GPT-4
GPT-4 is a large-scale language model developed by OpenAI designed to solve complex problems with high accuracy. It focuses on providing advanced reasoning capabilities and broad general knowledge for text-based tasks. The model also supports tool calling to assist in executing specific instructions.
GPT-4 specs and pricing
- Provider: OpenAI
- Released: May 28, 2023
- Context window: 8K tokens
- Max output: 4K tokens
- Input: text
- Output: text
- Price: $30 input / $60 output per 1M tokens
- Tool calling: yes
What GPT-4 is good at
- Complex problem solving
- Tasks requiring advanced reasoning
- Applications needing tool integration
To-dos to try with GPT-4
- Analyze a complex technical document and summarize the core logic.
- Draft a structured project plan based on a set of provided constraints.
- Use tool calling to retrieve specific data and format it into a report.
FAQ
- Who developed GPT-4? GPT-4 was developed by OpenAI.
- What is the primary focus of GPT-4? The model is designed for solving difficult problems with high accuracy using its broad general knowledge and advanced reasoning capabilities.
- How much does GPT-4 cost? GPT-4 costs $30 per million input tokens and $60 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 92.4 credits ($1 = 100 credits).
- What is the context window of GPT-4? GPT-4 can read up to 8K tokens at once and write up to 4K tokens in one reply.
- Can I use GPT-4 without coding? Yes. In todo.is you pick GPT-4 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.