o3
OpenAI's o3 is a versatile model designed for complex tasks including mathematics, science, and coding. It supports both text and image inputs and features advanced reasoning capabilities for technical writing and instruction-following.
o3 specs and pricing
- Provider: OpenAI
- Released: April 16, 2025
- Context window: 200K tokens
- Max output: 100K tokens
- Input: images, text, files
- Output: text
- Price: $2.00 input / $8.00 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What o3 is good at
- Solving complex mathematical and scientific problems
- Writing and debugging software code
- Analyzing technical documents and images
To-dos to try with o3
- Upload a scientific research paper and ask the model to summarize the methodology and key findings.
- Paste a complex coding script and ask the model to identify logical errors or optimize the performance.
- Provide an image of a technical diagram and ask for a detailed explanation of the components shown.
FAQ
- What types of input can o3 process? The model accepts text, image files, and general file uploads.
- What is o3 primarily designed to do? It is built to handle complex reasoning tasks, specifically in the fields of math, science, and programming.
- How much does o3 cost? o3 costs $2.00 per million input tokens and $8.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 6.72 credits ($1 = 100 credits).
- What is the context window of o3? o3 can read up to 200K tokens at once and write up to 100K tokens in one reply.
- Can I use o3 without coding? Yes. In todo.is you pick o3 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.