. Specify the model with the model field.

Response

{
  "ok": true,
  "data": {
    "model": "nvidia/nemotron-3-super-120b-a12b:free",
    "message": {
      "role": "assistant",
      "content": "GPU parallelism in deep learning leverages thousands of CUDA cores to perform matrix operations simultaneously, enabling massive speedups for training and inference compared to sequential CPU processing."
    },
    "usage": {
      "promptTokens": 14,
      "completionTokens": 146,
      "totalTokens": 160
    }
  }
}

Streaming

Set "stream": true to receive Server-Sent Events. Each chunk contains a delta object:

data: {"delta":{"content":"GPU"},"model":"nvidia/nemotron-3-super-120b-a12b:free","index":0}
data: [DONE]

Under the Hood

We handle auth, billing, and response normalization — you just send messages.