Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
Google

Gemma 4 31B

$AffordableRun locally
Google
CompareChat

Google's fourth-generation open dense model with native multimodal understanding. 31B parameters supporting text, image, and video inputs with 262K context. Strong reasoning, coding, and multilingual capabilities for self-hosted and fine-tuned deployments.

▼

Gemma 4 31B is somewhat expensive at $0.12/M tokens input and $0.37/M tokens output. The model supports vision/image input, extended reasoning, a 262K context window.

Best forVision tasksCost-effective
ReplacesGoogleGemma 3 27B·GoogleGemma 2 27B

Benchmarks

CodingInsufficient data
AgenticInsufficient data
ReasoningInsufficient data
MathInsufficient data
Sources:Epoch AI·OpenRouter· as of 2026-07-10

Specifications

Vision
Audio
Reasoning
Dense
Architecture
31B
Parameters
262K
Context
16K
Max output
20 GB
Local download
28 GB
Local RAM

Performance

Providers

Run locally

Run Gemma 4 31B on your own computer with the Local AI Engine for free, with no rate limits and no third-party AI provider involved. idapt installs it and routes chat to your hardware automatically.

Download
20 GB
Recommended RAM
28 GB

ollama pull gemma4:31b

Misc

April 2, 2026
Released
Same family
GoogleGemma 4 26B A4B
CompareChat with Gemma 4 31B

Compare with

OpenAIGPT 5.6 Solvs Gemma 4 31BOpenAIGPT 5.6 Lunavs Gemma 4 31BAnthropicClaude Fable 5vs Gemma 4 31BAnthropicClaude Opus 4.8vs Gemma 4 31BAnthropicClaude Sonnet 5vs Gemma 4 31BAnthropicClaude Haiku 4.5vs Gemma 4 31BGoogleGemini 3.6 Flashvs Gemma 4 31BGoogleGemini 3.5 Flashvs Gemma 4 31BGoogleGemini 3.5 Flash-Litevs Gemma 4 31BxAIGrok 4.5vs Gemma 4 31BxAIGrok Build 0.1vs Gemma 4 31BxAIGrok 4.1 Fastvs Gemma 4 31BMetaMuse Spark 1.1vs Gemma 4 31BDeepSeekDeepSeek V4 Provs Gemma 4 31BDeepSeekDeepSeek V4 Flashvs Gemma 4 31BMiniMaxMiniMax M3vs Gemma 4 31BMoonshotAIKimi K3vs Gemma 4 31BMoonshotAIKimi K2.7 Codevs Gemma 4 31BZhipu AIGLM 5.2vs Gemma 4 31BQwenQwen3.7 Maxvs Gemma 4 31BQwenQwen3.7 Plusvs Gemma 4 31BQwenQwen3 Coder Nextvs Gemma 4 31BNVIDIANemotron 3 Ultravs Gemma 4 31BMistral AIMistral Small 4vs Gemma 4 31B
Frequently Asked Questions about Gemma 4 31B▼

When was Gemma 4 31B released?

▼

Gemma 4 31B was released on April 2, 2026.

Who created Gemma 4 31B?

▼

Gemma 4 31B was created by Google.

How much does Gemma 4 31B cost?

▼

Gemma 4 31B costs $0.12/M input tokens and $0.37/M output tokens.

What is Gemma 4 31B API pricing?

▼

The Gemma 4 31B API is priced at $0.12 per million input tokens and $0.37 per million output tokens. You can access Gemma 4 31B through idapt.app alongside 200+ other AI models in one workspace.

Is Gemma 4 31B a reasoning model?

▼

Yes, Gemma 4 31B is a reasoning model. It can think step-by-step through complex problems before providing an answer, often yielding better results on difficult tasks like math, coding, and multi-step logic.

Does Gemma 4 31B support image or vision input?

▼

Yes, Gemma 4 31B supports vision/image input. You can share images in your conversation and the model will analyze and respond based on their content.

Does Gemma 4 31B support audio?

▼

No, Gemma 4 31B does not support audio input.

What is the context window of Gemma 4 31B?

▼

Gemma 4 31B has a context window of 262K tokens, meaning it can process approximately 196,608 words of context at once.

Is Gemma 4 31B open source?

▼

Gemma 4 31B is a proprietary model developed by Google. The model weights and training data are not publicly available.

What is Gemma 4 31B good at?

▼

Based on benchmark data, Gemma 4 31B excels at: visual analysis and image understanding. It is Google's capable model suitable for a wide range of tasks.

Where can I use Gemma 4 31B?

▼

You can chat with Gemma 4 31B on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access Gemma 4 31B through Google's own API or platform.

  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Credentials
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • idapt Code
  • Code Execution
  • Computers
  • Computer Use
  • Computer Assist · Soon
  • Containers · Soon
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • LLM cost calculator
  • Token counter
  • Context window checker
  • Can I run it
  • Model picker quiz
  • Savings finder
  • Video cost estimator
  • Text to speech cost
  • Transcription cost
  • API endpoint tester
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Skills
  • Learn
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)