Compare

Nemotron 3.5 Lightning (free) vs …

Put models side by side on context, price, speed and availability.

Side-by-side comparison of the selected models
Model
Overview
Developer NVIDIA
Context tokens1M
Max output tokens64K
Input text
Output text
Providers 5
Released Aug 11, 2026
Pricing
Input per 1MFree
Output per 1MFree
Cache read per 1MVariable
Performance
Latency p50, median provider0.60s
Throughput p50, median provider131 tps
Uptime last 24h100.00%

Add a model