N
Nemotron 3 Ultra (batch)OPEN
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).
Prices update automatically — checked daily against provider list prices.
- $1.35 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 10% of the 191 open-weight models tracked here
- 10 of 10 NVIDIA models tracked here, from cheapest
Benchmarks
Artificial Analysis measures 273 of the 383 models tracked here — this one is not yet covered. The pricing position above is measured across the full catalog and does not depend on benchmarks.
About this model
Nemotron 3 Ultra (batch) is an open-weight AI model by NVIDIA. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Nemotron 3 Ultra (batch)?
Nemotron 3 Ultra (batch) is an AI language model from NVIDIA. It is open-weight: you can download it and run it on your own hardware, for free.
Is Nemotron 3 Ultra (batch) free?
The weights are free and open — you can self-host Nemotron 3 Ultra (batch) and pay nothing per token. If you prefer a hosted API, list prices are $0.6 per million input tokens and $3.6 per million output tokens.
Can I self-host Nemotron 3 Ultra (batch)?
Yes. Nemotron 3 Ultra (batch) has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.