NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks. It is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.
All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.
| Parameter | Providers | Default |
|---|---|---|
| frequency_penalty | All providers | Not sent by default |
| include_reasoning | All providers | - |
| logit_bias | Some providers | - |
| max_tokens | All providers | - |
| min_p | Some providers | - |
| presence_penalty | All providers | Not sent by default |
| reasoning | All providers | - |
| reasoning_effort | All providers | - |
| repetition_penalty | Some providers | Not sent by default |
| response_format | Some providers | - |
| seed | Some providers | - |
| stop | All providers | - |
| structured_outputs | Some providers | - |
| temperature | All providers | 1 |
| tool_choice | Some providers | - |
| tools | Some providers | - |
| top_k | All providers | Not sent by default |
| top_p | All providers | 0.95 |