> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.beatapi.io/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.beatapi.io/_mcp/server.

# GPT Image 2 Standard

POST https://api.beatapi.io/v1/images/tasks
Content-Type: application/json

根据文本和最多 16 张参考图生成或编辑图片，支持 1K、2K、4K 或精确像素尺寸。按每次生成实际用掉的 token 计费，可用 `quality` 设定输出 token 数。- 按 token 计费：文本输入、图片输入和输出 token 各按每 100 万 token 的单价计算。下方的每张价格是按 `medium` 质量的估算。
- `quality` 决定一次生成用掉多少输出 token，也就决定价格：取值越低越便宜。不传时为 `medium`。
- 只支持异步：用 `POST /v1/images/tasks` 创建任务，再轮询 `GET /v1/tasks/{task_id}`。生成在 BeatAPI 一侧进行，耗时再长也不会占住你的连接。该模型不提供同步接口 `POST /v1/images/generations`。
- 每个任务生成一张图片。需要多张图片时，请创建多个任务。
- 文生图，或编辑、合成最多 16 张以公网 HTTPS 链接给出的参考图。
- 用 `resolution` 和 `aspect_ratio` 选择画幅，或用一个精确的 `size`，例如 `1536x1024`。两者不能同时使用。这是按 token 计费的 [`gpt-image-2`](/image-api/gpt-image-2)。模型和请求完全相同：字段、分辨率、宽高比和参考图都一样。`gpt-image-2` 每张图片一个固定价格；`gpt-image-2-std` 按每次生成实际用掉的 token 收费，并接受 `quality` 设置。[查看价格](https://beatapi.io/zh/pricing)。POST/v1/images/tasks试一试在调试窗口里打开本模型，填入你的 BeatAPI API 密钥即可创建任务。调用是真实的，费用从你自己的余额中扣除。## 模型 ID固定价型号和本型号接受同样的请求，区别只在 `quality` 和价格的计算方式。下表的取值直接来自网关契约。| 模型 ID                 | `resolution`     | `quality`               | `images` 上限 | 价格                                                        |
| --------------------- | ---------------- | ----------------------- | ----------- | --------------------------------------------------------- |
| `gpt-image-2`         | `1K`, `2K`, `4K` | —                       | 16          | 按尺寸档位每张图片一个固定价格。不接受 `quality`。                            |
| **`gpt-image-2-std`** | `1K`, `2K`, `4K` | `low`, `medium`, `high` | 16          | 按生成用掉的 token、以每 100 万 token 的单价计费。`quality` 决定输出 token 数。 |## 接口与鉴权`POST https://api.beatapi.io/v1/images/tasks`Authorization
string
必需你的 BeatAPI API 密钥，以 `Bearer <BEATAPI_API_KEY>` 形式发送。在[控制台](https://beatapi.io/dashboard)创建密钥。密钥只能保存在你的服务端，不要放进浏览器或移动端应用。请求体使用 JSON，并设置 `Content-Type: application/json`。`Idempotency-Key` 为可选：每个逻辑请求发送一个唯一值（最长 255 个字符），仅在重试完全相同的请求体时复用。24 小时内，用相同的键和请求体重试会再次返回第一次的响应，并带上 `Idempotent-Replayed: true`；相同的键搭配不同的请求体则返回 `409 idempotency_conflict`。非 2xx 的响应不会被保存，因此 400 或 402 之后的重试会重新执行。## 请求流程向接口 `POST` 下方的参数。返回 `201` 表示任务已被接受，其价格已从你的余额中预留；任务在后台运行。保存 `data.id`。调用 `GET /v1/tasks/{task_id}`，两次调用之间等待 `data.poll_after_seconds` 秒（图片 5 秒，视频 8 秒），直到 `status` 为 `succeeded` 或 `failed`。也可以为 `task.succeeded` 和 `task.failed` 注册 [Webhook](/webhooks)；仍需保留轮询作为兜底，因为因处理超时而终止的任务不会发送事件。状态为 `succeeded` 时，下载每个 `data.output.media[].url` 并保存你需要的文件；BeatAPI 不承诺结果链接的保留时长。状态为 `failed` 时，读取 `data.error_code` 和 `data.error_message`：预扣的金额已退回你的余额，`data.retryable` 表示再次发送相同请求是否可能成功。## 输入模式| 模式      | 必填输入                        | 说明                                                |
| ------- | --------------------------- | ------------------------------------------------- |
| 文生图     | `model`, `prompt`           | 不要传 `images`。                                     |
| 编辑或合成图片 | `model`, `prompt`, `images` | 1 到 16 个公网 HTTPS 图片链接。在 `prompt` 中描述要修改、保留或合成的内容。 |## 请求参数model
string
必需要运行的模型。**取值**：`gpt-image-2-std`**取值有误时**- 缺失：`"model" is required`
- 未知的模型 ID：`"model" gpt-image-9 is not catalogued`
- 把视频模型发到了这个接口：`"model" seedance-2.5 is served by POST /v1/videos/tasks, not this endpoint`prompt
string
必需要画什么，或要修改参考图中的什么。用平实的语言效果最好：主体、风格、光线、构图，以及必须出现在图片中的文字。**长度**：1–5000 个字符- 长度按字符计算（一个中日韩文字算一个字符）。
- 传了 `images` 时，请说明每张图的作用，例如 "Use the first image for the product and the second for the background"。**取值有误时**- 缺失：`"prompt" is required`
- 为空或超过长度上限：`"prompt" has an unsupported length`
- 不是字符串：`"prompt" must be a string`images
string[]
可选要编辑或合成的参考图。传入该字段会把请求从文生图切换为图片编辑。**数量**：1–16  \
每一项都必须是公网 `https://` 链接。本地文件请先[上传](/quick-guide#upload-an-input-file)（`POST /v1/files`），再传入返回的 `data.url`。- 每个链接必须通过公网 HTTPS 直接返回图片文件本身（PNG、JPEG 或 WebP），且不超过 50 MB。网关在创建任务之前会下载每个链接开头的若干字节，并根据这些字节识别类型，而不是根据文件名或 `Content-Type`。
- 指向网页、登录页、已过期的签名链接或有防盗链的主机的链接会被拒绝，因为它们返回的不是图片。
- 错误信息中的位置从 0 开始：`images[0]` 是第一个链接。**取值有误时**- 超过数量上限：`"images" accepts at most 16 items`
- 空数组：`"images" requires at least 1 item`
- 不是 https\:// 链接：`"images[0]" must be a public HTTPS URL`
- 私有或不安全的地址：`"images[0]" must be a publicly reachable HTTPS image URL`
- 主机返回 4xx 错误：`"images[0]" could not be downloaded: the URL returned HTTP 404`
- 链接返回的不是 PNG、JPEG 或 WebP：`"images[0]" is not a PNG, JPEG or WebP image: the URL returned text/html`
- 大于 50 MB：`"images[2]" is 63.4 MB; images must be 50 MB or smaller`**示例**```json
"images": [
  "https://cdn.beatapi.io/samples/smart-bottle.png",
  "https://cdn.beatapi.io/samples/neon-singer.png"
]
```aspect_ratio
string
可选默认值: auto图片的形状，以 宽:高 表示。与 `resolution` 一起传，或两者都不传而改传 `size`。**可选值**：`auto`, `1:1`, `3:2`, `2:3`, `4:3`, `3:4`, `5:4`, `4:5`, `16:9`, `9:16`, `2:1`, `1:2`, `3:1`, `1:3`, `21:9`, `9:21`  \
