How much does Nemotron-4 340B cost?

Nvidia has not published per-token API pricing for Nemotron-4 340B at the time of writing. Check the official site for current pricing tiers, or compare against alternative models on LLMDex.

What is Nemotron-4 340B's context window?

Nemotron-4 340B supports a context window of 4.1K tokens.

Is Nemotron-4 340B open source?

Nemotron-4 340B ships with open weights under the Nvidia Open Model License license. You can self-host it, fine-tune it, and (subject to the license terms) deploy it commercially.

When was Nemotron-4 340B released?

Nemotron-4 340B was released on Jun 14, 2024 by Nvidia.

How much does Nemotron-4 340B cost?

Nvidia has not published per-token API pricing for Nemotron-4 340B at the time of writing. Check the official site for current pricing tiers, or compare against alternative models on LLMDex.

What is Nemotron-4 340B's context window?

Nemotron-4 340B supports a context window of 4.1K tokens.

Is Nemotron-4 340B open source?

Nemotron-4 340B ships with open weights under the Nvidia Open Model License license. You can self-host it, fine-tune it, and (subject to the license terms) deploy it commercially.

When was Nemotron-4 340B released?

Nemotron-4 340B was released on Jun 14, 2024 by Nvidia.

Open weightsNvidiaopentext

Nemotron-4 340B

Nvidia's 340B open-weight model, useful as a synthetic-data generator and benchmark.

UpdatedApr 30, 2026

Quick facts

Released: Jun 2024
Context: 4.1K tokens
Output / 1M: Pricing not published
License: Nvidia Open Model License

About Nemotron-4 340B

Nemotron-4 340B is Nvidia's open-weight contribution from mid-2024, primarily positioned as a synthetic-data generator for fine-tuning other models. The license permits commercial use with caveats; it sees relatively little direct deployment but heavy use as a teacher model.

Benchmarks

Published scores from Nvidia's model card or independent leaderboards. We do not publish numbers we cannot source, see methodology.

HumanEval

Python coding pass@1

MMLU

81.1

Broad academic knowledge

GPQA

Graduate-level reasoning

SWE-bench

Real software-engineering tasks

MMLU81.1

Capabilities

Strengths

Synthetic-data use case
Open weights

Tracked weaknesses

Tiny 4k context, not for production chat
Custom license
Heavy at 340B

Pricing

Per-million-token rates as published by Nvidia.

Per-token pricing not yet published for Nemotron-4 340B. Check the official provider site for current tiers.

Call Nemotron-4 340B from your code

Drop-in snippet for the Nvidia SDK. Set your API key in the environment and run.

typescript

import OpenAI from "openai";

const client = new OpenAI({
  // Use OPENAI_API_KEY for OpenAI, or your provider's key + baseURL.
  apiKey: process.env.OPENAI_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "nemotron-4-340b",
  messages: [
    { role: "user", content: "What's the time complexity of quicksort?" },
  ],
});

console.log(completion.choices[0].message.content);

Compare Nemotron-4 340B with…

Frequently asked

How much does Nemotron-4 340B cost?
Nvidia has not published per-token API pricing for Nemotron-4 340B at the time of writing. Check the official site for current pricing tiers, or compare against alternative models on LLMDex.
What is Nemotron-4 340B's context window?
Nemotron-4 340B supports a context window of 4.1K tokens.
Is Nemotron-4 340B open source?
Nemotron-4 340B ships with open weights under the Nvidia Open Model License license. You can self-host it, fine-tune it, and (subject to the license terms) deploy it commercially.
When was Nemotron-4 340B released?
Nemotron-4 340B was released on Jun 14, 2024 by Nvidia.

Friday digest

One short email every Friday, new model launches, leaderboard moves, and pricing drops. Curated by hand. Free, no spam.