Nemotron 3.5 Lightning
by NVIDIA · nvidia/nemotron-3.5-lightning · #38 cheapest of 422 paid models
Prices updated Sep 19, 2026, 6:21 PM UTC · refreshed hourly
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.07
per 1M tokens
Output
$0.20
per 1M tokens
Blended (3:1)
$0.103
3 input : 1 output
Cache read
$0.04
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Nemotron 3.5 Lightning with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.103 | $0.00734 | — |
| 50% | $0.091 | $0.00584 | −20% |
| 90% | $0.082 | $0.00464 | −37% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $9.50e-5 | $0.095 |
| Document summary | 8,000 | 1,000 | $0.00076 | $0.76 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0025 | $2.50 |
| Long-context analysis | 150,000 | 5,000 | $0.0115 | $11.50 |
Performance
Intelligence Index
13.6
AA composite quality
Coding Index
26.8
Math Index
—
Agentic Index
6.1
Output speed
288 tok/s
median
Time to first token
0.48s
median
Time to first answer
7.43s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 74.3% |
| Humanity's Last Exam | 10.6% |
| SciCode | 32.1% |
| AA-LCR (Long Context Reasoning) | 60.3% |
| Terminal-Bench 2.1 | 24.3% |
| τ³-Bench Banking | 8.9% |
Specs
Context window
262K
tokens
Max output
236K
tokens
Input modalities
text
Tokenizer
Other