GPT-5 Mini
GPT-5 Mini is a compact model from OpenAI designed for efficient reasoning tasks. It supports text, image, and file inputs while maintaining the instruction-following and safety standards of the larger GPT-5 model.
GPT-5 Mini specs and pricing
- Provider: OpenAI
- Released: August 7, 2025
- Context window: 400K tokens
- Max output: 128K tokens
- Input: text, images, files
- Output: text
- Price: $0.25 input / $2.00 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What GPT-5 Mini is good at
- Tasks requiring fast, cost-effective reasoning
- Processing documents and images
- Applications that benefit from low-latency responses
To-dos to try with GPT-5 Mini
- Analyze this 50-page financial report and summarize the key risks.
- Extract text from these three scanned receipts and format them into a table.
- Review this technical document and explain the core concepts in simple terms.
FAQ
- What is the primary purpose of GPT-5 Mini? It is designed to handle lighter-weight reasoning tasks with reduced latency and cost compared to the full GPT-5 model.
- Can this model process visual information? Yes, GPT-5 Mini supports both image and file inputs alongside standard text.
- How much does GPT-5 Mini cost? GPT-5 Mini costs $0.25 per million input tokens and $2.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.98 credits ($1 = 100 credits).
- What is the context window of GPT-5 Mini? GPT-5 Mini can read up to 400K tokens at once and write up to 128K tokens in one reply.
- Can I use GPT-5 Mini without coding? Yes. In todo.is you pick GPT-5 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.