Roar AI
DiscordGet started
All models
Google · Open weights

Gemma 4 31B

Gemma 4 31B costs $0.182 per million input tokens and $0.52 per million output tokens on Roar AI. Google’s largest open Gemma: a 31-billion-parameter model that reads images and video, under Apache 2.0.

Input$0.182per 1M tokens
Output$0.52per 1M tokens
Context window256Ktokens

Gemma 4 31B API pricing

Input$0.182 per 1M tokens
Output$0.52 per 1M tokens
Batch input$0.091 per 1M tokens
Batch output$0.26 per 1M tokens

Example: 1,000 requests with 3,000 input and 1,000 output tokens each cost $1.07. Every rate is published and stays the same from one request to the next. See every model.

Rates as of 20 November 2026.

Specs

Made byGoogle
ReleasedApril 2026
TypeChat
Context window256K tokens
ReadsText, images, video
Thinks before answeringYes, adjustable
WeightsOpen (Apache 2.0)
Size31B, dense
Processed inGlobal
Model idgemma-4-31b-it

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.

What is Gemma 4 31B good for?

  • 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.

Gemma 4 31B limitations

  • 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.

How to use the Gemma 4 31B API

Use the OpenAI SDK you already have: point it at Roar AI and set the model name. 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."}],
)

Gemma 4 31B FAQ

How much does Gemma 4 31B cost?

Input is $0.182 per 1M tokens; output is $0.52 per 1M tokens. For example, 1,000 requests with 3,000 input and 1,000 output tokens each cost $1.07.

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 only means changing the model name 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.

What is the context window of Gemma 4 31B?

Gemma 4 31B can read up to 256K tokens in one request.

Can Gemma 4 31B read images and PDFs?

It reads images directly. You can still send it a PDF: Roar AI turns each page into text first, at no extra charge.

Start using Gemma 4 31B

Create a free account, get an API key and call Gemma 4 31B with the OpenAI SDK.