GPT-5.4
GPT-5.4 is a frontier model developed by OpenAI that combines their previous Codex and GPT lines into one system. It is designed to handle complex reasoning tasks and supports both text and image inputs within a massive context window of over one million tokens.
GPT-5.4 specs and pricing
- Provider: OpenAI
- Released: March 5, 2026
- Context window: 1.1M tokens
- Max output: 128K tokens
- Input: text, images, files
- Output: text
- Price: $2.50 input / $15 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What GPT-5.4 is good at
- Analyzing large sets of documents or codebases
- Complex reasoning tasks requiring multi-step logic
- Processing multimodal inputs including images and files
To-dos to try with GPT-5.4
- Upload a 500-page technical manual and summarize the troubleshooting procedures for a specific error code.
- Provide a folder of code files and ask the model to identify architectural inconsistencies.
- Upload a series of project diagrams and request a text-based breakdown of the workflow.
FAQ
- What is the primary purpose of GPT-5.4? It is a unified model designed to integrate OpenAI's previous Codex and GPT capabilities into a single system capable of advanced reasoning.
- Can this model process images? Yes, GPT-5.4 supports both text and image inputs.
- How much does GPT-5.4 cost? GPT-5.4 costs $2.50 per million input tokens and $15 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 9.1 credits ($1 = 100 credits).
- What is the context window of GPT-5.4? GPT-5.4 can read up to 1.1M tokens at once and write up to 128K tokens in one reply.
- Can I use GPT-5.4 without coding? Yes. In todo.is you pick GPT-5.4 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.