**默认值**：`auto`- 默认值是 `auto`，所以省略该字段的请求同样会生成正方形。
- 支持 `2:1`、`1:2`、`3:1`、`1:3`、`21:9` 和 `9:21` 等全景比例。最宽或最高的画幅是 3:1。
- 不能与 `size` 同时使用。`auto` 不是“沿用参考图的形状”。无论是否传了 `images`，它都会在所选 `resolution` 下生成正方形画幅。要把编辑结果改成其他形状，请指定比例，或传 `size`。**取值有误时**- 取值不在列表中：`"aspect_ratio" must be one of: [auto 1:1 3:2 2:3 4:3 3:4 5:4 4:5 16:9 9:16 2:1 1:2 3:1 1:3 21:9 9:21]`
- 与 `size` 一起传：`"size" already fixes the output; do not send "aspect_ratio" with it`resolution
string
可选默认值: 1K图片的尺寸档位。档位越高，图片越大、价格越高；具体像素尺寸取决于 `aspect_ratio`，由模型决定。**可选值**：`1K`, `2K`, `4K`  \
**默认值**：`1K`- K 必须大写：`2k` 会被拒绝。
- 本页不承诺某个档位对应的精确像素尺寸。如果需要精确画幅，请传 `size`。
- 不能与 `size` 同时使用；`size` 自带尺寸。**取值有误时**- 取值不在列表中：`"resolution" must be one of: [1K 2K 4K]`
- 与 `size` 一起传：`"size" already fixes the output; do not send "resolution" with it`size
string
可选以像素表示的精确输出画幅，格式为 `WIDTHxHEIGHT`，例如 `1536x1024`。它会取代 `resolution` 和 `aspect_ratio`。- 两条边都必须是 16 的倍数，且在 16 到 3840 px 之间。
- 像素总数必须在 655,360 到 8,294,400 之间，长边最多是短边的三倍。
- 分隔符可以是 `x`、`X` 或 `×`；两侧的空格会被忽略。
- 像素总数会改变输出 token 数，也就改变价格。任务结算前，预扣的是像素总数所属档位的估算价：不超过 2,097,152 像素为 1K，不超过 5,898,240 为 2K，超过则为 4K。
- 不要同时传 `resolution` 或 `aspect_ratio`，即使是默认值也不行。`size` 按所传的值校验，但本页不保证交付的图片恰好是这些像素。如果你的流程依赖精确尺寸，请读取已保存的文件。**取值有误时**- 不是字符串：`"size" must be a string`
- 不是 WIDTHxHEIGHT 形式（单独一个数字、`auto`、逗号）：`"size" must be WIDTHxHEIGHT in pixels, for example 1536x1024`
- 某条边不是 16 的倍数：`"size" width and height must be multiples of 16`
- 某条边小于 16 或大于 3840：`"size" edges must be between 16 and 3840 pixels`
- 像素太少或太多：`"size" must have between 655,360 and 8,294,400 pixels; 512x512 has 262,144`
- 宽或高超过 3:1：`"size" must not be wider or taller than 3:1`
- 与 `resolution` 一起传：`"size" already fixes the output; do not send "resolution" with it`
- 与 `aspect_ratio` 一起传：`"size" already fixes the output; do not send "aspect_ratio" with it`**示例**```json
"size": "1536x1024"
```quality
string
可选默认值: medium模型在这张图片上投入多少功夫。它决定一次生成用掉多少输出 token，也就决定价格：取值越低越便宜，越高越贵。**可选值**：`low`, `medium`, `high`  \
**默认值**：`medium`- 不传时为 `medium`，本页的每张价格就是按这个质量估算的。
- 固定价的 [`gpt-image-2`](/image-api/gpt-image-2) 不接受这个字段，传入会被拒绝。**取值有误时**- 取值不在列表中：`"quality" must be one of: [low medium high]`**示例**```json
"quality": "low"
```background
string
可选默认值: auto图片是有填充背景，还是透明背景。**可选值**：`auto`, `opaque`, `transparent`  \
**默认值**：`auto`- `auto`（默认值）由模型自行选择。`opaque` 要求填充背景。
- `transparent` 要求背景无颜色的图片。结果是带 alpha 通道的 PNG；请查看 `output.media[].mime_type`。**取值有误时**- 取值不在列表中：`"background" must be one of: [auto opaque transparent]`网关还会在创建任务之前检查以下组合：- `size` 写为 `宽x高`，替代 `resolution` 和 `aspect_ratio`：两边均为 16 的倍数，各为 16–3840 像素；总像素为 655,360–8,294,400；最长边与最短边之比不超过 3:1。
- `size` 按这次出图实际用到的 token 计费，不按档位。
- `quality` 决定输出 token 数，也就决定价格；默认 `medium`。
- 按 token 以牌价计费，token 数按每次出图实际用到的计（文本输入、图片输入、输出）；列出的每张价格是按 medium 质量的估算。
- 这是官方版本，按 token 计费：支持 `quality` 取 `low`、`medium`、`high`；固定每张价格的 `gpt-image-2` 不支持。## 输入素材限制网关会在创建任务之前读取每一项输入，超出这些限制的输入会被拒绝，并返回点名该输入的 `400 bad_request`。不扣费。- 参考图：PNG、JPEG 或 WebP，按文件内容识别；每张不超过 50 MB（十进制 MB；仅在主机声明大小时检查）；1 到 16 个链接。GIF、HEIC 和 SVG 会被拒绝。
- 不检查参考图本身的像素或宽高比限制。
- 如果主机未在时限内响应，创建任务时不会拒绝该链接。网关会在任务派发时再次获取；若仍无法获取，任务失败并退款。
- 有本地文件？先用 `POST /v1/files` 上传，再传入返回的 `data.url`。## 选择画幅：`resolution` 和 `aspect_ratio`，或 `size`指定图片大小和宽高有两种方式，二者互斥：- **档位加比例。** 传 `resolution`（`1K`、`2K` 或 `4K`），需要指定形状时再传 `aspect_ratio`。两者都不传，则得到 `1K` 和 `auto`，即正方形画幅。
- **精确尺寸。** 只传 `size`，例如 `1536x1024`。像素总数会改变输出 token 数；任务结算前，按它所属的档位预扣（见上方组合规则）。把 `size` 与 `resolution` 或 `aspect_ratio` 一起传会被拒绝，错误为 `"size" already fixes the output; do not send "resolution" with it`（或 `"aspect_ratio"`）。即使另一个字段取的是默认值，也会触发该检查。## 先提交，再轮询该模型只以任务方式运行。`POST /v1/images/tasks` 会立即返回，任务 ID 在 `data.id`；之后每隔 `data.poll_after_seconds` 调用一次 `GET /v1/tasks/{task_id}`，直到 `data.status` 为 `succeeded` 或 `failed`。生成在 BeatAPI 一侧进行，耗时再长也不会占住你的连接，也不会触发你客户端的超时。该模型不提供同步接口 `POST /v1/images/generations`。```bash title="Submit, then poll"
# 1. Create the task. The call returns at once; the task ID is in data.id.
TASK_ID=$(curl -sS -X POST https://api.beatapi.io/v1/images/tasks \
  -H "Authorization: Bearer $BEATAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-image-2-std","prompt":"A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field","resolution":"2K","quality":"medium"}' | jq -r '.data.id')

# 2. Poll until the task is final. The render runs on BeatAPI, not on this connection.
while true; do
  TASK=$(curl -sS "https://api.beatapi.io/v1/tasks/$TASK_ID" -H "Authorization: Bearer $BEATAPI_API_KEY")
  STATUS=$(echo "$TASK" | jq -r '.data.status')
  if [ "$STATUS" = "succeeded" ] || [ "$STATUS" = "failed" ]; then break; fi
  sleep 5
done
echo "$TASK" | jq '.data.output.media[].url, .data.usage'
