Models.dev

An open-source database of AI models

Nemotron 3 Ultra 550B A55B

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

nvidia/nemotron-3-ultra-550b-a55b
Lab
Nvidia
Family
nemotron
Providers
24
Context
1,000,000
Output limit
128,000
Knowledge
-
Release
2026-06-04
Updated
2026-06-04
Weights
Open
Input
Output types
Capabilities
tools, reasoning, temperature

Providers

24
Provider Lab Model ID Context Output Price Reasoning Tool Call Structured Temperature
BasetenNvidianvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B202,800202,800$0.60 / $2.40YesYesYesYes
DevPass (LLM Gateway)Nvidianemotron-3-ultra-550b1,048,576128,000$0.50 / $2.20YesYes-Yes
Eden AINvidiadeepinfra/nemotron-3-ultra-550b-a55b262,144128,000$0.50 / $2.20YesYesYesYes
Eden AINvidiatogether_ai/nvidia/nemotron-3-ultra-550b-a55b512,288128,000$0.60 / $3.60YesYesYesYes
Eden AINvidianebius/nvidia/Nemotron-3-Ultra-550b-a55b1,048,576128,000$1.00 / $3.00YesYesYesYes
Fireworks AINvidiaaccounts/fireworks/models/nemotron-3-ultra-nvfp4262,144128,000$0.60 / $2.40YesYes-Yes
KenariNvidianemotron-3-ultra-550b-a55b1,000,000128,000$0.00 / $0.00YesYes-Yes
Kilo GatewayNvidianvidia/nemotron-3-ultra-550b-a55b512,288461,059$0.50 / $2.20YesYesYesYes
Kilo GatewayNvidianvidia/nemotron-3-ultra-550b-a55b:free1,000,00065,536$0.00 / $0.00YesYesNoYes
NanoGPTNvidianvidia/nemotron-3-ultra-550b-a55b1,000,00065,536$0.50 / $2.50YesYesNoYes
NanoGPTNvidianvidia/nemotron-3-ultra-550b-a55b:thinking1,000,00065,536$0.50 / $2.50YesYesNoYes
NvidiaNvidianvidia/nemotron-3-ultra-550b-a55b1,000,00065,536$0.50 / $2.50YesYesYesYes
Ollama CloudNvidianemotron-3-ultra262,144128,000-YesYes-Yes
OpenCode ZenNvidianemotron-3-ultra-free1,000,000128,000$0.00 / $0.00YesYes-Yes
OpenRouterNvidianvidia/nemotron-3-ultra-550b-a55b:free1,000,00065,536$0.00 / $0.00YesYesNoYes
OpenRouterNvidianvidia/nemotron-3-ultra-550b-a55b512,288461,059$0.60 / $3.60YesYesYesYes
PioneerNvidianvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF161,000,00065,000$0.50 / $2.50YesYes-Yes
RequestyNvidianemotron-3-ultra-550b-a55b1,048,57665,536$0.00 / $0.00YesYesNoYes
routing.runNvidianemotron-3-ultra131,07232,000$0.10 / $0.10YesYes-Yes
Together AINvidianvidia/nemotron-3-ultra-550b-a55b512,300512,300$0.60 / $3.60YesYesYesYes
UnoRouterNvidianemotron-3-ultra-550b-a55b:free1,000,000128,000$0.00 / $0.00YesYes-Yes
Venice AINvidianvidia-nemotron-3-ultra-550b-a55b256,00032,768$0.63 / $3.13YesYesYesYes
Vercel AI GatewayNvidianvidia/nemotron-3-ultra-550b-a55b1,000,00065,000$0.60 / $2.40YesYes-Yes
Weights & BiasesNvidianvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B262,144262,144$0.75 / $2.75YesYesYesYes
No rows match the current search.

No rows match the current search.

Menu

Esc

Search

No matching results.

How to use

Models.dev is a comprehensive open-source database of AI model specifications, pricing, and features.

The homepage starts with provider-agnostic model metadata. Model pages list the providers serving that model; provider pages list every model available from that provider; lab pages group canonical models by author.

API

You can access provider data, provider-agnostic model metadata, or the combined catalog through JSON endpoints.

Logos

Provider logos are available at /logos/{provider}.svg where {provider} is the provider ID. Lab logos are available at /logos/labs/{lab}.svg.

SDK

Use the SDK to query the API from your app. It's type-safe and exports the latest snapshot for offline use.

Contribute

The data is stored in GitHub as TOML files organized by provider and canonical model.