NVIDIA Nemotron 3 Ultra
nemotron-3-ultranemotron-3-ultra-550bnemotron-3-ultra-550b-a55bnvidia-nemotron-3-ultra-550b-a55b- 🧠 Frontier open reasoning model built for long-running agents.
- 📏 550B total parameters, 55B active per token.
- 🔧 Hybrid Mamba-Transformer Mixture-of-Experts architecture.
- 📚 Supports up to 1M-token context for sustained agent sessions.
- ⚡ NVIDIA reports up to 5x faster inference, ~30% lower agentic cost.
- 🎯 Toggleable reasoning modes with an optional token budget.
- 🌐 Multilingual, with broad programming-language coverage.
- 🏢 Open weights for commercial use; NVFP4, FP8 and BF16 variants.
Nvidia Corporation is an American technology company founded in 1993 by Jensen Huang, Chris Malachowsky, and Curtis Priem, headquartered in Santa Clara, California. Long recognized as the dominant force in graphics processing units, Nvidia has expanded into a central pillar of…
Explore 4 more models by Nvidia →NVIDIA Nemotron 3 Ultra is the flagship, frontier-scale tier of NVIDIA's Nemotron 3 open-model family, released in 2026 and built specifically for orchestration, coding agents, deep research, and complex enterprise workflows. It is a 550B-parameter Mixture-of-Experts model that activates only 55B parameters per token, keeping throughput high even at long context lengths.
Architecturally, it pairs a hybrid Mamba-Transformer backbone with Mixture-of-Experts routing, and ships with toggleable reasoning modes plus an optional token budget for controlling effort. NVIDIA documents the model in its technical blog as engineered for faster, more efficient reasoning on long-running agents, reporting up to 5x faster inference and up to roughly 30% lower cost for agentic workloads versus prior approaches. Weights are published in NVFP4, FP8 and BF16 formats for commercial use.
Within the family, Ultra is the heavyweight reasoning tier above smaller, higher-volume siblings like NVIDIA Nemotron 3 Nano 30B and Nemotron Cascade 2 30B A3B, and complements the retrieval-focused Nemotron Embed VL 1B v2. NVIDIA positions Ultra for the harder calls in an agent pipeline, with smaller models handling routine execution. The published context window reaches up to 1M tokens; this catalog entry lists a 256K window with FP8 quantization.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
Daily usage · NVIDIA Nemotron 3 Ultra · Organic sellers
Top sellers · NVIDIA Nemotron 3 Ultra · Organic
- Relay Works68.5%
- Sapiens14.7%
- Fire Ant 🔥🐜9.1%
- ▲ Apex Ant6.5%
- Surplus-backed seller0.8%
- JOI SEED0.4%
| Seller | Health | Rep↓ | Sales | Tokens | Routing | Input $/M | Cached $/M | Output $/M | Save |
|---|---|---|---|---|---|---|---|---|---|
| ▲ Apex Ant 0x73b4…e736 | — | 81.71 | $0.01 | 56.01k | #1 | $0.31 | $0.09 | $1.56 | −48% |
| Relay Works 0x3040…7139 | — | 54.66 | $0.13 | 225.31k | gated | $0.26 | $0.063 | $1.144 | −57% |
| OpenCheap 0x0ee1…6c41 | — | 12.43 | — | — | gated | $0.4246 | $0.1158 | $1.9582 | −29% |
| Sapiens 0x1fae…8318 | healthy | 8.21 | $0.03 | 82.64k | gated | $0.3586 | $0.1076 | $1.7992 | −40% |
| Apex TEE Test 0xe672…7955 | — | 0.00 | — | — | gated | $0.72 | $0.72 | $4.32 | — |
| surplus-hive 0xe177…e91c | — | 0.00 | — | — | gated | $0.5062 | $0.5062 | $2.6322 | −16% |
| Fire Ant 🔥🐜 0xbe05…bc5d | — | 0.00 | $0.02 | 38.99k | gated | $0.4146 | $0.1458 | $1.9531 | −31% |
| Joi Gateway 0x8a90…7007 | — | 0.00 | — | — | gated | $0.305 | $0.305 | $1.525 | −49% |
| antseed-neon-puma-944e 0x6650…944e | — | 0.00 | — | — | gated | $0.2131 | $0.1875 | $1.0656 | −64% |
"Best price" and the seller table are live Antseed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = buyer trust score (0-100, the Antseed SDK's own formula). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on Antseed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.