```通过 Capabilities API 调用时是同一个任务：用 `POST /v1/capabilities/run` 启动，再用返回的任务 ID 发送状态查询，直到 `succeeded` 或 `failed`。```json title="POST /v1/capabilities/run"
{"reference":"model:gpt-image-2-std","input":{"model":"gpt-image-2-std","prompt":"A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field","resolution":"2K","quality":"medium"}}
``````json title="POST /v1/capabilities/run (status)"
{"reference":"model:gpt-image-2-std","operation":"status","task_id":"<task_id>"}
```## 按 token 计费与固定价的对比|                | `gpt-image-2-std`                      | `gpt-image-2`   |
| -------------- | -------------------------------------- | --------------- |
| 价格             | 生成用掉的 token，按下方每 100 万 token 的单价       | 按尺寸档位每张图片一个固定价格 |
| 创建任务时预扣        | 该档位的每张估算价                              | 这张图片的价格         |
| 任务成功时收取        | 按实际用掉的 token 结算；`data.usage` 可能与预扣金额不同 | 预扣的价格           |
| `quality`      | 接受，默认 `medium`                         | 拒绝              |
| 字段、分辨率、宽高比、参考图 | 相同                                     | 相同              |
| 失败的任务          | 不收费                                    | 不收费             |## 该模型不接受的字段图片接口认识一些其他图片模型使用的字段。在这里传入其中任何一个都会被拒绝，而不是被忽略，这样你不会为一个没有效果的设置付费：- `seed`、`output_format`、`enhance_prompt` → `field "seed" is not supported by model gpt-image-2-std`（其中是你所传的字段）。结果格式不能选择：请读取输出中的 `mime_type`。
- 其他任何未知字段，例如 `n` 或 `moderation` → `unknown field: n`。没有 `n` 这个字段：一个任务只生成一张图片。与固定价的 [`gpt-image-2`](/image-api/gpt-image-2) 不同，本型号接受 `quality`。## 请求示例```bash title="cURL"
curl --request POST \
  --url https://api.beatapi.io/v1/images/tasks \
  --header "Authorization: Bearer $BEATAPI_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "gpt-image-2-std",
  "prompt": "A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field",
  "aspect_ratio": "3:2",
  "resolution": "2K",
  "quality": "medium"
}'
``````python title="Python"
import os
import requests

response = requests.post(
    "https://api.beatapi.io/v1/images/tasks",
    headers={"Authorization": f"Bearer {os.environ['BEATAPI_API_KEY']}"},
    json={
      "model": "gpt-image-2-std",
      "prompt": "A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field",
      "aspect_ratio": "3:2",
      "resolution": "2K",
      "quality": "medium"
    },
    timeout=60,
)
body = response.json()
if not response.ok:
    raise RuntimeError(f"{response.status_code} {body['error']['code']}: {body['error']['message']}")
task = body["data"]
print(task["id"], task["status"])
``````javascript title="JavaScript"
const response = await fetch('https://api.beatapi.io/v1/images/tasks', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.BEATAPI_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    "model": "gpt-image-2-std",
    "prompt": "A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field",
    "aspect_ratio": "3:2",
    "resolution": "2K",
    "quality": "medium"
  }),
});
const body = await response.json();
if (!response.ok) throw new Error(`${response.status} ${body.error.code}: ${body.error.message}`);
console.log(body.data.id, body.data.status);
```### 文生图根据提示词生成一张 2K 横版图片，指定了档位和比例。```bash
curl --request POST \
  --url https://api.beatapi.io/v1/images/tasks \
  --header "Authorization: Bearer $BEATAPI_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "gpt-image-2-std",
  "prompt": "A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field",
  "aspect_ratio": "3:2",
  "resolution": "2K",
  "quality": "medium"
}'
```### 低质量草稿第一个请求改用 `quality: "low"` 和 1K，用掉的输出 token 更少、价格更低。适合草稿和预览。```bash
curl --request POST \
  --url https://api.beatapi.io/v1/images/tasks \
  --header "Authorization: Bearer $BEATAPI_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "gpt-image-2-std",
  "prompt": "A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field",
  "aspect_ratio": "3:2",
  "resolution": "1K",
  "quality": "low"
}'
```### 编辑一张图片更换背景并保留商品。这里明确指定了形状，因为 `auto` 会生成正方形。```bash
curl --request POST \
  --url https://api.beatapi.io/v1/images/tasks \
  --header "Authorization: Bearer $BEATAPI_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "gpt-image-2-std",
  "prompt": "Keep the bottle exactly as it is. Replace the background with a sunlit kitchen counter and add a soft reflection under the bottle.",
  "images": [
    "https://cdn.beatapi.io/samples/smart-bottle.png"
  ],
  "aspect_ratio": "1:1",
  "resolution": "1K"
}'
```### 合成多张图片在提示词中按位置指明每张参考图。```bash
curl --request POST \
  --url https://api.beatapi.io/v1/images/tasks \
  --header "Authorization: Bearer $BEATAPI_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "gpt-image-2-std",
  "prompt": "Place the bottle from the first image on a neon-lit stage like the one in the second image. Keep the bottle label readable.",
  "images": [
