Nemotron 3.5 Lightning cut across 2 DeepInfra listings, by up to 25% at DeepInfra through OpenRouter (input and cache read)
Published 29 September 2026
Price move, per 1M tokens
- DeepInfra through OpenRouter · input↓ 25%$0.080 → $0.060
- DeepInfra through OpenRouter · output↓ 20%$0.20 → $0.16
- DeepInfra through OpenRouter · cache read↓ 25%$0.040 → $0.030
- DeepInfra's own listing · input↓ 25%$0.080 → $0.060
- DeepInfra's own listing · output↓ 20%$0.20 → $0.16
| host | rate | was | now | change |
|---|---|---|---|---|
| DeepInfra through OpenRouter | input | $0.080 | $0.060 | ↓ 25% |
| DeepInfra through OpenRouter | output | $0.20 | $0.16 | ↓ 20% |
| DeepInfra through OpenRouter | cache read | $0.040 | $0.030 | ↓ 25% |
| DeepInfra's own listing | input | $0.080 | $0.060 | ↓ 25% |
| DeepInfra's own listing | output | $0.20 | $0.16 | ↓ 20% |
DeepInfra through OpenRouter input and cache read: ↓ 25%DeepInfra's own listing input: ↓ 25%
If you buy
this cut makes the model easier to justify for high-volume, cache-heavy work, so re-check your cache-read share and whether your routing still fits how you use it.
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 29 September 2026.
read the original at openrouter.ai ↗