Gemma 4 31B
Google’s largest open Gemma: a 31-billion-parameter model that reads images and video, under Apache 2.0.
About Gemma 4 31B
Gemma 4 31B is the biggest model in Google’s open Gemma family, built from the same research as Gemini 3. It is the first Gemma released under the standard Apache 2.0 licence rather than Google’s own terms, and at launch it ranked third among open models on the LMArena text leaderboard. Google’s model card reports 85.2% on MMLU-Pro and 84.3% on GPQA Diamond.
It reads images and video as well as text, with a 256K-token context, and thinks before answering when you switch that on. As a dense 31B model it is small next to the trillion-parameter open models, which shows on long, hard agent tasks — but it is quick and inexpensive for document and image work.
Where it’s strong
Reading documents, forms and images.
Everyday chat and drafting at a low price.
Maths for its size — 89.2% on AIME 2026, by Google’s count.
Where to be careful
Its knowledge stops at January 2025, older than most 2026 models.
Behind the large open models on hard, multi-step coding agents.
The 31B version does not take audio.
Price
For scale: 1,000 requests of about 3,000 tokens in and 1,000 out cost $1.07 — a long prompt and a page of answer each. Every rate is published and stays the same from one request to the next. See every model.
Specs
gemma-4-31b-itCall it
Use the OpenAI SDK you already have — point it at Roar AI and name the model. Read the docs.
from openai import OpenAI
client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")
reply = client.chat.completions.create(
model="gemma-4-31b-it",
messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)Compare Gemma 4 31B
Questions
How much does Gemma 4 31B cost?
Input is $0.182 per 1M tokens; output is $0.52 per 1M tokens. For scale, 1,000 requests of about 3,000 tokens in and 1,000 out cost $1.07. The rate is published and does not change from one request to the next.
Can I use Gemma 4 31B alongside other models?
Yes. Every model on Roar AI is on the same API key and the same monthly invoice, so switching from Gemma 4 31B to another model is a change to one word in your code.
Is Gemma 4 31B open source?
Its weights are open under the Apache 2.0 licence, so you could run it yourself. Through Roar AI you call it like any other model, with no servers to manage.