We're excited to partner with NVIDIA to bring @cf/nvidia/nemotron-3-120b-a12b to Workers AI. NVIDIA Nemotron 3 Super is a Mixture-of-Experts (MoE) model with a hybrid Mamba-transformer architecture, 120B total parameters, and 12B active parameters per forward pass. The model is optimized for running many collaborating agents per application. It delivers high accuracy for reasoning, tool calling, and instruction following across complex multi-step tasks. Key capabilities:
Hybrid Mamba-transformer architecture delivers over 50% higher token generation throughput compared to leading open models, reducing latency for real-world applications Tool calling support for building AI agents that invoke tools across multiple conversation turns Multi-Token Prediction (MTP) accelerates long-form text generation by predicting several future tokens simultaneously in a single forward pass 32,000 token context window for retaining conversation history and plan states across multi-step agent workflows
Prompt cachingFor optimal performance with multi-turn conversations, send the x-session-affinity header with a unique session identifier to enable prompt caching. This routes requests to the same model instance, reducing latency and inference costs. For details, refer to Prompt caching. Use Nemotron 3 Super through the Workers AI binding (env.AI.run()), the REST API at /run or /v1/chat/completions, or the OpenAI-compatible endpoint. For more information, refer to the Nemotron 3 Super model page.
Fetched April 4, 2026