Gemma 4 26B A4B (free)
Google DeepMind's Gemma 4 26B A4B is an instruction-tuned Mixture-of-Experts model designed for efficient performance. It supports a large context window and can process text, image, and video inputs to generate text responses.
Gemma 4 26B A4B (free) specs and pricing
- Provider: Google
- Released: April 3, 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 26B A4B (free) is good at
- Analyzing multimodal content like videos and images
- Complex reasoning tasks requiring large context
- Applications benefiting from tool-calling capabilities
To-dos to try with Gemma 4 26B A4B (free)
- Upload a video file and summarize the key events that occur throughout the footage.
- Provide a long technical document and ask the model to extract specific data points using its tool-calling function.
- Analyze a set of images and describe the common visual themes found across them.
FAQ
- Who developed the Gemma 4 26B A4B model? This model was developed by Google DeepMind.
- What types of media can this model process? The model is capable of processing text, images, and video as input.
- How much does Gemma 4 26B A4B (free) cost? Gemma 4 26B A4B (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 26B A4B (free)? Gemma 4 26B A4B (free) can read up to 262K tokens at once and write up to 33K tokens in one reply.
- Can I use Gemma 4 26B A4B (free) without coding? Yes. In todo.is you pick Gemma 4 26B A4B (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.