GPT-5.6 Luna
GPT-5.6 Luna is an AI model developed by OpenAI designed for high-volume and latency-sensitive tasks. It supports text, image, and file inputs, and features built-in reasoning capabilities for efficient agentic workflows.
GPT-5.6 Luna 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 is good at
- High-volume data classification
- Real-time chat applications
- Lightweight agentic automation
To-dos to try with GPT-5.6 Luna
- Analyze a folder of images and categorize them based on their content
- Process a large technical document to extract key data points
- Automate a multi-step workflow that requires reasoning through file inputs
FAQ
- What types of files can GPT-5.6 Luna process? The model is capable of handling text, images, and various file types as input.
- Does this model support tool calling? Yes, GPT-5.6 Luna is equipped with tool-calling capabilities to assist in agentic workflows.
- How much does GPT-5.6 Luna cost? GPT-5.6 Luna 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? GPT-5.6 Luna 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 without coding? Yes. In todo.is you pick GPT-5.6 Luna 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.