GPT-5 Image Mini
GPT-5 Image Mini is a multimodal model developed by OpenAI that integrates language processing with image generation capabilities. It supports both text and image inputs and outputs, offering advanced instruction following and reasoning features. The model is designed for efficient performance across a wide range of creative and analytical tasks.
GPT-5 Image Mini specs and pricing
- Provider: OpenAI
- Released: October 16, 2025
- Context window: 400K tokens
- Max output: 128K tokens
- Input: files, images, text
- Output: images, text
- Price: $2.50 input / $2.00 output per 1M tokens
- Reasoning: yes
What GPT-5 Image Mini is good at
- Generating images from detailed text descriptions
- Analyzing and interpreting uploaded image files
- Complex reasoning tasks that require text-based outputs
To-dos to try with GPT-5 Image Mini
- Upload a sketch of a website layout and ask the model to generate a high-fidelity image representation.
- Provide a series of technical diagrams and ask for a written summary of the processes described.
- Submit a complex prompt involving both text instructions and reference images to generate a new visual asset.
FAQ
- What types of media can this model process and create? GPT-5 Image Mini is natively multimodal, meaning it can accept and produce both text and image data.
- Who is the developer of this model? This model is developed by OpenAI and utilizes their GPT-5 Mini language technology alongside GPT Image 1 Mini.
- How much does GPT-5 Image Mini cost? GPT-5 Image Mini costs $2.50 per million input tokens and $2.00 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 GPT-5 Image Mini? GPT-5 Image Mini can read up to 400K tokens at once and write up to 128K tokens in one reply.
- Can I use GPT-5 Image Mini without coding? Yes. In todo.is you pick GPT-5 Image Mini 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.