Catalog Changes · 2026-10-14 00:05:18.286935

NVIDIA: Nemotron 3 Ultra · 2026-10-14 00:05:18.286935 UTC

Current Model Listing

OpenRouter

6 Changed Fields

Field / Array Position Previous Value Observed Value
Benchmarks · Design Arena[1] · Elo 1098 1097
Benchmarks · Design Arena[3] · Elo 1142 1141
Benchmarks · Design Arena[3] · Rank 82 83
Benchmarks · Design Arena[5] · Elo 1069 1068
Benchmarks · Design Arena[6] · Rank 79 78
Benchmarks · Design Arena[7] · Elo 1144 1145
← Back To Results

NVIDIA: Nemotron 3 Ultra

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

OpenRouter Catalog Changes

Last Observed: 2026-10-14 12:02:50.667017 UTC

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...

Architecture And Modalities · 3
Architecture · Instruct Type
API Details

/architecture/instruct_type

Explicit Null

Explicit Null
Architecture · Modality
API Details

/architecture/modality

text->text

text->text
Architecture · Tokenizer
API Details

/architecture/tokenizer

Other

Other
Benchmarks · 3
Benchmarks · Artificial Analysis · Agentic Index
API Details

/benchmarks/artificial_analysis/agentic_index

20.1

20.1
Benchmarks · Artificial Analysis · Coding Index
API Details

/benchmarks/artificial_analysis/coding_index

49.3

49.3
Benchmarks · Artificial Analysis · Intelligence Index
API Details

/benchmarks/artificial_analysis/intelligence_index

22.9

22.9
Catalog Identity And Metadata · 11
Canonical Slug
API Details

/canonical_slug

nvidia/nemotron-3-ultra-550b-a55b-20260604

nvidia/nemotron-3-ultra-550b-a55b-20260604
Context Tokens
API Details

/context_length

262144

262,144
Created
API Details

/created

1780551208

2026-06-04 05:33:28 UTC
Description
API Details

/description

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...

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...
Expiration Date
API Details

/expiration_date

Explicit Null

Explicit Null
Hugging Face Id
API Details

/hugging_face_id

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
Id
API Details

/id

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

nvidia/nemotron-3-ultra-550b-a55b
Knowledge Cutoff
API Details

/knowledge_cutoff

Explicit Null

Explicit Null
Links · Details
API Details

/links/details

/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints

/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b-20260604/endpoints
Name
API Details

/name

NVIDIA: Nemotron 3 Ultra

NVIDIA: Nemotron 3 Ultra
Supported Voices
API Details

/supported_voices

Explicit Null

Explicit Null
Default Parameters · 6
Default Parameters · Frequency Penalty
API Details

/default_parameters/frequency_penalty

Explicit Null

Explicit Null
Default Parameters · Presence Penalty
API Details

/default_parameters/presence_penalty

Explicit Null

Explicit Null
Default Parameters · Repetition Penalty
API Details

/default_parameters/repetition_penalty

Explicit Null

Explicit Null
Default Parameters · Temperature
API Details

/default_parameters/temperature

1

1
Default Parameters · Top K
API Details

/default_parameters/top_k

Explicit Null

Explicit Null
Default Parameters · Top P
API Details

/default_parameters/top_p

0.95

0.95
Request Limits · 1
Per Request Limits
API Details

/per_request_limits

Explicit Null

Explicit Null
Pricing · 3
Output Price · USD/Token
API Details

/pricing/completion

0.0000024

0.0000024
Pricing · Input Cache Read
API Details

/pricing/input_cache_read

0.00000012

0.00000012
Input Price · USD/Token
API Details

/pricing/prompt

0.0000006

0.0000006
Reasoning · 4
Reasoning · Default Effort
API Details

/reasoning/default_effort

high

high
Reasoning · Default Enabled
API Details

/reasoning/default_enabled

True

True
Reasoning · Mandatory
API Details

/reasoning/mandatory

False

False
Reasoning · Supports Max Tokens
API Details

/reasoning/supports_max_tokens

True

True
Provider Limits · 3
Top Provider · Context Length
API Details

/top_provider/context_length

202800

202,800
Top Provider · Is Moderated
API Details

/top_provider/is_moderated

False

False
Top Provider · Max Completion Tokens
API Details

/top_provider/max_completion_tokens

182520

182,520
API Structure And Container Types
Architecture
API Details

/architecture

Object · See Fields

Object · See Fields
Architecture · Input Modalities
API Details

/architecture/input_modalities

Array · See Items

Array · See Items
Architecture · Output Modalities
API Details

/architecture/output_modalities

Array · See Items

Array · See Items
Benchmarks
API Details

/benchmarks

Object · See Fields

Object · See Fields
Benchmarks · Artificial Analysis
API Details

/benchmarks/artificial_analysis

Object · See Fields

Object · See Fields
Benchmarks · Design Arena
API Details

/benchmarks/design_arena

Array · See Items

Array · See Items
Default Parameters
API Details

/default_parameters

Object · See Fields

Object · See Fields
Links
API Details

/links

Object · See Fields

Object · See Fields
Pricing
API Details

/pricing

Object · See Fields

Object · See Fields
Reasoning
API Details

/reasoning

Object · See Fields

Object · See Fields
Reasoning · Supported Efforts
API Details

/reasoning/supported_efforts

Array · See Items

Array · See Items
Supported Parameters
API Details

/supported_parameters

Array · See Items

Array · See Items
Top Provider
API Details

/top_provider

Object · See Fields

Object · See Fields

Architecture · Input Modalities

1 items · source order preserved

  • text
API Details
Item /architecture/input_modalities/*
1 text

Architecture · Output Modalities

1 items · source order preserved

  • text
API Details
Item /architecture/output_modalities/*
1 text

Supported Parameters

18 items · source order preserved

  • frequency_penalty
  • include_reasoning
  • logit_bias
  • max_tokens
  • min_p
  • presence_penalty
  • reasoning
  • reasoning_effort
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_p
API Details
Item /supported_parameters/*
1 frequency_penalty
2 include_reasoning
3 logit_bias
4 max_tokens
5 min_p
6 presence_penalty
7 reasoning
8 reasoning_effort
9 repetition_penalty
10 response_format
11 seed
12 stop
13 structured_outputs
14 temperature
15 tool_choice
16 tools
17 top_k
18 top_p

Benchmarks · Design Arena

8 items · source order preserved

Item Arena Category Elo Rank Win Rate
1 models 3d 1132 74 39
2 models asciiart 1097 60 37.5
3 models codecategories 1148 83 36
4 models dataviz 1141 83 37.3
5 models gamedev 1142 77 36.3
6 models svg 1068 69 32.4
7 models uicomponent 1142 78 36.2
8 models website 1145 91 35
API Details
Item /benchmarks/design_arena/*/arena /benchmarks/design_arena/*/category /benchmarks/design_arena/*/elo /benchmarks/design_arena/*/rank /benchmarks/design_arena/*/win_rate
1 models 3d 1132 74 39
2 models asciiart 1097 60 37.5
3 models codecategories 1148 83 36
4 models dataviz 1141 83 37.3
5 models gamedev 1142 77 36.3
6 models svg 1068 69 32.4
7 models uicomponent 1142 78 36.2
8 models website 1145 91 35

Reasoning · Supported Efforts

2 items · source order preserved

  • high
  • medium
API Details
Item /reasoning/supported_efforts/*
1 high
2 medium