NVIDIA Nemotron 3 Ultra (550B-A55B)
Knowledge cutoff = pre-training data (Sep 2025); post-training data to May 2026. NVFP4 repo nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4.
- Context window
- 1,000,000 tokens
- Knowledge cutoff
- 2025-09
- Input
- text
- Output
- text
- License
- openmdw-1.1
- Pricing
- input: $0.6 · output: $2.4 (per 1M tokens (USD) on OpenRouter (262K context there); NVIDIA hosted pricing not verified) source
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| NVIDIA API (build.nvidia.com) | nvidia/nemotron-3-ultra-550b-a55b | https://integrate.api.nvidia.com/v1/chat/completions | docs |
| OpenRouter | nvidia/nemotron-3-ultra-550b-a55b | openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b | — |
| Hugging Face | — | huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 | — |
Notable capabilities (3)
- Hybrid Mamba-2 / LatentMoE at frontier scale: 550B total / 55B active; interleaved Mamba-2 and LatentMoE layers with select attention, plus multi-token prediction for faster generation. source
- NVFP4 pretraining and weights: Pre-trained with an NVFP4 recipe; weights published in both BF16 and NVFP4 under the permissive OpenMDW-1.1 license. source
- Reasoning on / off / medium: enable_thinking toggle in the chat template plus a medium-effort mode to cut reasoning tokens. source
NVIDIA's largest open reasoning model for agentic workflows and long-context analysis.
curl https://integrate.api.nvidia.com/v1/chat/completions -H "Authorization: Bearer $NVIDIA_API_KEY" -H "Content-Type: application/json" \
-d '{"model":"nvidia/nemotron-3-ultra-550b-a55b","messages":[{"role":"user","content":"Hello"}]}'
Sources: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 , https://integrate.api.nvidia.com/v1/models
Other NVIDIA models
NVIDIA Nemotron 3.5 Lightning (30B-A3B) · NVIDIA NemotronLabs VoiceChat 11B (and PersonaPlex-7B) · Cosmos 3 (Nano / Super) · NVIDIA Nemotron 3 Nano Omni (30B-A3B Reasoning) · Isaac GR00T N1.7 · NVIDIA Nemotron 3 Super (120B-A12B) · Cosmos Reason 2 · NVIDIA MagpieTTS Multilingual 357M · NVIDIA Parakeet / Canary / Nemotron Speech ASR (open) · Isaac GR00T N2 · Cosmos Predict 2.5 / Transfer 2.5 · Isaac GR00T N1 / N1.5 / N1.6