    "https://cdn.beatapi.io/samples/smart-bottle.png",
    "https://cdn.beatapi.io/samples/neon-singer.png"
  ],
  "aspect_ratio": "16:9",
  "resolution": "2K"
}'
```### 精确尺寸1536x1024 的画幅。`size` 单独使用：不传 `resolution`，也不传 `aspect_ratio`。按 1K 的估算价预扣。```bash
curl --request POST \
  --url https://api.beatapi.io/v1/images/tasks \
  --header "Authorization: Bearer $BEATAPI_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "gpt-image-2-std",
  "prompt": "A flat illustration of a lighthouse on a cliff at dawn, pastel colours, clean shapes",
  "size": "1536x1024"
}'
```### 透明背景没有背景的贴纸风格主体。结果是带 alpha 通道的 PNG。```bash
curl --request POST \
  --url https://api.beatapi.io/v1/images/tasks \
  --header "Authorization: Bearer $BEATAPI_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "gpt-image-2-std",
  "prompt": "A single cartoon red fox sitting, sticker style, thick white outline, isolated on a transparent background",
  "aspect_ratio": "1:1",
  "resolution": "1K",
  "background": "transparent"
}'
```## 响应### 创建任务（201）任务对象。任务成功之前 `output` 为 `null`。标注“运行中”的字段会在任务结束后消失。```json
{
  "data": {
    "id": "task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ",
    "object": "task",
    "task_kind": "image",
    "capability_id": "gpt-image-2-std",
    "capability_version": 1,
    "media_type": "image",
    "model": "gpt-image-2-std",
    "status": "queued",
    "stage": "queued",
    "created_at": 1791993600,
    "updated_at": 1791993600,
    "completed_at": null,
    "poll_after_seconds": 5,
    "output": null,
    "usage": {
      "credits_reserved": 0.069576,
      "credits_settled": 0,
      "credits_refunded": 0,
      "credits_charged": 0.069576
    },
    "request_id": "req_5f0c2a9e4b7d4e31",
    "error_code": null,
    "error_message": null
  }
}
```| 字段                                     | 类型                | 说明                                                                        |
| -------------------------------------- | ----------------- | ------------------------------------------------------------------------- |
| `data.id`                              | `string`          | 任务 ID：`task_` 后接 32 位字母和数字。用于轮询以及匹配 Webhook 事件。                           |
| `data.object`                          | `string`          | 固定为 `task`。                                                               |
| `data.task_kind`                       | `string`          | `image` 或 `video`。                                                        |
| `data.capability_id`                   | `string`          | 你发送的模型 ID。                                                                |
| `data.capability_version`              | `integer`         | 模型的契约版本，当前为 `1`。                                                          |
| `data.media_type`                      | `string`          | `image` 或 `video`。                                                        |
| `data.model`                           | `string`          | 你发送的模型 ID（与 `capability_id` 相同）。                                          |
| `data.status`                          | `string`          | `queued`、`processing`、`succeeded` 或 `failed`。只有后两个是终态。                    |
| `data.stage`                           | `string`          | 与 `status` 相同；为旧版客户端保留。                                                   |
| `data.created_at`                      | `integer`         | 任务创建时间，Unix 秒。                                                            |
| `data.updated_at`                      | `integer`         | 最后一次变更时间，Unix 秒。                                                          |
| `data.completed_at`                    | `integer \| null` | 任务结束时间，Unix 秒；运行中为 `null`。                                                |
| `data.poll_after_seconds`              | `integer`         | 运行中：下一次轮询前需要等待的秒数（图片 5，视频 8）。                                             |
| `data.typical_seconds`                 | `object`          | 运行中且近期样本足够时出现：在最近的 `window` 内，根据 `samples` 个任务统计的完成时间 `p50` 和 `p90`，单位为秒。 |
| `data.output`                          | `object \| null`  | 任务结果；`status` 为 `succeeded` 之前为 `null`。见下方输出字段。                           |
| `data.usage.credits_reserved`          | `number`          | 创建任务时从你的余额中预扣的美元金额。                                                       |
| `data.usage.credits_charged`           | `number`          | 该任务的费用（美元）；失败的任务为 `0`。                                                    |
| `data.usage.credits_settled`           | `number`          | 最终结算扣除的美元金额；任务成功时设置，否则为 `0`。                                              |
| `data.usage.credits_refunded`          | `number`          | 退回你余额的美元金额；失败的任务在退款记录完成后等于预扣金额。                                           |
