GeniusRelay
EN中文Sign upConsole

NVIDIA: Nvidia Nemotron 3 Ultra 550B

nemotron-3-ultra-550b-a55b

CompareAPIGet an API keyGet an API key

Nvidia's Nemotron 3 Ultra 550B A55B model from the Nemotron 3 family. It uses a hybrid Mamba-Transformer MoE architecture.

Modalities

Text → Text

Input / output price

$0.650 / $3.25 per 1M

Context

512K · max output 66K

Capabilities

ReasoningTool callingLong contextOpen weights

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$0.650
Output$3.25
Cached input$0.195

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.00455
Per day
$2.27
Per month (30 days)
$68.25

Nvidia Nemotron 3 Ultra 550B: input $0.65/M · output $3.25/M · cached input $0.195/M

Request with these settings
curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "nemotron-3-ultra-550b-a55b", "max_tokens": 800,
       "messages": [{"role": "user", "content": "…"}]}'

Code samples

OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to nemotron-3-ultra-550b-a55b.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nemotron-3-ultra-550b-a55b",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Use it in a client: Cursor · Cline · SillyTavern · Codex

Parameters

Common OpenAI parameters can be passed as-is.

temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed

FAQ

How is Nvidia Nemotron 3 Ultra 550B billed?
Input is $0.650 and output is $3.25 per million tokens; cached input is $0.195. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
512K tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
Does it support streaming?
Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.