Google: Gemma 4 31B 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.
| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Exact match with 1 other model | tk_ba03436b |
| API surface | No other entry shares this exact contract | api_6e963360 |
| Context and output | 262,144 context · 262,144 max output | declared |
| Reasoning contract | Optional | declared |
| Serving providers observed | DeepInfra | measured 21 August 2026 |
Click a row to open the full comparison.
An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 13 prompt tokens.
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
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,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}
Cite this page as the evidence record for Google: Gemma 4 31B: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings. The raw data behind every figure is on the data page.
