Nemotron 3.5 Lightning 30B

nvidia/nemotron-3.5-lightning

A chat model with a 262K-token context window, at $0.0525 per million input tokens and $0.21 per million output tokens.

Details

Maker: nvidia
Kind: Chat
Context window: 262,144 tokens
Max output: 131,072 tokens
Input: $0.0525 per million tokens
Cached input: $0.0105 per million tokens, 80% off
Cache write: Same as input
Output: $0.21 per million tokens
Capabilities: Reasoning, tool use
Takes: Text
Returns: Text
Zero data retention: Not on every provider
No training on requests: Not on every provider
Released: 2026-08-11
Newer model: nvidia/nemotron-3.5-lightning-freeReleased later by the same maker, costs no more, and lists the same capabilities. Compare the two

Description

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 is a large language model (LLM) trained by NVIDIA. The model employs a hybrid Mixture-of-Experts architecture, utilizing interleaved Mamba-2 and MoE layers, along with select Attention layers. The Lightning 3.5 model is released alongside a number of speculative decoding methods for faster text generation. The model has 3B active parameters and 30B parameters in total.

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-lightning",
    "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