| `data.usage.billable_duration_seconds` | `integer`         | 仅视频：计价所依据的秒数。模型未上报时长时不出现。                                                 |
| `data.request_id`                      | `string`          | 请求 ID。联系支持时请附上。                                                           |
| `data.error_code`                      | `string \| null`  | 失败码；任务未失败时为 `null`。                                                       |
| `data.error_message`                   | `string \| null`  | 出了什么问题以及该改什么；任务未失败时为 `null`。                                              |### 任务完成`GET /v1/tasks/{task_id}` 返回 HTTP 200 和 `status: "succeeded"`，结果在 `data.output` 中。```json
{
  "data": {
    "id": "task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ",
    "object": "task",
    "task_kind": "image",
    "capability_id": "gpt-image-2-std",
    "capability_version": 1,
    "media_type": "image",
    "model": "gpt-image-2-std",
    "status": "succeeded",
    "stage": "succeeded",
    "created_at": 1791993600,
    "updated_at": 1791993690,
    "completed_at": 1791993690,
    "output": {
      "media": [
        {
          "type": "image",
          "url": "https://media.beatapi.io/outputs/task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ/0.png",
          "mime_type": "image/png"
        }
      ],
      "r2_url": "https://media.beatapi.io/outputs/task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ/0.png"
    },
    "usage": {
      "credits_reserved": 0.069576,
      "credits_settled": 0.069576,
      "credits_refunded": 0,
      "credits_charged": 0.069576
    },
    "request_id": "req_5f0c2a9e4b7d4e31",
    "error_code": null,
    "error_message": null
  }
}
```#### 输出字段| 字段                         | 类型         | 说明                                                                                  |
| -------------------------- | ---------- | ----------------------------------------------------------------------------------- |
| `output.media`             | `object[]` | 生成的文件；该模型只有一项。                                                                      |
| `output.media[].type`      | `string`   | 固定为 `image`。                                                                        |
| `output.media[].url`       | `string`   | 已保存图片的 HTTPS 链接。请下载并自行保存；不承诺保留期限。                                                   |
| `output.media[].mime_type` | `string`   | 已保存文件的类型，例如 `image/png`。这些模型没有 `output_format` 字段，因此 BeatAPI 不会转换文件：请读取该值，不要自行假定类型。 |
| `output.r2_url`            | `string`   | 第一个 media 链接的重复，供旧版客户端使用。请读取 `media`。                                               |### 任务失败失败的任务在 `GET /v1/tasks/{task_id}` 上仍然是 HTTP 200：失败信息在响应体里。预扣金额会全额退回，因此不会扣费。```json
{
  "data": {
    "id": "task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ",
    "object": "task",
    "task_kind": "image",
    "capability_id": "gpt-image-2-std",
    "capability_version": 1,
    "media_type": "image",
    "model": "gpt-image-2-std",
    "status": "failed",
    "stage": "failed",
    "created_at": 1791993600,
    "updated_at": 1791993690,
    "completed_at": 1791993690,
    "output": null,
    "usage": {
      "credits_reserved": 0.069576,
      "credits_settled": 0,
      "credits_refunded": 0.069576,
      "credits_charged": 0
    },
    "retryable": true,
    "request_id": "req_5f0c2a9e4b7d4e31",
    "error_code": "processing_failed",
    "error_message": "The task failed during processing on our side. Retry; a failed task is refunded."
  }
}
```| 字段                   | 类型        | 说明                                                                                                                                                                          |
| -------------------- | --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `data.error_code`    | `string`  | `bad_request` 和 `content_policy_violation`（需修改请求）之一，或 `processing_unavailable`、`processing_timeout`、`processing_failed` 和 `result_transfer_failed`（稍后重试）之一。见[错误码](/errors)。 |
| `data.error_message` | `string`  | 一句话，指出问题和处理方式。                                                                                                                                                              |
| `data.retryable`     | `boolean` | 仅在任务失败时出现：为 `true` 表示再次发送相同请求可能成功。                                                                                                                                          |
| `data.usage`         | `object`  | 退款记录完成后（通常就在任务失败的那一刻）：`credits_charged` 和 `credits_settled` 为 `0`；`credits_refunded` 等于 `credits_reserved`。                                                                 |## 完整示例创建任务，按服务端给出的轮询提示等待，然后打印结果链接。请在环境变量中设置 `BEATAPI_API_KEY` 并安装 `requests`。```python
import os
import time
import uuid

