{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/nemotron-3-ultra/","md":"https://postcutoff.com/m/nemotron-3-ultra/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"nemotron-3-ultra","name":"NVIDIA Nemotron 3 Ultra (550B-A55B)","org":"NVIDIA","family":"Nemotron 3","released":"2026-06-04","status":"current","type":"reasoning-llm","modality_in":["text"],"modality_out":["text"],"open_weights":true,"model_license":"openmdw-1.1","context_window":1000000,"max_output":null,"knowledge_cutoff":"2025-09","pricing":{"input":0.6,"output":2.4,"unit":"per 1M tokens (USD) on OpenRouter (262K context there); NVIDIA hosted pricing not verified","source":"https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b"},"price_line":"$0.60 in, $2.40 out per 1M tokens","access":[{"provider":"NVIDIA API (build.nvidia.com)","model_id":"nvidia/nemotron-3-ultra-550b-a55b","endpoint":"https://integrate.api.nvidia.com/v1/chat/completions","docs":"https://build.nvidia.com"},{"provider":"OpenRouter","model_id":"nvidia/nemotron-3-ultra-550b-a55b","url":"https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b"},{"provider":"Hugging Face","url":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"}],"capabilities":[{"name":"Hybrid Mamba-2 / LatentMoE at frontier scale","detail":"550B total / 55B active; interleaved Mamba-2 and LatentMoE layers with select attention, plus multi-token prediction for faster generation.","first":false,"discovered":"launch","source":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"},{"name":"NVFP4 pretraining and weights","detail":"Pre-trained with an NVFP4 recipe; weights published in both BF16 and NVFP4 under the permissive OpenMDW-1.1 license.","first":false,"discovered":"launch","source":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"},{"name":"Reasoning on / off / medium","detail":"enable_thinking toggle in the chat template plus a medium-effort mode to cut reasoning tokens.","first":false,"discovered":"launch","source":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"}],"entry":null,"notes":"Knowledge cutoff = pre-training data (Sep 2025); post-training data to May 2026. NVFP4 repo nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4.","verified":"2026-09-29","body_md":"NVIDIA's largest open reasoning model for agentic workflows and long-context analysis.\n\n```bash\ncurl https://integrate.api.nvidia.com/v1/chat/completions -H \"Authorization: Bearer $NVIDIA_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"nvidia/nemotron-3-ultra-550b-a55b\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}'\n```\n\nSources: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 , https://integrate.api.nvidia.com/v1/models","page_url":"https://postcutoff.com/m/nemotron-3-ultra/","events_after":1990,"major_after":455,"historic_after":86,"missing_at_launch":168,"events_since_release":null,"you_url":"https://postcutoff.com/you/nemotron-3-ultra/","briefings":{"xs":"https://postcutoff.com/briefings/cutoff-2025-09-xs.md","s":"https://postcutoff.com/briefings/cutoff-2025-09-s.md","m":"https://postcutoff.com/briefings/cutoff-2025-09-m.md","full":"https://postcutoff.com/briefings/cutoff-2025-09.md"}}