GPT-5.4 Mini
OpenAI's GPT-5.4 Mini is an efficient model designed for high-throughput tasks that require complex reasoning and coding capabilities. It supports both text and image inputs, offering a large context window to handle extensive information.
GPT-5.4 Mini specs and pricing
- Provider: OpenAI
- Released: March 17, 2026
- Context window: 400K tokens
- Max output: 128K tokens
- Input: files, images, text
- Output: text
- Price: $0.75 input / $4.50 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What GPT-5.4 Mini is good at
- Analyzing large documents or datasets
- Complex coding and technical problem-solving
- Processing image-based information alongside text
To-dos to try with GPT-5.4 Mini
- Upload a technical manual and ask the model to summarize the troubleshooting steps for a specific error code.
- Provide a set of code files and request a refactor to improve performance.
- Upload a series of diagrams and ask the model to explain the workflow depicted in them.
FAQ
- What types of inputs does GPT-5.4 Mini support? The model can process text, image, and file inputs.
- What are the primary strengths of this model? GPT-5.4 Mini is optimized for high-throughput workloads and features strong reasoning and coding capabilities.
- How much does GPT-5.4 Mini cost? GPT-5.4 Mini costs $0.75 per million input tokens and $4.50 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 2.73 credits ($1 = 100 credits).
- What is the context window of GPT-5.4 Mini? GPT-5.4 Mini can read up to 400K tokens at once and write up to 128K tokens in one reply.
- Can I use GPT-5.4 Mini without coding? Yes. In todo.is you pick GPT-5.4 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.