GPT-4o (2024-11-20)
GPT-4o is an AI model developed by OpenAI that accepts text, images, and files as input. This version is designed to provide more natural and engaging creative writing while improving the handling of uploaded documents.
GPT-4o (2024-11-20) specs and pricing
- Provider: OpenAI
- Released: November 20, 2024
- Context window: 128K tokens
- Max output: 16K tokens
- Input: text, images, files
- Output: text
- Price: $2.50 input / $10 output per 1M tokens
- Tool calling: yes
What GPT-4o (2024-11-20) is good at
- Drafting creative and professional content
- Analyzing information from uploaded files
- Interpreting and processing image-based data
To-dos to try with GPT-4o (2024-11-20)
- Upload a long report and summarize the key findings into a short email.
- Provide an image of a handwritten note and transcribe it into a digital document.
- Draft a creative story based on a provided outline and specific tone requirements.
FAQ
- What is the primary focus of this specific GPT-4o update? This version focuses on enhancing creative writing capabilities to be more natural and relevant, while improving the model's ability to work with uploaded files.
- Can this model process visual information? Yes, GPT-4o is capable of accepting both images and text as input.
- How much does GPT-4o (2024-11-20) cost? GPT-4o (2024-11-20) costs $2.50 per million input tokens and $10 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 8.4 credits ($1 = 100 credits).
- What is the context window of GPT-4o (2024-11-20)? GPT-4o (2024-11-20) can read up to 128K tokens at once and write up to 16K tokens in one reply.
- Can I use GPT-4o (2024-11-20) without coding? Yes. In todo.is you pick GPT-4o (2024-11-20) 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.