NVIDIA Models on XALEN
GPU pioneer now building optimized AI models.
Founded: 1993 · HQ: Santa Clara, USA · 2 models available
Available Models
Nemotron 4 340B
Open SourceNVIDIA large model for synthetic data generation and training.
Params: 340B
Context: 128K
Input: $0.07
Output: $0.12
Latency: ~500ms
NVIDIA Nemotron 70B
Open SourceNVIDIA-optimized Llama with improved helpfulness.
Params: 70B
Context: 128K
Input: $0.04
Output: $0.06
Latency: ~300ms
Quick Start
import XALEN from 'xalen-sdk';
const client = new XALEN({ apiKey: 'xln_test_YOUR_KEY' });
const response = await client.chat.completions.create({
model: 'nemotron-4-340b',
messages: [{ role: 'user', content: 'Hello!' }]
});
Start Using NVIDIA Models
All models available through a single API. No separate accounts needed.
Get API KeyLast updated: 2026-05-21.