Gemma 3 27B
Gemma 3 27B is a large language model made by Google, added to the catalog on 12 Mar 2025. It has a context window of 131,072 tokens and costs $0.08 per 1M input tokens and $0.45 per 1M output tokens. It accepts text and images and produces text. Typical uses: develop multilingual chatbots, create complex data analysis tools and design interactive educational apps.
Price checked · source: OpenRouter
What Gemma 3 27B is
Released in March 2025, Google: Gemma 3 27B is a state-of-the-art multimodal model that processes both text and images to generate text outputs. With a substantial context window of 131,072 tokens, it can handle complex tasks across over 140 languages. This model enhances capabilities in math, reasoning, and chat, making it versatile for diverse applications. It also supports structured outputs and function calling, offering flexibility for developers. As an open-source model, Gemma 3 27B builds on the strengths of its predecessor, Gemma 2, providing a robust tool for innovative AI solutions.
Key features
- Supports vision-language input and text output
- Handles up to 128k token context windows
- Understands over 140 languages
- Enhanced math and reasoning capabilities
- Structured outputs and function calling
- Open-source model from Google
Typical uses
- Develop multilingual chatbots
- Create complex data analysis tools
- Design interactive educational apps
- Enhance image-to-text conversion
- Implement advanced language processing
Gemma 3 27B pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.08 |
| Output, per 1M tokens | $0.45 |
| Cached input read, per 1M tokens | $0.04 |
No price change since it was added on 12 Mar 2025.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0002 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0024 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0033 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.013 |
Gemma 3 27B specifications
| Model id | google/gemma-3-27b-it |
|---|---|
| Version | gemma-3-27b-it |
| Context window | 131,072 tokensAbout 98,304 English words |
| Max output | 117,964 tokens |
| Knowledge cutoff | 2024-08-31 |
| Added to catalog | 12 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 Upswing: Work, Leisure & Creativity AI isn't about *replacing* us, but fundamentally *upending* how we approach work, leisure and creativity. Work will shift from repetitive tasks to higher-level strategy and problem-solving, augmented by AI assistants handling mundane duties. This frees us for more fulfilling, impactful roles. Leisure will blossom with hyper-personalization. Imagine AI curating travel itineraries based on your evolving mood, or generating dynamic game experiences. Accessibility will increase – AI-powered translation & assistance opening experiences to wider audiences. Most excitingly, AI democratizes creativity. Tools will empower anyone to compose music, write stories, or design visuals *without* needing years of training. AI becomes a collaborative partner, sparking new ideas and expanding artistic boundaries. This isn’t a future of robotic overlords, but one of amplified human potential - more time, more access, and more opportunities to *create*.
Draw with code
RUN20 Nov 2026Generate an SVG of a pelican riding a bicycle.
Compare Gemma 3 27B
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.