NVIDIA Nemotron 3.5 Super VL

nvidia/nemotron-3.5-super-vl

A chat model with a 1M-token context window, at $0.21 per million input tokens and $0.525 per million output tokens.

Details

Maker: nvidia
Kind: Chat
Context window: 1,048,576 tokens
Max output: 1,048,576 tokens
Input: $0.21 per million tokens
Cached input: $0.042 per million tokens, 80% off
Cache write: Same as input
Output: $0.525 per million tokens
Capabilities: Reasoning, tool use, vision
Takes: Text, image, video
Returns: Text
Zero data retention: Not on every provider
No training on requests: Not on every provider
Released: 2026-10-15

Description

NVIDIA Nemotron 3.5 Super VL is a vision-language model for reasoning, coding, tool use, and document understanding. Its hybrid Mamba-2, attention, and Mixture-of-Experts architecture has 120B total parameters with 12B active per token. Baseten serves text and image inputs with up to one million tokens of context for long conversations and agent workflows.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3.5-super-vl",
    "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