GPT-6 Luna
Developed by OpenAI, GPT-6 Luna is a cost-efficient model designed for high-volume and latency-sensitive tasks. It features a large 1.05 million token context window and supports input from text, files, and images.
GPT-6 Luna specs and pricing
- Provider: OpenAI
- Released: September 22, 2026
- Context window: 1.1M tokens
- Max output: 128K tokens
- Input: files, images, text
- Output: text
- Price: $0.10 input / $0.50 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What GPT-6 Luna is good at
- High-volume chat applications
- Automated data classification
- Lightweight agentic workflows
To-dos to try with GPT-6 Luna
- Analyze a 500-page document and summarize the key findings.
- Process a batch of 50 images to categorize the objects within them.
- Use tool calling to fetch real-time data and generate a structured report.
FAQ
- What is GPT-6 Luna best at? It is optimized for high-volume and latency-sensitive workloads, such as chat interactions and data classification.
- Can this model process images? Yes, GPT-6 Luna accepts image files as input alongside text and other file types.
- How much does GPT-6 Luna cost? GPT-6 Luna costs $0.10 per million input tokens and $0.50 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.35 credits ($1 = 100 credits).
- What is the context window of GPT-6 Luna? GPT-6 Luna can read up to 1.1M tokens at once and write up to 128K tokens in one reply.
- Can I use GPT-6 Luna without coding? Yes. In todo.is you pick GPT-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.