G

Google: Gemma 3 12B Instruct-Tuned

Google
Vision
8K
Context
$0.0250
Input /1M
$0.0750
Output /1M
4K
Max Output
Run API Call Open in Chat

Google: Gemma 3 12B Instruct-Tuned

Model Overview

Property Value
Model ID google/gemma-3-12b-it
Name Gemma 3 12B Instruct-Tuned
Status Stable
Released 2025-11-15

Description

Compact 12B instruction-tuned model.

Description

Google: Gemma 3 12B Instruct-Tuned is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

Specifications

Spec Value
Context Window 8,192 tokens
Max Output 4,096 tokens
Modalities text

Pricing

Type Price
Input $0.025/1M tokens
Output $0.075/1M tokens

Capabilities

  • Text: Yes
  • Image: No
  • Audio: No
  • Video: No
  • Tool Use: No
  • JSON Mode: No

Key Features

  1. Multimodal Support - Text, images, audio, and video
  2. Large Context - Up to 8,192 tokens
  3. Tool Use - Not supported
  4. JSON Mode - Not available
  5. Streaming - Real-time generation
  6. Cost Effective - Optimized pricing

Best For

  • Resource-limited
  • Edge computing
  • Mobile apps
  • Lightweight services

Detailed Analysis

Data & Usage Policies

Policy Status
Training Data Not used for training
Prompt Retention Does not retain prompts
Data Processing Google Cloud privacy compliant

Status & Availability

  • Status: STABLE
  • Free Tier: No
  • Provider: Google

API Usage Example

curl https://api.langmart.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "google/gemma-3-12b-it",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 4096
  }'
  • google/gemini-3-pro-preview - Latest flagship
  • google/gemini-2.5-pro - Advanced 2.5 model
  • google/gemini-2.0-flash - Fast multimodal
  • google/gemma-3-27b-it - Open-source alternative

Performance-Optimized Mid-Size Model

Source

Generated for LangMart AI Platform on 2025-12-28