aiaimodel.cards

Gemma 4 31B

Language modelOpen weightsCard summarized

Our most intelligent open models to date, purpose-built for advanced reasoning and agentic workflows

● Re-checked 12 Oct 2026 · 71 facts · 0 corrections · 3 unconfirmedSource: Gemma 4 model card

Use it via API

$132 /month
$2.64 per 1K requests · via DeepInfra
RAG over docs: 12K in · 600 out · 50K requests/mo · 30% cached · change
Code exampleCompare

Where to call it

  • Self-host (weights)google/gemma-4-31B-it
  • Gemini API / Google AI Studiogemma-4-31b-it
  • Google Vertex AIGemma 4 31B

Supports

  • Image input
  • Tool calling
Full feature support

Good for

  • Text generation: creative writing, code, marketing copy, email drafts
  • Chatbots and virtual assistants
  • Summarization

Watch out for

Overview

Google · 02Gemma, front

Gemma 4 31B

Our most intelligent open models to date, purpose-built for advanced reasoning and agentic workflows

Cost
$0.20 host
Context
256K
Cheapest host
$0.20 / $0.40
Max output
—
Knows up to
January 2025
Released
2 Apr 2026

Gemma 4 is an Apache 2.0 open-weights family in five sizes (E2B, E4B, 12B Unified, 26B A4B MoE, 31B dense), released as pre-trained and instruction-tuned checkpoints. 31B is the largest: a 30.7B-parameter dense model with a 256K context that takes text and images and outputs text. Model information

gemma-4-31b-it
Input / output per 1M
$0.20 / $0.40 via DeepInfra
Context window
256K
Max output
—
Knows up to
January 2025
Reasoning
Configurable (<|think|> token in system prompt)
Weights
Open · Apache 2.0

About this card. A model card is the maker's own account of a model: what it's for, how it was trained and tested, and where it falls short. This page condenses Google DeepMind's Gemma 4 model card. Every claim carries its source page.