Gemini 3.1 Pro Preview
Google's Gemini 3.1 Pro Preview is a multimodal reasoning model designed for complex workflows and software engineering tasks. It supports a wide range of input formats including audio, video, images, and files, and features enhanced reliability for agentic operations.
Gemini 3.1 Pro Preview specs and pricing
- Provider: Google
- Released: February 19, 2026
- Context window: 1M tokens
- Max output: 66K tokens
- Input: audio, files, images, text, video
- Output: text
- Price: $2.00 input / $12 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Gemini 3.1 Pro Preview is good at
- Complex software engineering projects
- Multimodal data analysis involving video and audio
- Automated agentic workflows
To-dos to try with Gemini 3.1 Pro Preview
- Analyze a 30-minute video meeting recording to generate a list of action items.
- Debug a complex codebase by providing multiple related files for context.
- Extract and summarize data from a set of technical documents and accompanying images.
FAQ
- What types of media can I provide to this model? The model accepts text, audio, video, images, and file uploads as input.
- What is the primary focus of this model? It is built as a frontier reasoning model specifically optimized for improved software engineering performance and agentic reliability.
- How much does Gemini 3.1 Pro Preview cost? Gemini 3.1 Pro Preview costs $2.00 per million input tokens and $12 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 7.28 credits ($1 = 100 credits).
- What is the context window of Gemini 3.1 Pro Preview? Gemini 3.1 Pro Preview can read up to 1M tokens at once and write up to 66K tokens in one reply.
- Can I use Gemini 3.1 Pro Preview without coding? Yes. In todo.is you pick Gemini 3.1 Pro Preview 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.