Gemini 3.7 Flash
Gemini 3.7 Flash is a multimodal model developed by Google designed for fast agentic workflows and complex reasoning. It supports a wide range of input formats including text, images, video, audio, and files, and is built to handle multi-step tasks efficiently.
Gemini 3.7 Flash specs and pricing
- Provider: Google
- Released: August 13, 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 3.7 Flash is good at
- Complex multi-step reasoning tasks
- Coding and software development workflows
- Processing large files or multimedia content
To-dos to try with Gemini 3.7 Flash
- Analyze a 30-minute video file and summarize the key discussion points.
- Debug a complex codebase by reviewing multiple uploaded project files.
- Perform a multi-step data extraction from a series of documents to generate a structured report.
FAQ
- What types of media can I upload to this model? You can provide text, images, video, audio, and various file formats as input for the model to process.
- What is the primary focus of Gemini 3.7 Flash? This model is designed to provide responsive performance for agentic workflows and complex reasoning tasks.
- How much does Gemini 3.7 Flash cost? Gemini 3.7 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 3.7 Flash? Gemini 3.7 Flash can read up to 1M tokens at once and write up to 66K tokens in one reply.
- Can I use Gemini 3.7 Flash without coding? Yes. In todo.is you pick Gemini 3.7 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.