Gemma 3 27B
Gemma 3 27B is a multimodal model developed by Google that processes both text and image inputs to generate text outputs. It supports over 140 languages and features a 128k token context window for handling large amounts of information. The model is designed for improved performance in reasoning, mathematics, and tool-calling tasks.
Gemma 3 27B specs and pricing
- Provider: Google
- Released: March 12, 2025
- Context window: 131K tokens
- Max output: 118K tokens
- Input: text, images
- Output: text
- Price: $0.08 input / $0.45 output per 1M tokens
- Tool calling: yes
What Gemma 3 27B is good at
- Analyzing visual data alongside written instructions
- Processing large documents or long-form text
- Building applications that require tool-calling capabilities
To-dos to try with Gemma 3 27B
- Upload a screenshot of a complex chart and ask the model to summarize the trends in a bulleted list.
- Paste a 50-page technical document and ask the model to extract all specific project requirements.
- Provide a set of math problems and ask the model to show its step-by-step reasoning for each solution.
FAQ
- What types of input does Gemma 3 27B accept? The model accepts both text and image inputs.
- Can this model interact with external tools? Yes, Gemma 3 27B supports tool-calling functionality.
- How much does Gemma 3 27B cost? Gemma 3 27B costs $0.08 per million input tokens and $0.45 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.29 credits ($1 = 100 credits).
- What is the context window of Gemma 3 27B? Gemma 3 27B can read up to 131K tokens at once and write up to 118K tokens in one reply.
- Can I use Gemma 3 27B without coding? Yes. In todo.is you pick Gemma 3 27B 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.