OpenAI API 文档（英文） | AI 原生开放教材

Earlier GPT Image models

The details below apply to earlier models, not Sunburst or Flare. For new integrations, use one of the GPT Image 2.5 models described above.

<details> <summary>GPT Image 2 settings and input fidelity</summary>

gpt-image-2 accepts any resolution in the size parameter when it satisfies the constraints below. Square images are typically fastest to generate.

Popular sizes	`1024x1024` (square) `1536x1024` (landscape) `1024x1536` (portrait) `2048x2048` (2K square) `2048x1152` (2K landscape) `3840x2160` (4K landscape) `2160x3840` (4K portrait) `auto` (default)
Size constraints	Maximum edge length must be less than or equal to `3840px` Both edges must be multiples of `16px` Long edge to short edge ratio must not exceed `3:1` Total pixels must be at least `655,360` and no more than `8,294,400`
Quality options	`low` `medium` `high` `auto` (default)

Image input fidelity

The input_fidelity parameter controls how strongly a model preserves details from input images during edits and reference-image workflows. For gpt-image-2, omit this parameter; the API doesn't allow changing it because the model processes every image input at high fidelity automatically.

Because gpt-image-2 always processes image inputs at high fidelity, image input tokens can be higher for edit requests that include reference images. To understand the cost implications, refer to the vision costs section.

</details> <details> <summary>Older-model pricing examples</summary>

Models prior to `gpt-image-2`

GPT Image models prior to gpt-image-2 generate images by first producing specialized image tokens. Both latency and eventual cost are proportional to the number of tokens required to render an image—larger image sizes and higher quality settings result in more tokens.

The number of tokens generated depends on image dimensions and quality:

Quality	Square (1024×1024)	Portrait (1024×1536)	Landscape (1536×1024)
Low	272 tokens	408 tokens	400 tokens
Medium	1056 tokens	1584 tokens	1568 tokens
High	4160 tokens	6240 tokens	6208 tokens

Note that you will also need to account for input tokens: text tokens for the prompt and image tokens for the input images if editing images. Because gpt-image-2 always processes image inputs at high fidelity, edit requests that include reference images can use more input tokens.

Refer to the pricing page for current text and image token prices, and use the Calculating costs section below to estimate request costs.

The final cost is the sum of:

input text tokens
input image tokens if using the edits endpoint
image output tokens

Calculating costs

Use the pricing calculator below to estimate request costs for GPT Image models. gpt-image-2 supports thousands of valid resolutions; the table below lists the same sizes used for previous GPT Image models for comparison. For GPT Image 1.5, GPT Image 1, and GPT Image 1 Mini, the legacy per-image output pricing table is also listed below. You should still account for text and image input tokens when estimating the total cost of a request.

A larger non-square resolution can sometimes produce fewer output tokens than a smaller or square resolution at the same quality setting.

<table style={{ borderCollapse: "collapse", tableLayout: "fixed", width: "100%" }}

<thead> <tr> <th style={{ textAlign: "left", padding: "8px", width: "28%" }}>Model <th style={{ textAlign: "left", padding: "8px", width: "14%" }}> Quality

  &lt;th style=&#123;&#123; padding: "8px", width: "19.33%" &#125;&#125;>1024 x 1024
  &lt;th style=&#123;&#123; padding: "8px", width: "19.33%" &#125;&#125;>1024 x 1536
  &lt;th style=&#123;&#123; padding: "8px", width: "19.34%" &#125;&#125;>1536 x 1024
</tr>

</thead> <tbody> <tr> <td rowSpan="3" style={{ padding: "8px", width: "28%" }}> GPT Image 2

Additional sizes available

  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>Low
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.006
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.005
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.005
</tr>
<tr>
  &lt;td style=&#123;&#123; padding: "8px" }}>Medium
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.053
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.041
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.041
</tr>
<tr>
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>High
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.211
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.165
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.165
</tr>

<tr>
  &lt;td rowSpan="3" style=&#123;&#123; padding: "8px", width: "28%" }}>
    GPT Image 1.5
  
  &lt;td style=&#123;&#123; padding: "8px" }}>Low
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.009
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.013
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.013
</tr>
<tr>
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>Medium
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.034
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.05
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.05
</tr>
<tr>
  &lt;td style=&#123;&#123; padding: "8px" }}>High
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.133
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.2
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.2
</tr>

<tr>
  &lt;td rowSpan="3" style=&#123;&#123; padding: "8px", width: "28%" &#125;&#125;>
    GPT Image 1
  
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>Low
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.011
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.016
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.016
</tr>
<tr>
  &lt;td style=&#123;&#123; padding: "8px" }}>Medium
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.042
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.063
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.063
</tr>
<tr>
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>High
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.167
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.25
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.25
</tr>

<tr>
  &lt;td rowSpan="3" style=&#123;&#123; padding: "8px", width: "28%" }}>
    GPT Image 1 Mini
  
  &lt;td style=&#123;&#123; padding: "8px" }}>Low
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.005
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.006
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.006
</tr>
<tr>
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>Medium
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.011
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.015
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.015
</tr>
<tr>
  &lt;td style=&#123;&#123; padding: "8px" }}>High
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.036
  &lt;td style=&#123;&#123; padding: "8px" &#125;&#125;>$0.052
  &lt;td style=&#123;&#123; padding: "8px" }}>$0.052
</tr>

</tbody> </details>

Earlier GPT Image models ​

Image input fidelity ​

Models prior to gpt-image-2 ​

Calculating costs ​

Earlier GPT Image models

Image input fidelity

Models prior to `gpt-image-2`

Calculating costs