MODELS / NVIDIA

Nemotron 3 Ultra

A 550B parameter (55B active) open reasoning model from NVIDIA, built for long-running agent workflows. It uses a hybrid Mamba-Transformer MoE architecture and supports a 1M token context window.

TEXTREASONINGREASONINGTOOL-USEIMPLICIT-CACHING
1M
CONTEXT WINDOW
65K
MAX OUTPUT TOKENS
$0.6 / 1M tokens
INPUT PRICE
$2.40 / 1M tokens
OUTPUT PRICE
QUICKSTART

Call it in one request.

OpenAI-compatible — change the base URL, and the setup is complete.

SHELL
curl https://enterprise.blackbox.ai/v1/chat/completions \
  -H "Authorization: Bearer $BLACKBOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "blackboxai/nvidia/nemotron-3-ultra-550b-a55b",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'
INPUT: textOUTPUT: textRELEASED: 2026-06-04
RELATED MODELS

Also worth a look.

NVIDIA

Nemotron 3 Nano 30B A3B

262.1K context · $0.05 / 1M tokens input · $0.24 / 1M tokens output

NVIDIA

NVIDIA Nemotron 3 Super 120B A12B

256K context · $0.15 / 1M tokens input · $0.65 / 1M tokens output

NVIDIA

Nvidia Nemotron Nano 12B V2 VL

131.1K context · $0.2 / 1M tokens input · $0.6 / 1M tokens output