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. Features a 256K token context window, configurable thinking/reasoning mode, native function...

It is part of Google's Gemini and Gemma catalog: Pro tiers lead on capability, Flash tiers on speed and price, 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 1.10x margin. Raw prices shown per 1M tokens.

Try Gemma 4 31B (free) now

Ask Gemma 4 31B (free) anything. Your prompt opens in the Zeplik app with this model selected.

Gemma 4 31B (free)

What Gemma 4 31B (free) is best for

Example prompts

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

Google family

ModelContextInput cr/MOutput cr/MReleased
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)66K2.816.5June 2026
Nano Banana 2 (Gemini 3.1 Flash Image)131K5.533.0June 2026
Nano Banana Pro (Gemini 3 Pro Image)66K22.0132June 2026
Gemini 3.5 Flash1.0M16.599.0May 2026
Gemini 3.1 Flash Lite1.0M2.816.5May 2026
Gemma 4 26B A4B (free)262K00April 2026
Gemma 4 26B A4B262K0.663.6April 2026
Gemma 4 31B (free)262K00April 2026
Gemma 4 31B262K1.33.8April 2026
Lyria 3 Pro Preview1.0M00March 2026

All 28 Google models

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. Features a 256K token context window, configurable thinking/reasoning mode, native function...
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

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Fast and light

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...

66K ctx16.5 cr/M outJune 2026
Nano Banana 2 (Gemini 3.1 Flash Image)Fast and light

Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...

131K ctx33.0 cr/M outJune 2026
Nano Banana Pro (Gemini 3 Pro Image)Fast and light

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

66K ctx132 cr/M outJune 2026
Gemini 3.5 FlashFast and light

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...

1.0M ctx99.0 cr/M outMay 2026
Gemini 3.1 Flash LiteFast and light

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...

1.0M ctx16.5 cr/M outMay 2026
Gemma 4 26B A4B (free)Open weight

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

262K ctx0 cr/M outApril 2026
Gemma 4 31B (free) - Google AI Model | Zeplik Chat