GPT-5 Image
GPT-5 Image is an OpenAI model that integrates advanced reasoning and coding capabilities with image generation. It supports both text and image inputs and outputs, allowing for complex multimodal tasks within a 400,000 token context window.
GPT-5 Image specs and pricing
- Provider: OpenAI
- Released: October 14, 2025
- Context window: 400K tokens
- Max output: 128K tokens
- Input: images, text, files
- Output: images, text
- Price: $10 input / $10 output per 1M tokens
- Reasoning: yes
What GPT-5 Image is good at
- Tasks requiring complex reasoning and logical analysis
- Generating images based on detailed text descriptions
- Analyzing and processing large documents combined with visual data
To-dos to try with GPT-5 Image
- Analyze this 300-page technical manual and generate a diagram illustrating the assembly process.
- Review this set of architectural sketches and provide a written critique on structural feasibility.
- Summarize the key findings from these five research papers and create an infographic summarizing the data.
FAQ
- What types of media can this model process? The model accepts image, text, and file inputs and can produce both text and image outputs.
- Who developed this model? GPT-5 Image is developed by OpenAI.
- How much does GPT-5 Image cost? GPT-5 Image costs $10 per million input tokens and $10 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 29.4 credits ($1 = 100 credits).
- What is the context window of GPT-5 Image? GPT-5 Image can read up to 400K tokens at once and write up to 128K tokens in one reply.
- Can I use GPT-5 Image without coding? Yes. In todo.is you pick GPT-5 Image 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.