NVIDIA's compact Nemotron 3 MoE model with 30B total and 3B active parameters, offering toggleable reasoning and long context at low cost.
LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.
NVIDIA's compact Nemotron 3 MoE model with 30B total and 3B active parameters, offering toggleable reasoning and long context at low cost. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Nemotron 3 Nano 30B on LLM Gateway starts at $0.06 per million input tokens and $0.24 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Nemotron 3 Nano 30B supports a context window of up to 262,144 tokens on its largest provider deployment.
Nemotron 3 Nano 30B is served by Nebius AI through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Nemotron 3 Nano 30B supports tool (function) calling, but not structured JSON output mode.
Nemotron 3 Nano 30B was released on December 15, 2025.