Nemotron 3 Super

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models. The model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for the inference cost of only one, improving intelligence and generalization. Multi-environment RL training across 10+ environments delivers leading accuracy on benchmarks including AIME 2025, TerminalBench, and SWE-Bench Verified. Fully open with weights, datasets, and recipes under the NVIDIA Open License, Nemotron 3 Super allows easy customization and secure deployment anywhere — from workstation to cloud.

ChatNVIDIA1M tokens$0.0927 / $0.436 · 1M

nvidia/nemotron-3-super-120b-a12b

Contexto
1M tokens
Máx. completion
16,384
Tools
Sí
JSON
Sí
Lanzamiento
2026-03-11

Llámalo desde Geek Hub

El mismo SDK de OpenAI. Cambia el base URL y el id del modelo.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3-super-120b-a12b",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Consigue tu API key

Preguntas frecuentes

¿Qué es Nemotron 3 Super?
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models. The model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for the inference cost of only one, improving intelligence and generalization. Multi-environment RL training across 10+ environments delivers leading accuracy on benchmarks including AIME 2025, TerminalBench, and SWE-Bench Verified. Fully open with weights, datasets, and recipes under the NVIDIA Open License, Nemotron 3 Super allows easy customization and secure deployment anywhere — from workstation to cloud. Nemotron 3 Super corre en el API de Geek Hub (compatible con OpenAI). Id: nvidia/nemotron-3-super-120b-a12b.
¿Nemotron 3 Super es gratis?
No. El input cuesta $0.0927 / 1M tokens y el output $0.436 / 1M tokens en Geek Hub (markup incluido).
¿Cuál es el contexto de Nemotron 3 Super?
Nemotron 3 Super tiene una ventana de 1M tokens. Soporta hasta 16,384 tokens de completion.
¿Nemotron 3 Super soporta tool calling y structured outputs?
Nemotron 3 Super acepta tools y tool_choice para function calling. También soporta structured outputs con un JSON schema en response_format.
¿Cuándo se lanzó Nemotron 3 Super?
Nemotron 3 Super se lanzó el 11 de marzo de 2026.

Más modelos de NVIDIA