Home / Servers / OpenAI API / create_image
Create image
An MCP tool from the OpenAI API server, hosted on mcp.hjlabs.in.
Create image Creates an image given a prompt using a GPT Image model. Learn more. [POST /images/generations]
Name on the gateway: openai_api__create_image · may change things.
Parameters
| Name | Type | Description |
|---|---|---|
frame_count | integer | Number of frames for GIF output. Accepts integers from 2 through 16. Defaults… |
frame_duration_ms | integer | Requested delay per GIF frame, in milliseconds. Defaults to 200 when omitted.… |
complexity | string | Computation spent planning the image, independently of rendering quality. Uses… |
svg | object | Selects the model and reasoning effort used to author SVG output. Requires… |
prompt required | string | A text description of the desired image(s). The maximum length is 32000… |
model required | string | The GPT image model to use for image generation. Specify a model explicitly.… |
n | integer | The number of images to generate. Must be between 1 and 10. |
quality | low | medium | high | xhigh | max | auto | standard | hd | The quality of the image that will be generated. - auto (default value) will… |
response_format | string | Legacy response format parameter for retired image models. Unsupported for GPT… |
output_format | png | jpeg | webp | gif | svg | The format in which the generated images are returned. This parameter is only… |
output_compression | integer | The compression level (0-100%) for the generated images. This parameter is… |
stream | boolean | Generate the image in streaming mode. Defaults to false. See the Image… |
partial_images | integer | The number of partial images to generate. This parameter is used for streaming… |
size | string | The size of the generated images. For gpt-image-2, gpt-image-2-2026-04-21… |
moderation | low | auto | Control the content-moderation level for images generated by the GPT image… |
background | transparent | opaque | auto | Set the background of the generated image(s). This parameter is only supported… |
style | string | Legacy style parameter for retired image models. Unsupported for GPT image… |
safety_identifier | string | A stable identifier for an end user in your organization, used for safety… |
user | string | Deprecated: use safety_identifier instead. This parameter remains accepted for… |
How to call it
Through the Smart Gateway, any client can run it by name with call_tool, or let the gateway find it with search_tools:
{
"name": "openai_api__create_image",
"arguments": {
"prompt": "…",
"model": "…"
}
}Or connect the OpenAI API server directly, which lists 371 tools including this one:
claude mcp add --transport http hj-openai-api https://mcp.hjlabs.in/mcp/openai-api \
--header "Authorization: Bearer YOUR_API_KEY"Try asking
Use the create image tool with frame_count set to ….