Collaborative agente caballo de batalla activating 12B out de 120B parámetros, ofreciendo insignia-grade razonamiento un alto batch rendimiento.
Technical Specifications
- Provider
- NVIDIA
- Category
- open-source
- Release Date
- 2026-03
- Batch API Discount
- 50% off async batch
- Consumer Subscription
- Free / Self-Hosted
- Reasoning Effort Control
- Configurable (Low / Med / High)
- Structured Outputs
- Yes
- Output Modalities
- text
- Official Documentation
- Visit Official Docs ↗
Data Privacy, Licensing & Deployment Governance
Official Provider Release Intelligence, API Quotas & Agentic Specs
- Official API Model ID (SDK String)
- nemotron-3-super-120b-a12b
- Supported SDK & API Protocol
- OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
- Lifecycle & Deprecation Status
- Active GA (Guaranteed support through 2028+)
- Production Rate Limits (RPM & TPM)
- Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
- Long-Context Pricing Tier (>128K / >200K)
- Flat rate ($0.3/1M in) across full 262K window
- Prompt Cache Write & TTL Policy
- Cached input at $0.06/1M tokens
- Computer Use & Browser GUI Agent
- API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
- MCP & Parallel Tool Calling
- Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
- Web Search Grounding & Code Sandbox
- Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools
- Fine-Tuning & Distillation Support
- Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
- Multimodal Tokenization Billing
- Text BPE (~4 chars/token)
- Weights Precision & Quantization
- BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
- Minimum GPU VRAM Requirement
- 74 GB VRAM (4-bit Quantized) · 258 GB VRAM (Native BF16)
- Supported Inference Engines
- vLLM, SGLang, Ollama, llama.cpp, TensorRT-LLM, HuggingFace TGI
- System Card & Safety Framework
- Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma)
- Enterprise Compliance (SOC2 / HIPAA / ZDR)
- 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
Nemotron 3 Super 120B A12B Cost, Context, Hardware & API Integration
For single-user chat, a $20/mo subscription caps your bill below this API volume.
Break-even point: ~439 requests/day equals $20/month.
Same Monthly Workload Cost Across Popular Reference Models
Live Prompt Paste Tokenizer & Cost Counter
Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.
Hybrid Prompt Routing Cascade Simulator
Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Nemotron 3 Super 120B A12B:
Benchmark Scores & 6-Axis Capability Radar
- SWE-bench Verified
- 51%
- GPQA Diamond
- 64.5%
- MMLU-Pro
- 82.8%
- HumanEval
- 91.5%
- Terminal-Bench
- 45%
- AIME
- 74%
- Long-Context Reasoning
- 82%
- Chatbot Arena Elo
- 1350pts
Strengths
- 12B activo parámetro inferencia velocidad paired con 120B total capacidad knowledge
- Outstanding 262K contexto handling con zero needle-en-un-haystack dropoff
- Engineered specifically para autónomo multi-agente swarm coordination
Limitations & Trade-offs
- requiere dual 80GB empresarial GPUs para local implementación
- texto-solo sin nativo multimodal imagen inputs
Editorial Assessment
el ideal empresarial caballo de batalla balancing abierto accessibility con superior-nivel inteligencia.
Best for: empresarial multi-agente architectures, masivo datos extracción, y autónomo codificación
Compare Nemotron 3 Super 120B A12B
Frequently Asked Questions about Nemotron 3 Super 120B A12B
How much does the Nemotron 3 Super 120B A12B API cost per 1M tokens?+
Nemotron 3 Super 120B A12B by NVIDIA is priced at $0.3 per 1M input tokens and $0.8 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.06 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.
Should I use a $20/month subscription or the Nemotron 3 Super 120B A12B pay-as-you-go API?+
A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.
How many words and pages fit in Nemotron 3 Super 120B A12B's context window?+
Nemotron 3 Super 120B A12B features a 262K tokens context window, which equals approximately 196,608 English words or ~524 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 32,768 tokens.
Can I run Nemotron 3 Super 120B A12B locally on my own GPU (Open Weights)?+
Yes, Nemotron 3 Super 120B A12B (120B (12B active MoE)) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.
Does NVIDIA train on data sent to the Nemotron 3 Super 120B A12B API, and is commercial use allowed?+
100% Isolated when self-hosted on private GPUs or VPC. License tier: Open-Weights Research & Commercial License. Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.
How does Nemotron 3 Super 120B A12B perform on coding and reasoning benchmarks?+
Nemotron 3 Super 120B A12B achieves a composite Intelligence Index of 53/100, scoring 51% on SWE-bench Verified, 64.5% on GPQA Diamond, 82.8% on MMLU-Pro, and 1350 pts on Chatbot Arena Elo.
What is Nemotron 3 Super 120B A12B best used for?+
Nemotron 3 Super 120B A12B is best suited for: empresarial multi-agente architectures, masivo datos extracción, y autónomo codificación. Assessment: el ideal empresarial caballo de batalla balancing abierto accessibility con superior-nivel inteligencia.
NVIDIA Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to NVIDIA's flagship reasoning tier:
Nemotron 3 Ultra 550B A55B
Nemotron 3.5 Content Safety
Nemotron 3 Nano Omni 30B A3B Reasoning
Nemotron 3 Content Safety
Nemotron VoiceChat
Nemotron Cascade 2 30B A3B
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to Nemotron 3 Super 120B A12B:
La unidad básica de texto que procesa un modelo de lenguaje, que normalmente equivale a 3 o 4 caracteres o aproximadamente 0,75 palabras. Por ejemplo, una frase típica se divide en varios tokens.
Un conjunto estandarizado de pruebas para evaluar y comparar objetivamente las capacidades de distintos modelos de IA en tareas como programación (SWE-bench) o matemáticas avanzadas (AIME).
La cantidad máxima de tokens que un modelo puede considerar a la vez, incluyendo tanto la entrada que lee como la salida que genera. Una ventana de 1.000.000 de tokens puede procesar unas 750.000 palabras en una sola petición.
Un modelo de IA entrenado para invertir cómputo adicional en pensar y validar hipótesis lógicas antes de responder, diseñado para problemas complejos de ingeniería y matemáticas.
Una técnica de razonamiento paso a paso donde el modelo genera pensamientos intermedios antes de formular la respuesta final, mejorando radicalmente la resolución de problemas matemáticos y lógicos.
La capacidad de un modelo de detectar la necesidad de una función externa y emitir argumentos JSON estructurados para ejecutar API, búsquedas web o consultas a bases de datos.
Las puntuaciones de benchmarks, precios por token y límites de tasa evolucionan rápidamente. Verifique siempre las especificaciones actuales en la documentación oficial del proveedor.