How much does Gemma 4 31B (free) cost on Zeplik?

Input tokens cost 0 credits per million and output tokens 0 credits per million (1 credit = $0.10; the raw provider rates are $0 and $0 per million). New accounts start with free credits.

How long can a conversation with Gemma 4 31B (free) be?

Gemma 4 31B (free) has a 262K-token context window (262,144 tokens), which covers the conversation plus any documents you attach.

Does Gemma 4 31B (free) support images and tools?

Gemma 4 31B (free) accepts image input and supports tool calling.

Gemma 4 31B (free)

Open weightVisionTools

Google · Released April 2026

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.

It is part of Google's Gemini and Gemma catalog: Pro tiers lead on capability, Flash tiers on speed and price, Nano Banana covers image generation, and Gemma models are open weight.

Facts and pricing

Provider: Google
Context window: 262K tokens
Input price: 0 credits / 1M tokens ($0 raw)
Output price: 0 credits / 1M tokens ($0 raw)
Vision (image input): Yes
Tool calling: Yes
Extended reasoning: No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin. Raw prices shown per 1M tokens.

Try Gemma 4 31B now

Gemma 4 31B (free) is a serving variant of Gemma 4 31B, so Zeplik offers the Gemma 4 31B row and routes your prompt there.

Or open Zeplik with Gemma 4 31B already selected

What Gemma 4 31B (free) is best for

Everyday chat and drafting on an open-weight model with transparent lineage
Long documents: the 262K-token window holds lengthy reports, contracts or papers whole
Working with images: screenshots, charts, photos and scanned documents alongside text
Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows

Example prompts

Prompts that suit a open weight model like Gemma 4 31B (free):

Draft a project update from these rough notes
Explain how HTTPS works to a curious teenager
Turn this list of features into a changelog entry
Brainstorm objections to this proposal and how to answer them

Google family

Model	Context	Input cr/M	Output cr/M	Released
Gemini 4 Argon	1.0M	24.0	120	October 2026
Nano Banana 2.1	66K	18.0	90.0	October 2026
Gemini 3.8 Flash	1.0M	9.0	45.0	September 2026
Gemini 3.8 Flash (batch)	1.0M	4.5	22.5	September 2026
Gemini 3.7 Flash (batch)	1.0M	4.5	22.5	August 2026
Gemini 3.7 Flash	1.0M	9.0	45.0	August 2026
Gemini 3.6 Flash (batch)	1.0M	4.5	22.5	July 2026
Gemini 3.6 Flash	1.0M	9.0	45.0	July 2026
Gemini 3.5 Flash Lite (batch)	1.0M	1.8	15.0	July 2026
Gemini 3.5 Flash Lite	1.0M	3.6	30.0	July 2026

All 40 Google models

Model comparisons

Frequently asked questions

What is Gemma 4 31B (free)?: Gemma 4 31B (free) is an AI model by Google. Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
How much does Gemma 4 31B (free) cost on Zeplik?: Input tokens cost 0 credits per million and output tokens 0 credits per million (1 credit = $0.10; the raw provider rates are $0 and $0 per million). New accounts start with free credits.
How long can a conversation with Gemma 4 31B (free) be?: Gemma 4 31B (free) has a 262K-token context window (262,144 tokens), which covers the conversation plus any documents you attach.
Does Gemma 4 31B (free) support images and tools?: Gemma 4 31B (free) accepts image input and supports tool calling.

Related models

Gemini 4 ArgonFast and light

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents.

1.0M ctx120 cr/M outOctober 2026

Nano Banana 2.1Fast and light

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro.

66K ctx90.0 cr/M outOctober 2026

Gemini 3.8 FlashFast and light

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

1.0M ctx45.0 cr/M outSeptember 2026

Gemini 3.8 Flash (batch)Fast and light

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

1.0M ctx22.5 cr/M outSeptember 2026

Gemini 3.7 Flash (batch)Fast and light

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.

1.0M ctx22.5 cr/M outAugust 2026

Gemini 3.7 FlashFast and light

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.

1.0M ctx45.0 cr/M outAugust 2026