gpt-5.4-nano

It is best suited for clearly defined and frequent classification, field extraction, candidate ranking, and simple coding assistance tasks. Prompts should clearly specify decision criteria, allowed outputs, and how to handle missing information. If a task requires complex planning or final judgment, consider mini or a larger model.

You can use images together with text prompts for visual understanding and assisted classification. This page describes a workflow with image-and-text input and text output, not an image creation entry point; if you need to generate or edit images, choose a dedicated image model and the corresponding API.

If you already have messages history management and choices parsing logic, you can use Chat Completions; if you use a response object workflow, you can choose Responses and submit content through input. Both use gpt-5.4-nano, but their request structures and result parsing cannot be mixed.

When managing history yourself, include the necessary prior context in messages or input. To reduce history maintenance work, you can use the AI Chat conversation entry point, save the returned id after enabling stateful, and continue with the same id in subsequent requests, while promptly adding important task conditions.

You can require JSON output in the prompt and clearly define fields, types, and missing-value rules. The Chat Completions entry point provides a response_format setting; when the selected mode applies to this model, it can be used together, but JSON format settings should not be treated as guaranteeing all structural constraints. Your application must still parse and validate the result, checking field completeness, value ranges, and whether content matches the input, and handling formatting errors or incomplete responses.