Google

Google: Gemma 4 31B

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...

Context Window
262K tokens
Parameters
31B
Input Price
$0.10/1M
Output Price
$0.34/1M
Price Tier
budget
Provider
Google

How to Use Google: Gemma 4 31B

With CoreAI, you can start chatting with Google: Gemma 4 31B instantly — no separate subscription needed. CoreAI lets you chat with Google: Gemma 4 31B alongside 300+ other AI models from Google and other providers like OpenAI, Anthropic, Google, Meta, and more.

  1. Download the CoreAI app for iOS, Android, or use the Web App
  2. Select Google: Gemma 4 31B from the model selector
  3. Start chatting, comparing, or creating with AI

Google: Gemma 4 31B at a Glance

Measured against all 400 chat models CoreAI serves, Google: Gemma 4 31B sits at #166 for context capacity — 262K tokens, roughly 196,608 words or 393 pages of text in a single conversation. On price, it is the #50 cheapest of 125 budget-tier models by input cost. It joined the catalog on 2026-04-02. It supports step-by-step reasoning (thinking mode) and accepts image input.

Google: Gemma 4 31B Compared to Its Closest Alternatives

SpecGoogle: Gemma 4 31BGoogle: Gemini 2.5 Flash LiteNVIDIA: Nemotron 3.5 LightningIBM: Granite 4.0 Micro
ProviderGoogleGoogleNVIDIAIbm-granite
Input $/1M tokens$0.1$0.1$0.08$0.017
Output $/1M tokens$0.34$0.4$0.2$0.112
Context window262K1.0M262K131K
Reasoning modeYesYesYesNo
Image inputYesYesNoNo
Price tierbudgetbudgetbudgetbudget

Every model in this table is available on CoreAI — open the web app and run the same prompt through Google: Gemma 4 31B and Google: Gemini 2.5 Flash Lite side by side to judge with your own eyes.

What Google: Gemma 4 31B Actually Costs in Practice

A typical question (about 1,000 tokens in, 500 out) runs $0.00027 on Google: Gemma 4 31B's raw per-token rates; a heavy session with a 50K-token document costs about $0.007. On CoreAI you don't juggle these numbers — one subscription covers Google: Gemma 4 31B and 300+ other models under a plan usage limit, with no API keys. See plans.

More Google Models

Google

Google: Gemini 3.7 Flash

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that
1049K standard
Google

Google: Gemini 3.7 Flash (batch)

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that
1049K budget
Google

Google: Gemini 3.6 Flash

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished
1049K standard
Google

Google: Gemini 3.6 Flash (batch)

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished
1049K standard
Google

Google: Gemini 3.5 Flash Lite

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks
1049K standard
Google

Google: Gemini 3.5 Flash Lite (batch)

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks
1049K standard

Frequently Asked Questions about Google: Gemma 4 31B

What is Google: Gemma 4 31B's context window?

Google: Gemma 4 31B handles 262K tokens of context — roughly 196,608 words, or about 393 pages of text in one conversation.

How much does Google: Gemma 4 31B cost?

Google: Gemma 4 31B's underlying rates are $0.1 per 1M input tokens and $0.34 per 1M output tokens. On CoreAI it is included in one subscription alongside 300+ models, so there is no per-token billing to manage.

Can Google: Gemma 4 31B process images?

Yes — Google: Gemma 4 31B accepts image input, so you can attach screenshots, photos or diagrams and ask questions about them.

Does Google: Gemma 4 31B support reasoning or thinking mode?

Yes. Google: Gemma 4 31B can work through problems step by step before answering; on CoreAI you can toggle thinking mode per message.

How can I use Google: Gemma 4 31B without an API key?

Open the CoreAI web app or the iOS/Android app, pick Google: Gemma 4 31B in the model selector, and chat — no API key, no per-token billing. One subscription covers Google: Gemma 4 31B and 300+ other models.

What are the best alternatives to Google: Gemma 4 31B?

The closest alternatives on CoreAI are Google: Gemini 2.5 Flash Lite, NVIDIA: Nemotron 3.5 Lightning, IBM: Granite 4.0 Micro — similar tier and capability. The fastest way to choose is running one prompt through them side by side in CoreAI's Compare view.

Read More about Google: Gemma 4 31B

Try Google: Gemma 4 31B Now

Chat with Google: Gemma 4 31B and 300+ other AI models — all in one app.

Use Web App Download App →