Gemma 3 12B
Google developed Gemma 3 12B as a multimodal model capable of processing both text and image inputs. It supports over 140 languages and features a 131,072-token context window for handling large amounts of information. The model is designed for improved reasoning, mathematical performance, and tool-calling tasks.
Gemma 3 12B specs and pricing
- Provider: Google
- Released: March 13, 2025
- Context window: 131K tokens
- Max output: 16K tokens
- Input: text, images
- Output: text
- Price: $0.05 input / $0.15 output per 1M tokens
- Tool calling: yes
What Gemma 3 12B is good at
- Analyzing visual data alongside text prompts
- Processing long-form documents or large datasets
- Building applications that require tool-calling functionality
To-dos to try with Gemma 3 12B
- Upload a screenshot of a complex chart and ask the model to summarize the trends in a bulleted list.
- Paste a long technical manual and ask the model to extract specific troubleshooting steps.
- Provide a set of data and instruct the model to use its tool-calling capabilities to format the information into a structured table.
FAQ
- What types of input does Gemma 3 12B accept? The model supports both text and image inputs, allowing for multimodal analysis.
- Can this model interact with external tools? Yes, Gemma 3 12B is equipped with tool-calling capabilities to assist with external tasks.
- How much does Gemma 3 12B cost? Gemma 3 12B costs $0.05 per million input tokens and $0.15 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.16 credits ($1 = 100 credits).
- What is the context window of Gemma 3 12B? Gemma 3 12B can read up to 131K tokens at once and write up to 16K tokens in one reply.
- Can I use Gemma 3 12B without coding? Yes. In todo.is you pick Gemma 3 12B as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.