NVIDIA's open MoE model (30B total, 3B active) for high-throughput agentic workloads.
LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.
NVIDIA's open MoE model (30B total, 3B active) for high-throughput agentic workloads. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Nemotron 3.5 Lightning on LLM Gateway starts at $0.08 per million input tokens and $0.20 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Nemotron 3.5 Lightning supports a context window of up to 262,144 tokens on its largest provider deployment.
Nemotron 3.5 Lightning is served by DeepInfra through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Yes. Nemotron 3.5 Lightning supports both tool (function) calling and strict JSON output schema (upstream-enforced) through LLM Gateway.
Nemotron 3.5 Lightning was released on August 11, 2026.