Gemma 4 31B
Gemma 4 31B is a multimodal model developed by Google DeepMind designed to process text, images, and video. It features a 256K token context window and includes native support for function calling and configurable reasoning modes.
Gemma 4 31B specs and pricing
- Provider: Google
- Released: April 2, 2026
- Context window: 262K tokens
- Max output: 16K tokens
- Input: images, text, video
- Output: text
- Price: $0.20 input / $0.40 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Gemma 4 31B is good at
- Analyzing long documents or complex multimodal data
- Tasks requiring logical reasoning and step-by-step problem solving
- Integrating AI capabilities into applications via function calling
To-dos to try with Gemma 4 31B
- Upload a video of a technical lecture and ask for a summary of the key concepts discussed.
- Provide a set of images and a text prompt to extract specific data points into a structured format.
- Use the reasoning mode to solve a multi-step mathematical or logic problem.
FAQ
- What types of input can Gemma 4 31B process? The model supports text, image, and video inputs.
- Does this model support tool use? Yes, it features native function calling capabilities to interact with external tools.
- How much does Gemma 4 31B cost? Gemma 4 31B costs $0.20 per million input tokens and $0.40 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.62 credits ($1 = 100 credits).
- What is the context window of Gemma 4 31B? Gemma 4 31B can read up to 262K tokens at once and write up to 16K tokens in one reply.
- Can I use Gemma 4 31B without coding? Yes. In todo.is you pick Gemma 4 31B 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.