import requests

API = "https://api.beatapi.io"
HEADERS = {"Authorization": f"Bearer {os.environ['BEATAPI_API_KEY']}"}


def create_task(body: dict) -> dict:
    # One Idempotency-Key per logical request: a retry with the same key cannot create a second task.
    headers = {**HEADERS, "Idempotency-Key": str(uuid.uuid4())}
    for attempt in range(3):
        response = requests.post(f"{API}/v1/images/tasks", headers=headers, json=body, timeout=60)
        if response.status_code in (429, 503) and attempt < 2:
            time.sleep(int(response.headers.get("Retry-After", 10)))
            continue
        break
    try:
        payload = response.json()
    except ValueError:  # an edge error page is not JSON
        response.raise_for_status()
        raise
    if not response.ok:
        error = payload["error"]
        raise RuntimeError(f"{response.status_code} {error['code']}: {error['message']} (request_id={error.get('request_id')})")
    return payload["data"]


def wait_for_task(task_id: str, timeout_seconds: int = 1800) -> dict:
    deadline = time.monotonic() + timeout_seconds
    while time.monotonic() < deadline:
        response = requests.get(f"{API}/v1/tasks/{task_id}", headers=HEADERS, timeout=30)
        if response.status_code == 429 or response.status_code >= 500:
            time.sleep(int(response.headers.get("Retry-After", 10)))
            continue
        response.raise_for_status()
        task = response.json()["data"]
        if task["status"] in ("succeeded", "failed"):
            return task
        time.sleep(task.get("poll_after_seconds", 5))
    raise TimeoutError(f"task {task_id} is still running; keep polling later")


