Nemotron 3 Ultra 550B A55B

NVIDIAKey nemotron-3-ultra-550b-a55bAlso reported as nvidia/nemotron-3-ultra-550b-a55b

Rank
#247
by active users
Active users
3
No change from 3 active users in the previous 30 days. vs previous 30 days
Adoption
0.3%
of 961 accounts
Tokens
88.5M
cache included
Est. cost
$17
at public list prices
First seen
Jun 5, 2026
in any submission

Oct 14 – Nov 12, 2026 (UTC)961 accounts100% of tokens from an identified modelData through Nov 12, 2026, 07:57 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

0 active users on Nov 12, 2026

Daily active users for Nemotron 3 Ultra 550B A55B, Oct 14, 2026 to Nov 12, 2026. Peak 2. Use the left and right arrow keys to read each day.210
Show daily values
Daily active users and tokens for Nemotron 3 Ultra 550B A55B
Date (UTC)Active usersTokens
Oct 14, 202600
Oct 15, 202600
Oct 16, 202600
Oct 17, 202600
Oct 18, 20261284K
Oct 19, 202600
Oct 20, 202600
Oct 21, 202600
Oct 22, 202600
Oct 23, 202600
Oct 24, 2026132.6K
Oct 25, 202600
Oct 26, 202600
Oct 27, 202600
Oct 28, 2026116.7M
Oct 29, 2026157.9M
Oct 30, 202612.5M
Oct 31, 202622.6M
Nov 1, 202618.4M
Nov 2, 202600
Nov 3, 202600
Nov 4, 202600
Nov 5, 202600
Nov 6, 202600
Nov 7, 202600
Nov 8, 202600
Nov 9, 202600
Nov 10, 202600
Nov 11, 202600
Nov 12, 202600

Token mix

How the 88.5M tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input10%
  • Output0.2%
  • Cache read90%
  • Cache write0%
  • Reasoning0%

Agents that carry Nemotron 3 Ultra 550B A55B

Each agent's share of this model's tokens, and how many accounts used the model through it.

  1. OpenCode100% of this model's tokens1active users
  2. Claude Code0.3% of this model's tokens1active users
  3. Pi<0.1% of this model's tokens2active users

Benchmarks

The best result for Nemotron 3 Ultra 550B A55B in each benchmark Tokscale tracks. Each benchmark has its own unit, run conditions and source, so compare a score only with other models on the same benchmark. Rank is among the models Tokscale matched in that benchmark.

All benchmarks

No benchmark that Tokscale tracks has a result for Nemotron 3 Ultra 550B A55B yet.

Pricing

List prices from models.dev in US dollars per 1M tokens, retrieved Nov 12, 2026. Nvidia is the lab's own API and the reference price for the estimates below.

Price at real agent usageEstimate at list prices

What 1M tokens cost at the reference list price when they split into input, output and cache the way Tokscale users' agents used them. It is not what anyone paid.

At this model's mix
$0
Est. per 1M tokens
90% cache reads
At the community mix
$0
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$0
Per 1M tokens at list prices
No cache

Cache reads were 90% of Nemotron 3 Ultra 550B A55B tokens in the last 30 days and 96% of all tokens. The 3:1 blend, (3 × input + output) ÷ 4, is the usual comparison and ignores cache.

Assumptions

  • Nvidia list prices per 1M tokens: input $0, output $0.
  • This model's mix is its own input, output, cache and reasoning tokens in the last 30 days.
  • The community mix is the tokens of every identified model in the last 30 days.
  • This is an estimate at list prices, not what anyone paid.
  • Reasoning tokens are priced as output.
  • Long-context tiers, batch pricing and discounts are not applied.
  • Token mixes come from public Tokscale submissions. Hidden accounts are excluded.
  • No cache-read price is listed, so cache reads are priced as input.
  • No cache-write price is listed, so cache writes are priced as input.

List prices by provider

  • NvidiaReferencenvidia/nemotron-3-ultra-550b-a55b
    $0 input per 1M tokens$0 output per 1M tokensCache read not listedCache write not listed1M tokens of context
  • OpenRouternvidia/nemotron-3-ultra-550b-a55b
    $0.60 input per 1M tokens$2.40 output per 1M tokens$0.12 cache read per 1M tokensCache write not listed262K tokens of context
  • Vercel AI Gatewaynvidia/nemotron-3-ultra-550b-a55b
    $0.60 input per 1M tokens$2.40 output per 1M tokens$0.12 cache read per 1M tokensCache write not listed1M tokens of context
  • Together AInvidia/nemotron-3-ultra-550b-a55b
    $0.60 input per 1M tokens$3.60 output per 1M tokens$0.20 cache read per 1M tokensCache write not listed512K tokens of context
  • Basetennvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
    $0.60 input per 1M tokens$2.40 output per 1M tokens$0.12 cache read per 1M tokensCache write not listed203K tokens of context

Specs

From models.dev (MIT), retrieved Nov 12, 2026, as the lab or the first listed provider reports them. A dash means models.dev does not list the value.

Context window
1M tokens
Max output
66K tokens
Input
Text
Output
Text
Knowledge cutoff
Sep 2025
Release date
Jun 4, 2026
Open weights
Yes
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used Nemotron 3 Ultra 550B A55B most in this period, by tokens. Hidden accounts are never listed.

  1. 1Tom@tradmangh88.2Mtokens$17est. cost6active days$17 est. cost · 6 active days
  2. 2xingguangcuican@xingguangcuican6666284Ktokens—est. cost1active daysno price · 1 active days
  3. 3Sunghyun Cho@anaclumos9.6Ktokens—est. cost1active daysno price · 1 active days

More from NVIDIA

Other NVIDIA models in the same period, by active users.

  1. Nemotron 3.5 Super VL Free3.0% adoption29active users
  2. Nemotron 3.5 Lightning Free2.1% adoption20active users
  3. Nemotron 3 Ultra Free1.1% adoption11active users
  4. Nemotron 3 Ultra 550B A55B Free1.0% adoption10active users
  5. Nemotron 3.5 Super VL0.5% adoption5active users
  6. Nemotron 3.5 Lightning 30B A3B0.3% adoption3active users
All models

Sources and attribution

Each score keeps its own source, unit and run conditions. Tokscale does not combine benchmarks into one score, and a missing score means the model was not evaluated, not that it scored zero.

  • models.devSpecs and list prices per provider.MIT · Retrieved Nov 12, 2026models.dev, an open catalog of AI models (github.com/anomalyco/models.dev).
  • TokscaleActive users, tokens and token mix from public Tokscale submissions. Hidden accounts are excluded.How we count