NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
nvidia/nemotron-3-super-120b-a12bNemotron 3 Super is an API model from NVIDIA, released on Mar 11, 2026, with a context window of 1,000,000 tokens, pricing of $0.085 per million input tokens and $0.4 per million output tokens. It accepts text input and produces text output.
At listed prices, a request with 10,000 input tokens and 1,000 output tokens costs about $0.0013.
Specs are sourced from OpenRouter and were last checked on Aug 14, 2026. Always confirm current pricing and limits with the provider before production use.
Nemotron 3 Super supports a context window of 1,000,000 tokens.
Nemotron 3 Super is listed at $0.085 per million input tokens and $0.4 per million output tokens on OpenRouter.
Nemotron 3 Super was published on Mar 11, 2026.
Nemotron 3 Super accepts text input and produces text output.