NVIDIA: Nemotron 3.5 Lightning
by NVIDIANVIDIA: Nemotron 3.5 Lightning is a large language model from NVIDIA. It costs $0.080 per million input tokens and $0.200 per million output tokens. Its context window is 262K tokens.
- Input / 1M tokens
- $0.080
- Output / 1M tokens
- $0.200
- Cached input / 1M
- $0.040
- Context window
- 262K
On repeated prefixes
tokens
Who serves it cheapest
4 hosts serve Nemotron 3.5 Lightning. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| DarkbloomCheapestint4 | $0.065 | $0.180 | 262K | - | 99.9% |
| CoreWeavebf16 | $0.070 | $0.200 | 262K | - | 100.0% |
| Phala | $0.080 | $0.200 | 262K | - | 99.6% |
| DeepInfrabf16 | $0.080 | $0.200 | 262K | - | 99.9% |
The spread between Darkbloom and DeepInfra is 1.2× for identical weights. Quantization and context limits differ, so check both columns before switching.
Benchmarks
Independent scores published alongside the catalogue.
- Intelligence index
- 13.6
- Coding index
- 26.8
- Agentic index
- 6.1
About Nemotron 3.5 Lightning
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...
Specifications
| Model ID | nvidia/nemotron-3.5-lightning |
|---|---|
| Provider | NVIDIA |
| Context window | 262K tokens |
| Max output | 131K tokens |
| Input modalities | text |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | Yes - nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 |
| Released | August 11, 2026 |
Cheaper alternatives
Models that cost less than Nemotron 3.5 Lightning while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does NVIDIA: Nemotron 3.5 Lightning cost?
$0.080 per million input tokens and $0.200 per million output tokens. Cached input reads cost $0.040 per million tokens.
What is the context window of NVIDIA: Nemotron 3.5 Lightning?
262K tokens, with up to 131K tokens of output per request.
Which provider serves NVIDIA: Nemotron 3.5 Lightning cheapest?
Darkbloom at $0.065 per million input tokens - 1.2× cheaper than DeepInfra, the most expensive of the 4 hosts serving it.
Confirm against the source: NVIDIA official pricing.