Why high: an exact fingerprint shared with 21 models that declare the same family, without a second signal of a different kind yet.
NVIDIA: Nemotron 3 Nano 30B A3B is NVIDIA's model. Its measured tokenizer sits with the Mistral group, which is evidence that it builds on the Mistral tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against NVIDIA's authorship of the model itself.
| We checked | What we found | Where it came from |
|---|---|---|
| How it counts tokens | Counts every one of the 50 test strings exactly like 21 other models | tk_0da8a999 |
| How its API is set up | A combination of settings no other listing in the catalogue uses | api_4b7aefd5 |
| How much it can read and write | Reads up to 262,144 tokens at onceOpenRouter's listing shows 235,929 output tokens, which is 90% of the context window, the figure it carries where the provider declares no maximum. | its own listing |
| Whether it thinks before answering | Reasons when asked to | its own listing |
| Who served our requests | Crusoe | we measured it, 21 August 2026 |
Click a row to open the full comparison.
We sent NVIDIA: Nemotron 3 Nano 30B A3B fifty short pieces of text and recorded what each one cost it in tokens. The bars below are those costs. Two models built on the same tokenizer produce the same bars; a model built on a different one produces a different set, which is what makes this a fingerprint.
Overhead subtracted: 16 prompt tokens.
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
defaults: {"temperature":null,"top_p":null,"frequency_penalty":null}
