Gemma 3 12B
Gemma 3 12B is a large language model made by Google, added to the catalog on 13 Mar 2025. It has a context window of 131,072 tokens and costs $0.05 per 1M input tokens and $0.15 per 1M output tokens. It accepts text and images and produces text. Typical uses: enhance multilingual customer support, develop interactive educational tools and create detailed data analysis reports.
Price checked ยท source: OpenRouter
What Gemma 3 12B is
Google's Gemma 3 12B, released in March 2025, is a versatile AI model that supports both text and image inputs, delivering text outputs. It features an extensive context window of up to 128,000 tokens and understands over 140 languages. This model excels in tasks involving math, reasoning, and structured outputs, and includes function calling capabilities. As part of the Gemma 3 family, it is the second largest model, designed to handle complex multimodal interactions efficiently. Its support for a wide range of parameters allows for tailored responses, making it a robust choice for diverse applications.
Key features
- Multimodal support: text and image inputs
- Large context window: up to 128k tokens
- Understands over 140 languages
- Enhanced math and reasoning capabilities
- Structured outputs and function calling
Typical uses
- Enhance multilingual customer support
- Develop interactive educational tools
- Create detailed data analysis reports
- Automate complex reasoning tasks
Gemma 3 12B pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.05 |
| Output, per 1M tokens | $0.15 |
No price change since it was added on 13 Mar 2025.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0014 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0018 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0077 |
Gemma 3 12B specifications
| Model id | google/gemma-3-12b-it |
|---|---|
| Version | gemma-3-12b-it |
| Context window | 131,072 tokensAbout 98,304 English words |
| Max output | 16,384 tokens |
| Knowledge cutoff | 2024-08-31 |
| Added to catalog | 13 Mar 2025 |
| Input types | text, image |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
Write a short essay
RUN20 Nov 2026Write 150 words on how AI might positively upend work, leisure and creativity
## The AI Renaissance: Work, Leisure, & Creativity Transformed AI isn't about replacing us; it's about augmenting our potential. In work, expect a shift from repetitive tasks to strategic thinking. AI will automate data analysis, scheduling, and even initial drafts, freeing humans for complex problem-solving, leadership, and relationship building. This could lead to shorter workweeks and more fulfilling roles. Leisure time will be revolutionized. Personalized entertainment curated by AI, immersive virtual experiences, and effortless travel planning will become commonplace. Imagine AI composing music tailored to your mood or designing bespoke fitness routines. Creativity will flourish. AI tools can act as collaborators, generating initial ideas, exploring variations, and handling technical execution, allowing artists, writers, and musicians to focus on the core creative vision. We're entering an era where AI empowers human ingenuity, leading to unprecedented innovation and expression.
Draw with code
RUN20 Nov 2026Generate an SVG of a pelican riding a bicycle.
Compare Gemma 3 12B
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.