Vision Gemma

Gemma 3 12B

Google Gemma 3 with 12B parameters

12B
Parameters
128K
Context Window
2.5×
Credit Rate
Starter
Min Tier

Overview

Gemma 3 12B delivers exceptional performance for its size, optimized for complex reasoning and long-context understanding within a 128,000 token window. Built on the efficient Gemma family architecture, this model operates in FP16 precision to ensure high-quality outputs while maintaining latency suitable for production environments. Developers can integrate this model immediately via our standard API endpoints, requiring minimal configuration to start generating responses. The 2.5x credit multiplier reflects its balanced cost-to-performance ratio, making it an ideal choice for applications demanding robust capability without the overhead of larger parameter counts.

For enterprise deployments, Gemma 3 12B offers strong multilingual proficiency, including native-level Arabic comprehension and generation, ensuring seamless user experiences across diverse linguistic regions. The GEMMA license permits broad commercial use, removing legal barriers for production scaling. Whether building research pipelines or customer-facing chatbots, this model provides the stability required for critical workflows. Accessible from the starter tier, it allows teams to validate performance against benchmarks before committing to higher-volume usage, ensuring alignment with both technical requirements and budgetary constraints.

Specifications

Display Name Gemma 3 12B
Family Gemma
Category Vision
Parameters 12B
Context Window 128,000 tokens
Quantization FP16
License GEMMA
Min Tier Starter
Status Available

Pricing

2.5×
credits per token
1K 2,500 Credits
10K 25,000 Credits
100K 250,000 Credits
View Pricing Plans

Code Examples

from openai import OpenAI

client = OpenAI(
    base_url="https://llmapi.resayil.io/v1/",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="gemma3:12b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

print(response.choices[0].message.content)
const response = await fetch(
    "https://llmapi.resayil.io/v1/chat/completions",
    {
        method: "POST",
        headers: {
            "Content-Type": "application/json",
            "Authorization": "Bearer YOUR_API_KEY"
        },
        body: JSON.stringify({
            model: "gemma3:12b",
            messages: [
                { role: "user", content: "Hello!" }
            ]
        })
    }
);

const data = await response.json();
console.log(data.choices[0].message.content);
curl https://llmapi.resayil.io/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gemma3:12b",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Use Cases

Writing code snippets and debugging software errors
Summarizing long documents within large context window
Managing complex customer support conversations very effectively
Generating creative stories and interactive narrative content
Analyzing technical data and extracting key insights

Related Models

Start building with Gemma 3 12B

Get 1,000 free credits when you sign up — no credit card required.