Last refreshed 2026-11-18. Next refresh: weekly.
Why use Nemotron 3.5 Lightning on FlexAI?
FlexAI offers Nemotron 3.5 Lightning with pay-as-you-go pricing at $0.06/1M input tokens. FlexAI operates Token Factory, an OpenAI-compatible inference API for open models, plus dedicated GPU endpoints, fine-tuning, training, and private-cloud AI Factory deployments.
Compare Nemotron 3.5 Lightning across 3 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: NVIDIA-Nemotron-3.5-Lightning-30B-A3BNVIDIA-Nemotron-3.5-Lightning-30B-A3BRequest example
NVIDIA-Nemotron-3.5-Lightning-30B-A3B.Gotchas
- Use provider model ID "NVIDIA-Nemotron-3.5-Lightning-30B-A3B", not the LLMReference slug "nemotron-3.5-lightning".
Compare Nemotron 3.5 Lightning Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| OpenRouter | $0.06 | $0.16 |
| Vercel AI Gateway | $0.05 | $0.20 |
| FlexAI | $0.06 | $0.16 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.06 |
| Output tokens | $0.16 |
Capabilities
About Nemotron 3.5 Lightning
NVIDIA Nemotron 3.5 Lightning (HF nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B) is an open-weight hybrid Mamba-Transformer mixture-of-experts text model with 30B total and 3B active parameters (NemotronHForCausalLM), released 11 August 2026. NVIDIA lists context up to 1M tokens (256K used for single-H100 deployment). Weights ship in BF16, NVFP4 and speculative-decoding (DSpark/DFlash) variants plus a base checkpoint under OpenMDW 1.1. It is offered on build.nvidia.com and OpenRouter (free tier).