Why high: an exact fingerprint shared with 1 model that declares the same family, without a second signal of a different kind yet.
Google: Gemma 4 26B A4B is Google's model. Its measured tokenizer sits with the Gemma group, which is evidence that it builds on the Gemma tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against Google'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 1 other model | tk_ba03436b |
| How its API is set up | A combination of settings no other listing in the catalogue uses | api_0c93a24e |
| 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 | NextBit | we measured it, 21 August 2026 |
Click a row to open the full comparison.
We sent Google: Gemma 4 26B A4B 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: 13 prompt tokens.
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
defaults: {"temperature":1,"top_p":0.95,"top_k":64}
