> ## Documentation Index
> Fetch the complete documentation index at: https://docs.myrouter.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# GPT Text-to-Image

Use GPT image generation models to quickly generate high-quality images from text descriptions. Supports multiple size and quality options to meet various image generation needs.

## Request Headers

<ParamField header="Content-Type" type="string" required={true}>
  Enum: `application/json`
</ParamField>

<ParamField header="Authorization" type="string" required={true}>
  Bearer authentication format: Bearer \{\{API Key}}.
</ParamField>

## Request Body

<ParamField body="model" type="string" required={true}>
  The model used for image generation. Currently supports `gpt-image-1`, `gpt-image-1.5`.
</ParamField>

<ParamField body="prompt" type="string" required={true}>
  Text description of the desired image.

  For `gpt-image-1`, `gpt-image-1.5`, the maximum length is 32000 characters.
</ParamField>

<ParamField body="quality" type="string" required={false}>
  Quality of the generated image, Default: `auto`.

  For `gpt-image-1`, `gpt-image-1.5`, supported values are: `auto`, `high`, `medium`, `low`.
</ParamField>

<ParamField body="n" type="integer" required={false}>
  Number of images to generate, Range: 1\~10, Default: 1.
</ParamField>

<ParamField body="size" type="string" required={false}>
  Size of the generated image, Default: `auto`.

  For `gpt-image-1`, `gpt-image-1.5`, supported values are:

  * `1024x1024`: Square
  * `1536x1024`: Landscape
  * `1024x1536`: Portrait
  * `auto`: Default
</ParamField>

## Response Parameters

<ResponseField name="created" type="integer" required={true}>
  Unix timestamp (in seconds) of when the image was generated.
</ResponseField>

<ResponseField name="data" type="array" required={true}>
  List of generated images.

  <Expandable title="properties" defaultOpen={false}>
    <ResponseField name="b64_json" type="string" required={true}>
      Base64-encoded string of the generated image.
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="output_format" type="string" required={true}>
  Output format of the generated image. Possible values: `png`, `webp`, `jpeg`.
</ResponseField>

<ResponseField name="quality" type="string" required={true}>
  Quality of the generated image. Possible values: `low`, `medium`, `high`.
</ResponseField>

<ResponseField name="size" type="string" required={true}>
  Size of the generated image. Possible values: `1024x1024`, `1024x1536`, `1536x1024`.
</ResponseField>

<ResponseField name="usage" type="object" required={false}>
  Only supported by `gpt-image-1`, `gpt-image-1.5`. Token usage information for image generation.

  <Expandable title="properties" defaultOpen={false}>
    <ResponseField name="input_tokens" type="integer" required={true}>
      Number of tokens for the input prompt (including images and text).
    </ResponseField>

    <ResponseField name="input_tokens_details" type="object" required={false}>
      Detailed information about input tokens.

      <Expandable title="properties" defaultOpen={false}>
        <ResponseField name="image_tokens" type="integer" required={true}>
          Number of image tokens in the input prompt.
        </ResponseField>

        <ResponseField name="text_tokens" type="integer" required={true}>
          Number of text tokens in the input prompt.
        </ResponseField>
      </Expandable>
    </ResponseField>

    <ResponseField name="output_tokens" type="integer" required={true}>
      Number of output tokens generated by the model.
    </ResponseField>

    <ResponseField name="total_tokens" type="integer" required={true}>
      Total number of tokens consumed for this image generation (including images and text).
    </ResponseField>
  </Expandable>
</ResponseField>