← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
Nemotron 3.5 Lightning Pricing
NVIDIA · nvidia-nemotron-3-5-lightning
Input / 1M tokens
$0.080
Output / 1M tokens
$0.200
Context window
262,144 tokens
≈ 350 pages of text
Max output
131,072 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0002
1,000 requests / month$0.176/mo10,000 requests / month$1.76/mo100,000 requests / month$17.60/moEstimate your own workloadOpens the calculator with Nemotron 3.5 Lightning preloaded — adjust volume and token counts there.
Price history
List price per 1M tokens since we started tracking in Aug 2026. Each step marks a price change — hover a point for the exact date and rate.
What it excels at
Handles 256k-token contexts at very low per-token cost, suitable for high-volume document processing and summarization workloads.
The business tradeoff
Reasoning depth trails closed flagships; output quality depends on user-hosted inference stack and optimization.
Cheaper from NVIDIA
Head-to-head
Vendor list rates, as of Aug 28, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.