Create image
create_imageGenerate images from text prompts, with options for model selection, size, quality, and style. Supports text-to-image, image-to-image, and image editing workflows.
Instructions
Create image Creates an image given a prompt.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| n | No | Number of images to generate | |
| seed | No | Seed for deterministic-compatible image models. | |
| size | No | Image size. Defaults are model-specific. For gpt-image-2, omit this field or use auto for automatic sizing, or send WIDTHxHEIGHT; custom dimensions must both be multiples of 16, longest edge <= 3840px, long/short ratio <= 3:1, and total pixels between 655,360 and 8,294,400. | |
| user | No | End-user identifier | |
| async | No | Return a task before the final image is ready when the selected model supports public async execution. | |
| model | Yes | Model to use. Send this explicitly; query GET /v1/models?recommended_for=image for current recommendations. | |
| style | No | Optional model-specific style selector. Only send when the selected model documents support for this parameter. | |
| prompt | Yes | Image description | |
| stream | No | Image streaming is not exposed through MCP tool calls; omit stream or set it to false. | |
| quality | No | Image quality. Defaults and accepted values are model-specific. For gpt-image-2, omit this field or use auto for automatic quality, or send low, medium, or high. Other image families may use provider-specific values. | |
| mask_url | No | Optional mask URL for compatible image operations. | |
| image_url | No | Single reference image URL for compatible image-to-image models. | |
| operation | No | Public image operation family. Reference-image models use image-to-image with image_url, image_urls, or reference_image_urls. | |
| background | No | Background handling for compatible image generation flows such as gpt-image-2 text-to-image. Not supported for gpt-image-2 image edits. | |
| image_urls | No | Reference image URLs for compatible image-to-image models. | |
| moderation | No | Moderation strictness for compatible image models such as gpt-image-2 | |
| resolution | No | Resolution selector for compatible image model families. | |
| compression | No | Alias for output_compression when supported by the selected model | |
| aspect_ratio | No | Aspect-ratio selector for compatible image model families. | |
| expand_prompt | No | Ask compatible models to expand or enhance the prompt. | |
| output_format | No | Output image format for compatible image models such as gpt-image-2 | |
| negative_prompt | No | Content to avoid for compatible image models. | |
| response_format | No | Response format | url |
| output_compression | No | Output compression level from 0 to 100 for compressed formats | |
| reference_image_urls | No | Alias used by compatible reference-image model families. |