← all models
Nemotron 3 Ultra
nvidia · 55B active
openrouter
ollama cloud
free tier
Parameters
550B
openrouter api · from the model id
Context
256K
262144 tokens
Input
$0.50
OpenRouter · cheapest output
Output
$2.20
OpenRouter · cheapest output
Cache read
$0.10
OpenRouter · cheapest output
Providers
Accepts
text
Capabilities
frequency_penalty
include_reasoning
logit_bias
logprobs
max_tokens
min_p
presence_penalty
reasoning
reasoning_effort
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_logprobs
top_p
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...
Also known as
openrouter
nvidia/nemotron-3-ultra-550b-a55b
ollama
nemotron-3-ultra
huggingface
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
version slug
nvidia/nemotron-3-ultra-550b-a55b-20260604
name
NVIDIA: Nemotron 3 Ultra
display name
Nemotron 3 Ultra
Identifiers
- Vendor
-
nvidia
- OpenRouter
-
nvidia/nemotron-3-ultra-550b-a55b
- Ollama
-
nemotron-3-ultra
- Hugging Face
-
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
- Version slug
-
nvidia/nemotron-3-ultra-550b-a55b-20260604
- Active parameters
-
55B
- Released
-
2026-06-04T05:33:28.000Z
- First seen
-
59 d ago
- Last crawled
-
28 min ago