task = create_task({
  "model": "gpt-image-2-std",
  "prompt": "A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field",
  "aspect_ratio": "3:2",
  "resolution": "2K",
  "quality": "medium"
})
print("created", task["id"])
task = wait_for_task(task["id"])
if task["status"] == "failed":
    raise SystemExit(f"{task['error_code']}: {task['error_message']}")
for item in task["output"]["media"]:
    print(item["url"])
```## 计费- 按 token 计费，单价见下表（每 100 万 token）：文本输入（提示词）、图片输入（`images` 中的参考图）和输出（生成的图片）。token 由模型计数；`quality`、画幅和参考图都会改变数量。
- 每张价格是按 `medium` 质量、各档位正方形画幅、不带参考图生成一张的估算。`low` 用的输出 token 更少，更高的取值用得更多。
- 创建任务时，从你的余额（以及密钥额度，如果设置了的话）预扣该档位的估算价。任务成功时按实际用掉的 token 结算，所以最终的 `data.usage` 可能与预扣金额不同。在任务创建之前就被拒绝的请求不收费。
- 失败的任务全额退回。
- 固定价的 [`gpt-image-2`](/image-api/gpt-image-2) 是同一个模型，不管生成用了多少，每张图片都是一个固定价格。当前牌价，与[价格页](https://beatapi.io/pricing)一致。享有协商折扣的账户实付更低；任务的 `data.usage` 始终显示实际扣费金额。| 选项                         | 牌价（美元）     |
| -------------------------- | ---------- |
| 1 张图片 · 1K · 按 medium 质量估算 | \$0.034242 |
| 1 张图片 · 2K · 按 medium 质量估算 | \$0.069576 |
| 1 张图片 · 4K · 按 medium 质量估算 | \$0.115635 |
| 输入 · 每 100 万 tokens        | \$3.25     |
| 图片输入 · 每 100 万 tokens      | \$5.2      |
| 输出 · 每 100 万 tokens        | \$19.5     |## 常见错误| 错误或现象                                                                            | 原因                                                        | 处理方式                                                          |
| -------------------------------------------------------------------------------- | --------------------------------------------------------- | ------------------------------------------------------------- |
| 400 `"size" already fixes the output; do not send "resolution" with it`          | `size` 与 `resolution` 或 `aspect_ratio` 一起传了，即使取的是默认值。     | 只传 `size`，或只传 `resolution` 和 `aspect_ratio` 而不传 `size`。       |
| 400 `"size" width and height must be multiples of 16`                            | 尺寸如 `1000x1000` 或 `1920x1080`（1080 不是 16 的倍数）。            | 把两条边取整为 16 的倍数，例如 `1920x1088`。                                |
| 400 `"size" must have between 655,360 and 8,294,400 pixels; 512x512 has 262,144` | 画幅太小或太大。`4096x4096` 会更早因 3840 px 的边长限制而失败。                | 边长不超过 3840 px，像素总数保持在 655,360 到 8,294,400 之间。                 |
| 400 `"resolution" must be one of: [1K 2K 4K]`                                    | 使用了小写的 `2k`、`8K`，或在 `resolution` 中填了 `2048x2048` 这样的像素尺寸。 | 发送 `1K`、`2K` 或 `4K`，需要像素尺寸时改用 `size` 字段。                      |
| 400 `"quality" must be one of: [low medium high]`                                | 取值不在列表中，或写成了大写，例如 `High`。                                 | 传列表中的一个值，或不传该字段以使用 `medium`。                                  |
| 400 `field "seed" is not supported by model gpt-image-2-std`                     | 来自其他图片模型的字段（`seed`、`output_format`、`enhance_prompt`）。     | 删除该字段。                                                        |
| 400 `unknown field: n`                                                           | 想在一个任务里生成多张图片。                                            | 删除 `n`，每张图片创建一个任务。                                            |
| 400 `"images[0]" must be a public HTTPS URL`                                     | 使用了 `http://` 链接、`data:` URI 或本地路径。                       | 把文件放到 HTTPS 地址上，或用 `POST /v1/files` 上传并使用 `data.url`。         |
| 400 `"images[1]" is not a PNG, JPEG or WebP image: the URL returned text/html`   | 链接打开的是网页、登录页或已过期的签名链接，而不是文件。                              | 直接链接到图片文件。                                                    |
| 400 `"images[0]" could not be downloaded: the URL returned HTTP 403`             | 主机拒绝服务器下载（防盗链或私有存储桶）。                                     | 把文件设为公开，或用 `POST /v1/files` 上传。                               |
| 编辑后的图片是正方形                                                                       | `aspect_ratio` 被省略或设为 `auto`，这会生成正方形画幅。                   | 指定你想要的比例，或传 `size`。                                           |
| 任务 `failed`，错误码 `content_policy_violation`                                       | 提示词、参考图或生成的图片被内容审核拒绝。                                     | 修改提示词或图片。原样重试仍会失败；不收费。                                        |
| 任务 `failed`，错误码 `processing_timeout`                                             | 图片未在处理时限内完成。                                              | 重试；失败的任务已退款。                                                  |
| 404 `POST /v1/images/generations`                                                | 该模型只以异步任务方式提供，同步接口不可用。                                    | 用 `POST /v1/images/tasks` 创建任务，再轮询 `GET /v1/tasks/{task_id}`。 |
| 收费与每张价格不一致                                                                       | 收费按生成实际用掉的 token 结算；每张价格只是估算。                             | 查看已完成任务的 `data.usage`。想少用输出 token，传 `quality: "low"`。         |## HTTP 错误速查任务生成之前的错误会以非 2xx 响应返回，不扣费。请根据 `error.code` 或 `error.retryable` 判断处理方式；`message` 会指出问题所在。完整列表和重试策略见[错误码](/errors)。```json
{
  "error": {
    "code": "bad_request",
    "message": "\"prompt\" is required",
    "retryable": false,
    "request_id": "req_5f0c2a9e4b7d4e31"
  }
}
```| HTTP 状态码 | `error.code`                                                                                  | 处理方式                                                   |
| -------- | --------------------------------------------------------------------------------------------- | ------------------------------------------------------ |
| 400      | `bad_request`, `content_policy_violation`                                                     | 修改请求；message 会点名出错的字段。不要原样重试。                          |
| 401      | `missing_api_key`, `invalid_api_key`（旧版客户端可能看到 `unauthorized`）                                | 以 `Authorization: Bearer <key>` 发送有效的密钥。               |
| 402      | `insufficient_credits`                                                                        | 充值，或提高密钥的额度，然后重新发送。                                    |
| 403      | `forbidden`                                                                                   | 该密钥或账户不能使用此模型（例如免费额度只覆盖部分模型）。不要原样重试。                   |
| 404      | `not_found`                                                                                   | 在 `GET /v1/tasks/{task_id}` 上：该任务在此密钥所属账户下不存在。请检查 ID。  |
| 409      | `idempotency_conflict`                                                                        | 换一个新的 `Idempotency-Key`，或等待使用该键的第一个请求完成。               |
| 429      | `rate_limit_exceeded`                                                                         | 等待 `Retry-After` 秒（也见 `error.retry_after_seconds`）后重试。 |
| 500      | `internal_error`                                                                              | 退避重试；若持续出现，请带上 `request_id` 联系支持。                      |
| 503      | `processing_unavailable`, `processing_timeout`, `processing_failed`, `result_transfer_failed` | 未扣费。使用指数退避重试。                                          |

Reference: https://docs.beatapi.io/api-reference/image-api/gpt-image-2-std

## Authentication

- `Authorization` header (bearer token, required) — 通过 `Authorization: Bearer <BEATAPI_API_KEY>` 发送 API 密钥。

## Servers

- `https://api.beatapi.io` (Direct, default)
- `https://api.beatapi.io` (API)

## Request

### Headers

- `Idempotency-Key` (string, optional) — 请求体使用 JSON，并设置 `Content-Type: application/json`。`Idempotency-Key` 为可选：每个逻辑请求发送一个唯一值（最长 255 个字符），仅在重试完全相同的请求体时复用。24 小时内，用相同的键和请求体重试会再次返回第一次的响应，并带上 `Idempotent-Replayed: true`；相同的键搭配不同的请求体则返回 `409 idempotency_conflict`。非 2xx 的响应不会被保存，因此 400 或 402 之后的重试会重新执行。

### Body (application/json)

This endpoint expects a GptImage2StdRequest.

