GPT-5.4 Image 2
Developed by OpenAI, GPT-5.4 Image 2 is a multimodal model capable of processing and generating both text and images. It supports complex reasoning tasks and handles large inputs, making it suitable for integrated workflows involving documents and visual media.
GPT-5.4 Image 2 specs and pricing
- Provider: OpenAI
- Released: April 21, 2026
- Context window: 272K tokens
- Max output: 128K tokens
- Input: images, text, files
- Output: images, text
- Price: $8.00 input / $15 output per 1M tokens
- Reasoning: yes
What GPT-5.4 Image 2 is good at
- Analyzing complex documents alongside visual data
- Generating images based on detailed text descriptions
- Reasoning through multi-format project requirements
To-dos to try with GPT-5.4 Image 2
- Upload a technical diagram and ask the model to explain the components in text
- Provide a project brief and request a conceptual image to visualize the final result
- Analyze a 200-page report and generate a summary image representing the core findings
FAQ
- What types of media can this model process? The model accepts text, image, and file inputs, and it can produce both text and image outputs.
- Who developed this model? GPT-5.4 Image 2 is developed by OpenAI.
- How much does GPT-5.4 Image 2 cost? GPT-5.4 Image 2 costs $8.00 per million input tokens and $15 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 24.5 credits ($1 = 100 credits).
- What is the context window of GPT-5.4 Image 2? GPT-5.4 Image 2 can read up to 272K tokens at once and write up to 128K tokens in one reply.
- Can I use GPT-5.4 Image 2 without coding? Yes. In todo.is you pick GPT-5.4 Image 2 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.