AI Desk · AI FingerprintingWithdrawn *

Google: Gemma 4 31B (batch)

google/gemma-4-31b-it:batch · GoogleDeclared and measured agree

Tokenizer lineage (measured): Gemma
Declared tokenizer tag: Gemma
Entered catalogue: 2 April 2026
Measurement: Variant: inherits its base model’s measurement
Evidence confidence: High

Why high: inherited from google/gemma-4-31b-it: a serving variant shares its base model's tokenizer.

Evidence

✓ inherited from google/gemma-4-31b-it: a serving variant shares its base model's tokenizer

Compare with Google: Gemma 4 31B

Report a correction

This entry is a serving variant of Google: Gemma 4 31B. A variant shares its base model's tokenizer by construction, so the measurement lives on the base record and this page inherits it.

Identity statement

Google: Gemma 4 31B (batch) 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.

What we checked

Four different kinds of evidence, and what each one showed

We checked	What we found	Where it came from
How it counts tokens	Not measured yet	we measured it
How its API is set up	A combination of settings no other listing in the catalogue uses	api_91f95cf7
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

Declared record

What the catalogue claims about this model

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...

Modalities: text+image+video->text
Declared tokenizer: Gemma
Prompt price: $0.39 / M tokens
Completion price: $0.97 / M tokens

Supported parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

defaults: {"temperature":1,"top_p":0.95,"top_k":64,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}

Catalogue entry Weights on Hugging Face

History

Every observation, kept as taken

2 April 2026Enters the OpenRouter catalogue declared as Gemma.

* Google: Gemma 4 31B (batch) no longer appears in the OpenRouter catalogue, first absent from the snapshot of 16 September 2026. The record stays because the measurements above were real when they were taken and this address has been published.