GPT-4o (2024-08-06)
GPT-4o is an AI model developed by OpenAI that processes text, images, and files. This version features enhanced capabilities for generating structured outputs, allowing users to define specific JSON schemas for responses.
GPT-4o (2024-08-06) specs and pricing
- Provider: OpenAI
- Released: August 6, 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 (2024-08-06) is good at
- Extracting structured data from documents
- Analyzing images alongside text prompts
- Building applications that require consistent JSON output
To-dos to try with GPT-4o (2024-08-06)
- Analyze this uploaded image of a handwritten receipt and output the data as a JSON object with fields for date, merchant, and total.
- Read this 50-page technical manual and extract all safety warnings into a structured JSON format.
- Process these three product photos and generate a JSON file containing descriptions and tags for each item.
FAQ
- What is the primary focus of this specific GPT-4o release? This version is optimized for structured outputs, enabling the model to reliably follow a provided JSON schema.
- Can this model process visual information? Yes, it accepts both text and images as input.
- How much does GPT-4o (2024-08-06) cost? GPT-4o (2024-08-06) 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 (2024-08-06)? GPT-4o (2024-08-06) can read up to 128K tokens at once and write up to 16K tokens in one reply.
- Can I use GPT-4o (2024-08-06) without coding? Yes. In todo.is you pick GPT-4o (2024-08-06) 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.