{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/nemotron-3-super/","md":"https://postcutoff.com/m/nemotron-3-super/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-super","name":"NVIDIA Nemotron 3 Super (120B-A12B)","org":"NVIDIA","family":"Nemotron 3","released":"2026-03-11","status":"current","type":"reasoning-llm","modality_in":["text"],"modality_out":["text"],"open_weights":true,"model_license":"nvidia-open-model-license","context_window":1000000,"max_output":null,"knowledge_cutoff":"2025-06","pricing":{"input":0.08,"output":0.45,"unit":"per 1M tokens (USD) on OpenRouter; NVIDIA hosted pricing not verified","source":"https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b"},"price_line":"$0.08 in, $0.45 out per 1M tokens","access":[{"provider":"NVIDIA API (build.nvidia.com)","model_id":"nvidia/nemotron-3-super-120b-a12b","endpoint":"https://integrate.api.nvidia.com/v1/chat/completions","docs":"https://build.nvidia.com"},{"provider":"AWS Bedrock","model_id":"nvidia.nemotron-super-3-120b","docs":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nemotron-super-3-120b.html"},{"provider":"OpenRouter","model_id":"nvidia/nemotron-3-super-120b-a12b","url":"https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b"},{"provider":"Hugging Face","url":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16"}],"capabilities":[{"name":"Efficient hybrid LatentMoE for agents","detail":"120B total / 12B active hybrid Mamba-2 + MoE + attention, built for high-volume agentic workloads with up to 1M context (256K default).","first":false,"discovered":"launch","source":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16"},{"name":"Managed on AWS Bedrock","detail":"One of the few NVIDIA open models offered as a serverless Bedrock model (nvidia.nemotron-super-3-120b).","first":false,"discovered":"later","source":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nemotron-super-3-120b.html"}],"entry":null,"notes":"Knowledge cutoff = pre-training (Jun 2025); post-training to Feb 2026. Also FP8/NVFP4 repos. Free tier on OpenRouter (:free).","verified":"2026-09-29","body_md":"Mid-size open reasoning model, widely hosted (Bedrock, NIM, OpenRouter).\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-super-120b-a12b\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}'\n```\n\nSources: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 , https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nemotron-super-3-120b.html","page_url":"https://postcutoff.com/m/nemotron-3-super/","events_after":2016,"major_after":466,"historic_after":89,"missing_at_launch":107,"events_since_release":null,"you_url":"https://postcutoff.com/you/nemotron-3-super/","briefings":{"xs":"https://postcutoff.com/briefings/cutoff-2025-06-xs.md","s":"https://postcutoff.com/briefings/cutoff-2025-06-s.md","m":"https://postcutoff.com/briefings/cutoff-2025-06-m.md","full":"https://postcutoff.com/briefings/cutoff-2025-06.md"}}