GPT-5 Nano
GPT-5 Nano is a model developed by OpenAI designed for high-speed interactions and developer-focused tasks. It supports both text and image inputs and features built-in reasoning and tool-calling capabilities.
GPT-5 Nano specs and pricing
- Provider: OpenAI
- Released: August 7, 2025
- Context window: 400K tokens
- Max output: 128K tokens
- Input: text, images, files
- Output: text
- Price: $0.05 input / $0.40 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What GPT-5 Nano is good at
- Rapid application development
- Low-latency automated interactions
- Processing text and image data for quick insights
To-dos to try with GPT-5 Nano
- Analyze a series of screenshots to identify UI layout inconsistencies.
- Use tool-calling to fetch live data and summarize it into a text report.
- Process a large technical document to extract specific code snippets.
FAQ
- What is the primary focus of GPT-5 Nano? It is optimized for rapid interactions and low-latency environments, making it suitable for developer tools.
- Can this model process images? Yes, GPT-5 Nano supports both text and image inputs.
- How much does GPT-5 Nano cost? GPT-5 Nano costs $0.05 per million input tokens and $0.40 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.2 credits ($1 = 100 credits).
- What is the context window of GPT-5 Nano? GPT-5 Nano can read up to 400K tokens at once and write up to 128K tokens in one reply.
- Can I use GPT-5 Nano without coding? Yes. In todo.is you pick GPT-5 Nano 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.