NVIDIA: Nemotron 3.5 Lightning
nvidia/nemotron-3-5-lightningNVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.
Modalities
In / out per 1M$0.07 / $0.20
Context256K
ReleasedAug 11, 2026
Providers
5 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 CoreWeavebf16 | $0.07 | $0.20 | $0.04 | 0.21s | 284 tps | 100% |
| $0.04 | $0.13 | $0.02 | 0.56s | 151 tps | 99.97% | |
 DeepInfraus · bf16 | $0.06 | $0.16 | $0.03 | 0.57s | 38 tps | 99.81% |
 Darkbloomint4 | $0.03 | $0.12 | $0.01 | 2.52s | 85 tps | 95.58% |
| $0.05 | $0.13 | $0.02 | 0.57s | 183 tps | 95.52% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Nemotron 3.5 Lightning in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Nemotron 3.5 Lightning costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.07
per 1M tokens
Output
$0.20
per 1M tokens
Cache read
$0.04
per 1M cached tokens
Included in every pass
Nemotron 3.5 Lightning is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s5.0s10.0s15.0s20.0s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
CoreWeave io.net Wafer DeepInfra (us) Darkbloom
0 tok/s250 tok/s500 tok/s750 tok/s1000 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
CoreWeave io.net Wafer DeepInfra (us) Darkbloom
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.67%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.72%
100% 95% 90% 85%
Oct 13, 2:40 PMNow
Apps
Tools that most often run Nemotron 3.5 Lightning, by tokens this week.
Activity
203.0B tokens processed market-wide in the last month.
010.0B20.0B30.0B40.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for Nemotron 3.5 Lightning?
nvidia/nemotron-3.5-lightning. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Nemotron 3.5 Lightning hold?
262,144 tokens per request, of which up to 235,929 can be the response.
What can it accept and return?
Input: text. Output: text.
What does Nemotron 3.5 Lightning cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.07 per 1M input tokens and $0.20 per 1M output tokens.
Who built Nemotron 3.5 Lightning?
NVIDIA, in the Nemotron family.
Explore
Other models your pass can call.
