NVIDIA: Nemotron 3 Super

nvidia/nemotron-3-super-120b-a12b — available through the Autonomous Relay Agents API, served by NVIDIA NIM.

NVIDIA: Nemotron 3 Super has a 1,000,000-token context window and costs $0.085 per million input tokens and $0.40 per million output tokens, at the provider's list price on your own key.

Context length: 1,000,000 tokens
Input: $0.085 per M
Output: $0.40 per M
Served by: nvidia
Input modalities: text

Variants

The same model under another model id, priced or limited differently. Call it by its id; prices are per million tokens.

Variant	Model id	Context	Input	Output
NVIDIA: Nemotron 3 Super (free)	nvidia/nemotron-3-super-120b-a12b:free	262,144	$0.00 per M	$0.00 per M

This is a BYOK-only model: requests use your own provider key. Prices shown are the provider's list prices.

Call it

Any OpenAI-compatible client works: change the base URL and send this model id.

curl https://autonomousrelay.com/v1/chat/completions \
  -H "Authorization: Bearer $AUTONOMOUS_RELAY_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "nvidia/nemotron-3-super-120b-a12b", "messages": [{"role": "user", "content": "Hello"}]}'

Compare

In collections

A million tokens of context