NVIDIA's mid-size Nemotron 3 MoE model with 120B total and 12B active parameters, built for efficient reasoning and multi-agent applications.
OffRail routes requests to the best providers that are able to handle your prompt size and parameters.
NVIDIA's mid-size Nemotron 3 MoE model with 120B total and 12B active parameters, built for efficient reasoning and multi-agent applications. You can access it through OffRail's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Nemotron 3 Super 120B on OffRail starts at $0.30 per million input tokens and $0.90 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Nemotron 3 Super 120B supports a context window of up to 262,144 tokens on its largest provider deployment.
Nemotron 3 Super 120B is served by Nebius AI through OffRail. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Nemotron 3 Super 120B supports tool (function) calling and soft JSON output, but NOT strict JSON output schema (its upstream provider does not enforce it).
Nemotron 3 Super 120B was released on March 11, 2026.