GPT-5.6 Luna Pro
Developed by OpenAI, GPT-5.6 Luna Pro is a model designed for high-quality reasoning on complex tasks. It supports large-scale inputs including text, images, and files, and features integrated tool-calling capabilities.
GPT-5.6 Luna Pro specs and pricing
- Provider: OpenAI
- Released: July 9, 2026
- Context window: 1.1M tokens
- Max output: 128K tokens
- Input: files, images, text
- Output: text
- Price: $0.20 input / $1.20 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What GPT-5.6 Luna Pro is good at
- Analyzing complex documents and files
- Tasks requiring deep logical reasoning
- Processing image-based data
To-dos to try with GPT-5.6 Luna Pro
- Upload a long technical manual and summarize the troubleshooting steps for a specific error code.
- Provide an image of a handwritten diagram and ask the model to convert it into a structured text description.
- Use the tool-calling feature to extract data from multiple uploaded files and compile it into a summary report.
FAQ
- What is the difference between this model and the standard GPT-5.6 Luna? GPT-5.6 Luna Pro uses the same underlying architecture but is configured with a pro reasoning mode to improve output quality for complex tasks.
- Can this model process visual information? Yes, the model accepts images as input along with text and files.
- How much does GPT-5.6 Luna Pro cost? GPT-5.6 Luna Pro costs $0.20 per million input tokens and $1.20 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.73 credits ($1 = 100 credits).
- What is the context window of GPT-5.6 Luna Pro? GPT-5.6 Luna Pro can read up to 1.1M tokens at once and write up to 128K tokens in one reply.
- Can I use GPT-5.6 Luna Pro without coding? Yes. In todo.is you pick GPT-5.6 Luna Pro 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.