Nemotron 3 Ultra 550B a55b API

NVIDIA's Nemotron 3 Ultra 550B a55b, 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-ultra-550b-a55b 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-ultra-550b-a55b
Maker: NVIDIA
Context window: 262.1K · 1M tokens
Input price: $0.450 to $0.450 per million tokens
Output price: $0.044 to $1.900 per million tokens
Providers: 2 independent providers
Regions: us

Providers

Pera: us, $0.450 input and $0.044 output per million tokens, $0.450 cache read per million tokens, $0.00057 fee for each request, 262.1K tokens of context
amazee.ai: us, $0.450 input and $1.900 output per million tokens, $0.090 cache read per million tokens, 1M tokens of context

Scores

Intelligence: 11.8, #34 of 41
HLE: 28.4, #86 of 273
GPQA: 86.7, #62 of 250
AA-LCR: 79.3, #56 of 237
SciCode: 40.3, #94 of 123
Terminal-Bench Hard: 36.4, #35 of 166
τ²-Bench: 83.3, #60 of 169
IFBench: 81.4, #2 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-ultra-550b-a55b",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Nemotron 3 Ultra 550B a55b?: Nemotron 3 Ultra 550B a55b is a model from NVIDIA.
How much does Nemotron 3 Ultra 550B a55b cost?: Offers now ask $0.450 to $0.450 per million input tokens and $0.044 to $1.900 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 Ultra 550B a55b?: The largest offer takes 1,048,576 input tokens. One job can generate up to 32,768 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Nemotron 3 Ultra 550B a55b 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 Ultra 550B a55b support?: Text → Text.
Which providers serve Nemotron 3 Ultra 550B a55b?: 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 Ultra 550B a55b?: Send "nemotron-3-ultra-550b-a55b" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Nemotron 3 Ultra 550B a55b listed?: The exchange first listed it on 9/29/2026. This is not its release date.