Gemini 3.6 Flash
Google's Gemini 3.6 Flash is a high-efficiency AI model designed for coding, app development, and agentic workflows. It supports a wide range of input types, including video, audio, and files, and features built-in reasoning and tool-calling capabilities.
Gemini 3.6 Flash specs and pricing
- Provider: Google
- Released: July 21, 2026
- Context window: 1M tokens
- Max output: 66K tokens
- Input: text, images, video, files, audio
- Output: text
- Price: $0.75 input / $3.75 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Gemini 3.6 Flash is good at
- Building and debugging software applications
- Automating complex, multi-step agentic tasks
- Analyzing large media files like videos and audio recordings
To-dos to try with Gemini 3.6 Flash
- Upload a video of a software bug and ask the model to identify the cause and write a fix
- Provide a repository of code files and request a summary of the project architecture
- Use tool-calling to automate a workflow that extracts data from a document and updates a web application
FAQ
- What types of media can Gemini 3.6 Flash process? The model accepts text, images, video, audio, and various file formats as input.
- What is the primary focus of this model? It is specifically optimized for coding tasks, web and app development, and agentic workflows that require reasoning.
- How much does Gemini 3.6 Flash cost? Gemini 3.6 Flash costs $0.75 per million input tokens and $3.75 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 2.63 credits ($1 = 100 credits).
- What is the context window of Gemini 3.6 Flash? Gemini 3.6 Flash can read up to 1M tokens at once and write up to 66K tokens in one reply.
- Can I use Gemini 3.6 Flash without coding? Yes. In todo.is you pick Gemini 3.6 Flash 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.