Host CoreWeave cut Nemotron 3.5 Lightning input pricing by 30%
Published 14 September 2026
Price move, per 1M tokens
- CoreWeave · input↓ 30%$0.100 → $0.070
- CoreWeave · output↓ 20%$0.25 → $0.20
- CoreWeave · cache read↓ 20%$0.050 → $0.040
| host | rate | was | now | change |
|---|---|---|---|---|
| CoreWeave | input | $0.100 | $0.070 | ↓ 30% |
| CoreWeave | output | $0.25 | $0.20 | ↓ 20% |
| CoreWeave | cache read | $0.050 | $0.040 | ↓ 20% |
input: ↓ 30%
If you buy
input-heavy workloads on this model at this host now stretch further, so re-check your cache-read share and output mix before your next top-up.
The model
Nemotron 3.5 Lightningopen the model →
Open weights31.6B parameters262K context7 hosts
intelligence125th of 168 writing139th of 168 coding115th of 168
Nemotron 3.5 Lightning is a downloadable text model from NVIDIA with a 262,144-token request limit and broad Arena coverage. Its coding score is its standout measured skill, while creative writing lags well behind.
Source
Read on openrouter.ai · we published this on 14 September 2026.
read the original at openrouter.ai ↗