The Orchestrator › Models › NVIDIA
NVIDIA: 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
| Provider | NVIDIA |
| Model ID | nvidia/nemotron-3.5-lightning |
| Context window | 262K tokens (262,144) |
| Modalities | text → text |
| Tokenizer | Other |
| Router sources | OpenRouter, TrustedRouter, Vercel AI Gateway |
| Released | 2026-08-11 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Supported |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | nvidia/nemotron-3.5-lightning | $0.07 | $0.2 | 262K |
| free | OpenRouter | nvidia/nemotron-3.5-lightning:free | Free | Free | 1M |
| standard | TrustedRouter | nvidia/nemotron-3_5-lightning | $0.063 | $0.253 | 8K |
| standard | Vercel AI Gateway | nvidia/nemotron-3.5-lightning | $0.06 | $0.16 | 262K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.06 | $0.16 | 262K |
| 2026-11-14 | $0.063 | $0.253 | 8K |
| 2026-11-14 | $0.053 | $0.169 | 262K |
| 2026-11-14 | $0.07 | $0.2 | 262K |
Capabilities
Agentic tool useStructured outputs256K+ context windowControllable reasoningNo content storage (attested)Zero data retention
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p