Gemma 4 26B A4B
Google DeepMind's Gemma 4 26B A4B is an instruction-tuned Mixture-of-Experts model designed for efficient performance. It supports multi-modal inputs including text, images, and video, and includes capabilities for reasoning and tool calling.
Gemma 4 26B A4B specs and pricing
- Provider: Google
- Released: April 3, 2026
- Context window: 262K tokens
- Max output: 236K tokens
- Input: images, text, video
- Output: text
- Price: $0.076 input / $0.26 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Gemma 4 26B A4B is good at
- Analyzing complex video and image content
- Tasks requiring logical reasoning
- Applications that benefit from tool-calling capabilities
To-dos to try with Gemma 4 26B A4B
- Upload a video of a meeting and summarize the key decisions made
- Provide an image of a handwritten chart and extract the data into a table
- Use tool calling to search for current information and draft a report based on the findings
FAQ
- What types of media can this model process? Gemma 4 26B A4B accepts text, images, and video as input.
- Who developed this model? This model was developed by Google DeepMind.
- How much does Gemma 4 26B A4B cost? Gemma 4 26B A4B costs $0.076 per million input tokens and $0.26 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.25 credits ($1 = 100 credits).
- What is the context window of Gemma 4 26B A4B ? Gemma 4 26B A4B can read up to 262K tokens at once and write up to 236K tokens in one reply.
- Can I use Gemma 4 26B A4B without coding? Yes. In todo.is you pick Gemma 4 26B A4B 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.