Nvidia Nemotron 3.5 Lightning
Nvidia Nemotron 3.5 Lightning is an open-weight 30B-A3B hybrid Mamba-Transformer mixture-of-experts model for high-throughput agentic, coding, tool-use, instruction-following, and long-context workloads. Thinking is disabled on this variant.
- Reasoning
- Tool Calling
- Parallel Tool Calls
Added Aug 12, 2026
Model weightsPricing
Auto routing · per 1M tokens- Input
- $0.05
- Output
- $0.20
- Cache read
- $0.01
Specifications
- Context window
- 262.1K
- Max output
- 65.5K
- Parameters
- 30B / 3B
- Total / active
Benchmarks
No public benchmark scores for this model yet.
Providers
Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)
| $0.05 | $0.20 | $0.01 | N/A | N/A | |
| $0.05 | $0.20 | $0.01 | N/A | N/A | |
| $0.021 | $0.101 | N/A | N/A | N/A | |
| $0.0525 | $0.21 | $0.0105 | N/A | N/A | |
| $0.063 | $0.168 | $0.0315 | N/A | N/A | |
| $0.0735 | $0.21 | $0.042 | N/A | N/A | |
| $0.0735 | $0.21 | $0.042 | N/A | N/A |
Privacy:ZDR, prompts not retainedNo training on promptsRetention and training unclear
Batch API
Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.