Gemini 2.5 Flash
Gemini 2.5 Flash is a Google model engineered for complex reasoning, coding, mathematics, and scientific analysis. It features a large context window of over one million tokens and supports multimodal inputs including text, audio, video, images, and files.
Gemini 2.5 Flash specs and pricing
- Provider: Google
- Released: June 17, 2025
- Context window: 1M tokens
- Max output: 66K tokens
- Input: files, images, text, audio, video
- Output: text
- Price: $0.30 input / $2.50 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Gemini 2.5 Flash is good at
- Analyzing complex scientific or mathematical data
- Processing large files or long-form video and audio content
- Writing and debugging code with advanced reasoning
To-dos to try with Gemini 2.5 Flash
- Upload a long video lecture and summarize the key technical concepts discussed.
- Provide a complex mathematical proof and ask the model to verify each step.
- Upload a large codebase and identify potential logic errors or optimization opportunities.
FAQ
- What types of media can I upload to this model? Gemini 2.5 Flash accepts text, images, audio files, video files, and general documents.
- What is the primary focus of this model? It is designed as a workhorse model specifically for tasks requiring advanced reasoning, coding, mathematics, and scientific problem-solving.
- How much does Gemini 2.5 Flash cost? Gemini 2.5 Flash costs $0.30 per million input tokens and $2.50 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1.19 credits ($1 = 100 credits).
- What is the context window of Gemini 2.5 Flash? Gemini 2.5 Flash can read up to 1M tokens at once and write up to 66K tokens in one reply.
- Can I use Gemini 2.5 Flash without coding? Yes. In todo.is you pick Gemini 2.5 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.