gpt-image-2

Full OpenAI-compatible GPT Image 2 API coverage with text-to-image, edits, and streaming responses.

- Three subcommands cover all routes: generations for text-to-image, edits for mask-based image manipulation, and responses for streaming and mixed text+image flows

- Strict pre-flight validation enforces model constraints on size, aspect ratio, and feature combinations; includes --dry-run mode to inspect payloads before sending

- Supports multi-image batches, partial image previews, SSE streaming, and OpenAI-compatible gateways via environment variables or CLI flags

- Output patterns like image-{index}.png handle both single and batch workflows; raw JSON responses can be saved for debugging

GPT Image 2

A single Python entrypoint that covers every GPT Image 2 route, with strict pre-flight validation of the model's size, aspect, and feature constraints.

Workflow

- Open references/config.md to pick environment variables and defaults.

- Open references/api-surface.md to choose between generations, edits, and responses.

- Prefer OPENAI_BASE_URL=https://api.openai.com/v1 unless the user asks for a different OpenAI-compatible endpoint.

- Use gpt-image-2 for generations and edits; use a text-capable Responses model such as gpt-5.4 for responses.

- Run scripts/gpt_image.py with one of the three subcommands.

- Add --dry-run first when the payload shape is the main risk.

- Add --save-response <path> when the raw JSON body or SSE event stream needs to be kept for debugging.

Commands

Text-to-image through the public Images API: