Model · NVIDIA

Nemotron 3 Super

nvidia/nemotron-3-super

Try in Agents

NVIDIA's 120B hybrid MoE model with 12B active parameters for agentic AI

reasoning

Specs

Context

256K

Max output

16K

Provider

NVIDIA

Input

$0.150/ 1M tokens

Output

$0.650/ 1M tokens

Cache read

—

Try it

Chat with Nemotron 3 SuperTerramind API

⌘+Enter to run

Code

import { streamText } from "ai";
import { createOpenAICompatible } from "@ai-sdk/openai-compatible";

const terramind = createOpenAICompatible({
  name: "terramind",
  baseURL: "https://terramind.com/api/v1",
  apiKey: process.env.TERRAMIND_API_KEY!,
});

const result = streamText({
  model: terramind("nemotron-3-super"),
  prompt: "Why is the sky blue?",
});

for await (const chunk of result.textStream) {
  process.stdout.write(chunk);
}

Want to run this in your app? Grab an API key · Full chat reference

More by NVIDIA

Model	Context	In	Out	Capabilities
nvidia/nemotron-3-ultra	1M	$0.600	$2.40	reasoningcaching
nvidia/nemotron-3.5-lightning	262K	$0.050	$0.200	reasoningcaching