NVIDIAAvailable

Nemotron 3 Ultra

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).

Try in ewpirenvidia/nemotron-3-ultra-550b-a55b

Opens in the ewpire workspace. Creating an account is free; runs are paid from your credits.

Nemotron 3 Ultra in plain words

Nemotron 3 Ultra is a text model from NVIDIA. It takes text as input and returns text. Its context window is 262,144 tokens. It costs 0.744706 credits per 1M input tokens and 2.978824 credits per 1M output tokens.

It is good at reasoning through multi-step problems and calling tools. It does not read images. A context window of 262,144 tokens holds about 1,000,000 characters of English text, at 4 characters a token.

For example, a question of 2,000 tokens (about 8,000 characters) with an answer of 1,000 tokens (about 4,000 characters) costs 0.004469 credits. The exact charge follows the usage the model reports for your request.

Details

Made by: NVIDIA
Good at: ReasoningTool use
Reads: Text
Produces: Text
Context window: 262,144 tokens

Price

Input, per 1M tokens: 0.744706 credits
Output, per 1M tokens: 2.978824 credits

Charged per request from your credit balance. No subscription. See pricing

In the API – coming soon

API keys are not open yet. The docs show how to call this model with the OpenAI SDK or plain HTTP once they are. Read the docs

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

The docs show how to list the models the API serves, with their capabilities and prices, once API keys are open. Models in the docs

Nemotron 3 Ultra in plain words

Details

Price

In the API – coming soon

Similar models

Cookies and your privacy