Home / NVIDIA / Nemotron / Nemotron 3.5 Lightning
Nemotron 3.5 Lightning API price
nvidia/nemotron-3.5-lightning
The cheapest Nemotron 3.5 Lightning API is $0.05/M input at RunInfra (inference host) - all 4 providers compared below, per 1M tokens.
SmallNVIDIA262K context4 sellers
Input
$0.05
per 1M tokens · RunInfra (inference host)
up to $0.10
Output
$0.15
per 1M tokens · RunInfra (inference host)
up to $0.25
Where to buy it
Cheapest Nemotron 3.5 Lightning API providers compared - 4 sellers, from $0.05/M.
| Provider | Input $/M | Output $/M | Cached in | TPS | Uptime |
|---|---|---|---|---|---|
| RunInfra (inference host) | 0.050cheapest | 0.150 | 0.010 | 541 | - |
| DeepInfra (via OpenRouter)bf16 | 0.080 | 0.200 | 0.040 | - | 99.8% |
| CoreWeave (via OpenRouter)bf16 | 0.100 | 0.250 | 0.050 | - | 100% |
| TokenRouter (aggregator) | 0.100 | 0.250 | 0.050 | - | - |
2.0× between the cheapest and the dearest of 4 sellers.
Against its tier
- This model$0.20
- Cheapest · Qwen 3.7 Flash$0.16
- Tier median · GPT 5.6 Luna Pro$0.70
- Dearest · Claude Haiku 4.5$6.00
#4 of 17 small · cheaper than 81%
Details
- Context window
- 262K262,144 tokens
- Developer
- NVIDIA
- Intelligence
- 23.6
- Sellers
- 42.0× spread
- Cached input
- $0.01where the source publishes one
- Cheapest at
- RunInfra (inference host)
- Combined
- $0.20in + out per 1M
- Last checked
- 2026-08-28
- Throughput
- 540.9 tok/sas published by RunInfra (inference host)
- Availability
- 99.89%median of 2 OpenRouter endpoints, last 30 min