Compositev12
← All models Model directory

AI model

NVIDIA: Nemotron 3 Ultra (Free)

nvidia/nemotron-3-ultra-550b-a55b:free

NVIDIA: Nemotron 3 Ultra (Free) is a 1,000,000-token model free on Composite. Ranked #23 of 175 models by traffic on Composite over the last 30 days, taking 0.68% of tokens and 0.75% of requests. Measured on Composite, 97.0% of its last 100 requests on Composite succeeded, the typical first token arrives in 5459 ms, output runs at about 49.5 tokens per second.

Try in Playground

Community rating

— No community ratings yet.

Sign in to rate this model. Ratings come from accounts that have run requests through Composite.

Specifications

Specifications and pricing as served by Composite
Model IDnvidia/nemotron-3-ultra-550b-a55b:free
Providercv11
Context window1,000,000 tokens
Acceptstext
Returnstext
Input priceIncluded in free allowance
Output priceIncluded in free allowance
Prompt cachingNot offered for this model
ThinkingOptional - see "NVIDIA: Nemotron 3 Ultra (Free) (Reasoning)" in the catalog to turn it on by default
ModeratedNo
Cost on a monthly planFree - does not spend plan credits
Routing endpoints1

Use NVIDIA: Nemotron 3 Ultra (Free) in JanitorAI or SillyTavern

Make a Composite API key and type nvidia/nemotron-3-ultra-550b-a55b:free as the model name. JanitorAI takes the full URL https://composite.lucidity.sh/v1/chat/completions; SillyTavern, ChubAI, Agnai and RisuAI take https://composite.lucidity.sh/v1.

JanitorAI setup · SillyTavern setup · Best Janitor AI proxies compared

Traffic rank on Composite

#23 of 175

0.68% of tokens and 0.75% of requests over 30 days.

Success rate

97.0%

Across the last 100 requests Composite served for this model.

Time to first token

5459 ms

Median across the same sample.

Output speed

49.5 tok/s

Median generation rate after the first token.

Prompt cache hits

47.8%

Share of prompt tokens served from the provider's cache over 7 days.

Pricing

Free - 80 requests/day shared across free models

Credits pay the provider’s price plus 25%; cache hits cost less.

Monthly plans serve this model without spending any of their included credits.

Provider

cv11

Roleplay fit

Nemotron models are tuned by NVIDIA for instruction-following and tool use, and tend to behave predictably in structured prompts.

Context behavior

With a 1,000,000-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.

Cost for regular use

It is free on Composite, which makes it a reasonable place to test a character card, preset or lorebook before connecting your own provider.

From the provider

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

Supplied by cv11, not written by Composite.