Gemma 4 31B (free)
Google DeepMind's Gemma 4 31B is a multimodal model capable of processing text, images, and video inputs to generate text responses. It features a 256K token context window and includes native support for function calling and configurable reasoning modes.
Gemma 4 31B (free) specs and pricing
- Provider: Google
- Released: April 2, 2026
- Context window: 262K tokens
- Max output: 33K tokens
- Input: images, text, video
- Output: text
- Price: free
- Reasoning: yes
- Tool calling: yes
What Gemma 4 31B (free) is good at
- Analyzing complex documents and long-form content
- Interpreting visual data from images and videos
- Automating tasks through function and tool calling
To-dos to try with Gemma 4 31B (free)
- Analyze a 10-minute video clip and summarize the key events chronologically.
- Upload a series of technical diagrams and ask the model to explain the workflow process.
- Process a large collection of research papers to extract and compare specific data points.
FAQ
- What types of media can I provide to this model? You can provide text, images, and video files as input for the model to process.
- Does this model support reasoning capabilities? Yes, the model includes a configurable thinking and reasoning mode to assist with complex tasks.
- How much does Gemma 4 31B (free) cost? Gemma 4 31B (free) is available as a free model. In todo.is it doesn't use credits, though free models can be rate-limited by the provider.
- What is the context window of Gemma 4 31B (free)? Gemma 4 31B (free) can read up to 262K tokens at once and write up to 33K tokens in one reply.
- Can I use Gemma 4 31B (free) without coding? Yes. In todo.is you pick Gemma 4 31B (free) 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.