Nemotron 3 Ultra

nvidia/nemotron-3-ultra-550b-a55b

A chat model with a 1M-token context window, at $0.63 per million input tokens and $2.52 per million output tokens.

Details

Maker: nvidia
Kind: Chat
Context window: 1,000,000 tokens
Max output: 65,000 tokens
Input: $0.63 per million tokens
Cached input: $0.126 per million tokens, 80% off
Cache write: Same as input
Output: $2.52 per million tokens
Capabilities: Reasoning, tool use
Takes: Text
Returns: Text
Zero data retention: Yes, on every provider
No training on requests: Yes, on every provider
Released: 2026-06-04
Newer model: nvidia/nemotron-3.5-super-vlReleased later by the same maker, costs no more, and lists the same capabilities. Compare the two

Description

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.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3-ultra-550b-a55b",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model