Nemotron 3 Super 120B a12b API

NVIDIA's Nemotron 3 Super 120B a12b, through an OpenAI-compatible API. 2 providers quote it now, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send nemotron-3-super-120b-a12b as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: nemotron-3-super-120b-a12b
Maker: NVIDIA
Context window: 254K · 1M tokens
Input price: $0.080 to $0.120 per million tokens
Output price: $0.346 to $0.380 per million tokens
Providers: 2 independent providers
Regions: us

Providers

amazee.ai: us, $0.080 input and $0.380 output per million tokens, $0.020 cache read per million tokens, 1M tokens of context
Pera: us, $0.120 input and $0.346 output per million tokens, $0.120 cache read per million tokens, $0.00052 fee for each request, 254K tokens of context

Scores

HLE: 20.8, #115 of 273
GPQA: 80.0, #104 of 250
AA-LCR: 65.7, #131 of 237
SciCode: 36.2, #107 of 123
Terminal-Bench Hard: 28.8, #63 of 166
τ²-Bench: 67.8, #82 of 169
IFBench: 71.5, #34 of 178

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nemotron-3-super-120b-a12b",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Nemotron 3 Super 120B a12b?: Nemotron 3 Super 120B a12b is a model from NVIDIA.
How much does Nemotron 3 Super 120B a12b cost?: Offers now ask $0.080 to $0.120 per million input tokens and $0.346 to $0.380 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Nemotron 3 Super 120B a12b?: The largest offer takes 1,048,576 input tokens. One job can generate up to 65,536 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Nemotron 3 Super 120B a12b do?: Its providers list Reasoning effort, JSON object, JSON schema, Frequency penalty, Presence penalty, Seed, Stop sequences, Top-p sampling, Text, Tools.
What inputs and outputs does Nemotron 3 Super 120B a12b support?: Text → Text.
Which providers serve Nemotron 3 Super 120B a12b?: 2 independent providers quote it now, with 2 offers. The table above ranks them by the cost of a typical job.
How do I call Nemotron 3 Super 120B a12b?: Send "nemotron-3-super-120b-a12b" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Nemotron 3 Super 120B a12b listed?: The exchange first listed it on 9/29/2026. This is not its release date.