GPT-5
GPT-5 is OpenAI's most advanced model, designed to handle complex tasks that require step-by-step reasoning and high accuracy. It supports both text and image inputs and is built to improve performance in coding and instruction following.
GPT-5 specs and pricing
- Provider: OpenAI
- Released: August 7, 2025
- Context window: 400K tokens
- Max output: 128K tokens
- Input: text, images, files
- Output: text
- Price: $1.25 input / $10 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What GPT-5 is good at
- Complex tasks requiring multi-step reasoning
- Analyzing documents and images
- Generating and debugging high-quality code
To-dos to try with GPT-5
- Analyze a set of project images and text files to identify potential technical bottlenecks.
- Draft a complex software architecture plan based on provided requirements and constraints.
- Review a long-form technical document to extract and summarize key logical arguments.
FAQ
- What is GPT-5 primarily designed to do? It is optimized for complex tasks that require step-by-step reasoning, high accuracy, and precise instruction following.
- Can this model process visual information? Yes, GPT-5 accepts both text and image files as input.
- How much does GPT-5 cost? GPT-5 costs $1.25 per million input tokens and $10 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 4.9 credits ($1 = 100 credits).
- What is the context window of GPT-5? GPT-5 can read up to 400K tokens at once and write up to 128K tokens in one reply.
- Can I use GPT-5 without coding? Yes. In todo.is you pick GPT-5 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.