Nemotron 3.5 Lightning
- Input / output
- $0.025 / $0.12
- Providers
- 5
- Spread
- 2.1×
- 7 days
- 0%
- 30 days
- 0%
- Context
- 1M
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
DarkbloomCheapest int4 | $0.025 | $0.12 | $0.0488 | ref | |||
| bf16 | $0.06 | $0.16 | $0.085 | +74% | |||
| $0.05 | $0.20 | $0.0875 | +79% | ||||
| bf16 | $0.07 | $0.20 | $0.103 | +110% | |||
| fp4 | $0.07 | $0.20 | $0.103 | +110% |
- DarkbloomCheapest$0.0488$0.025 in · $0.12 outref vs ref256K ctx100% uptimeint4
- $0.085$0.06 in · $0.16 out+74% vs ref256K ctx99.8% uptimebf16
- $0.0875$0.05 in · $0.20 out+79% vs ref256K ctx100% uptime
- $0.103$0.07 in · $0.20 out+110% vs ref256K ctx100% uptimebf16
- $0.103$0.07 in · $0.20 out+110% vs ref1M ctx100% uptimefp4
Blended = (3 × input + output) / 4. Ref $0.0488 = median of cheapest 20%.
Price history
USD per 1M tokens · each step is a price change
Prices in USD / 1M tokens.
Other pricing
| Offered by | Cache read |
|---|---|
| Darkbloom | $0.0125 |
| DeepInfra | $0.03 |
| Fireworks | $0.01 |
| CoreWeave, ModelRun | $0.04 |
Changes
- ListedNow served,Listed
- DelistedNo longer served,Delisted
- ListedNow served,Listed
- DelistedNo longer served,Delisted
- PriceCache read price,$0.072→$0.017−76.4%
- PriceInput price,$0.09→$0.035−61.1%
- PriceCache read price,$0.082→$0.072−12.2%
- PriceInput price,$0.10→$0.09−10.0%
- PriceCache read price,$0.032→$0.082+156%
- PriceInput price,$0.05→$0.10+100%
- PriceCache read price,$0.017→$0.032+88.2%
- PriceInput price,$0.035→$0.05+42.9%
- DelistedNo longer served,Delisted
- PriceCache read price,$0.032→$0.017−46.9%
- PriceInput price,$0.05→$0.035−30.0%
About
The cheapest provider for Nemotron 3.5 Lightning is Darkbloom at $0.0488 per 1M tokens (blended), charging $0.025 per 1M input and $0.12 per 1M output tokens. 5 providers serve it; the most expensive charges 2.1× the typical price. Context window: 1M tokens. Prices tracked since Oct 3, 2026.
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...
- Released
- Aug 11, 2026
- First tracked
- Oct 3, 2026
- Canonical slug
- nvidia/nemotron-3.5-lightning-20260807
- Weights
- nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16