- `model` (enum, required) — 要运行的模型。 **取值**：`gpt-image-2-std` **取值有误时** - 缺失：`"model" is required` - 未知的模型 ID：`"model" gpt-image-9 is not catalogued` - 把视频模型发到了这个接口：`"model" seedance-2.5 is served by POST /v1/videos/tasks, not this endpoint`
  - Allowed values: `gpt-image-2-std`
- `prompt` (string, required) — 要画什么，或要修改参考图中的什么。用平实的语言效果最好：主体、风格、光线、构图，以及必须出现在图片中的文字。 **长度**：1–5000 个字符 - 长度按字符计算（一个中日韩文字算一个字符）。 - 传了 `images` 时，请说明每张图的作用，例如 "Use the first image for the product and the second for the background"。 **取值有误时** - 缺失：`"prompt" is required` - 为空或超过长度上限：`"prompt" has an unsupported length` - 不是字符串：`"prompt" must be a string`
- `aspect_ratio` (enum, optional, default: auto) — 图片的形状，以 宽:高 表示。与 `resolution` 一起传，或两者都不传而改传 `size`。 **可选值**：`auto`, `1:1`, `3:2`, `2:3`, `4:3`, `3:4`, `5:4`, `4:5`, `16:9`, `9:16`, `2:1`, `1:2`, `3:1`, `1:3`, `21:9`, `9:21` **默认值**：`auto` - 默认值是 `auto`，所以省略该字段的请求同样会生成正方形。 - 支持 `2:1`、`1:2`、`3:1`、`1:3`、`21:9` 和 `9:21` 等全景比例。最宽或最高的画幅是 3:1。 - 不能与 `size` 同时使用。 **说明**：`auto` 不是“沿用参考图的形状”。无论是否传了 `images`，它都会在所选 `resolution` 下生成正方形画幅。要把编辑结果改成其他形状，请指定比例，或传 `size`。 **取值有误时** - 取值不在列表中：`"aspect_ratio" must be one of: [auto 1:1 3:2 2:3 4:3 3:4 5:4 4:5 16:9 9:16 2:1 1:2 3:1 1:3 21:9 9:21]` - 与 `size` 一起传：`"size" already fixes the output; do not send "aspect_ratio" with it`
  - Allowed values: `auto`, `1:1`, `3:2`, `2:3`, `4:3`, `3:4`, `5:4`, `4:5`, `16:9`, `9:16`, `2:1`, `1:2`, `3:1`, `1:3`, `21:9`, `9:21`
- `background` (enum, optional, default: auto) — 图片是有填充背景，还是透明背景。 **可选值**：`auto`, `opaque`, `transparent` **默认值**：`auto` - `auto`（默认值）由模型自行选择。`opaque` 要求填充背景。 - `transparent` 要求背景无颜色的图片。结果是带 alpha 通道的 PNG；请查看 `output.media[].mime_type`。 **取值有误时** - 取值不在列表中：`"background" must be one of: [auto opaque transparent]`
  - Allowed values: `auto`, `opaque`, `transparent`
- `images` (list of string, optional) — 要编辑或合成的参考图。传入该字段会把请求从文生图切换为图片编辑。 **数量**：1–16 每一项都必须是公网 `https://` 链接。本地文件请先[上传](/quick-guide#upload-an-input-file)（`POST /v1/files`），再传入返回的 `data.url`。 - 每个链接必须通过公网 HTTPS 直接返回图片文件本身（PNG、JPEG 或 WebP），且不超过 50 MB。网关在创建任务之前会下载每个链接开头的若干字节，并根据这些字节识别类型，而不是根据文件名或 `Content-Type`。 - 指向网页、登录页、已过期的签名链接或有防盗链的主机的链接会被拒绝，因为它们返回的不是图片。 - 错误信息中的位置从 0 开始：`images[0]` 是第一个链接。 **取值有误时** - 超过数量上限：`"images" accepts at most 16 items` - 空数组：`"images" requires at least 1 item` - 不是 https:// 链接：`"images[0]" must be a public HTTPS URL` - 私有或不安全的地址：`"images[0]" must be a publicly reachable HTTPS image URL` - 主机返回 4xx 错误：`"images[0]" could not be downloaded: the URL returned HTTP 404` - 链接返回的不是 PNG、JPEG 或 WebP：`"images[0]" is not a PNG, JPEG or WebP image: the URL returned text/html` - 大于 50 MB：`"images[2]" is 63.4 MB; images must be 50 MB or smaller` **示例** ```json "images": [ "https://cdn.beatapi.io/samples/smart-bottle.png", "https://cdn.beatapi.io/samples/neon-singer.png" ] ```
- `quality` (enum, optional, default: medium) — 模型在这张图片上投入多少功夫。它决定一次生成用掉多少输出 token，也就决定价格：取值越低越便宜，越高越贵。 **可选值**：`low`, `medium`, `high` **默认值**：`medium` - 不传时为 `medium`，本页的每张价格就是按这个质量估算的。 - 固定价的 [`gpt-image-2`](/image-api/gpt-image-2) 不接受这个字段，传入会被拒绝。 **取值有误时** - 取值不在列表中：`"quality" must be one of: [low medium high]` **示例** ```json "quality": "low" ```
  - Allowed values: `low`, `medium`, `high`
- `resolution` (enum, optional, default: 1K) — 图片的尺寸档位。档位越高，图片越大、价格越高；具体像素尺寸取决于 `aspect_ratio`，由模型决定。 **可选值**：`1K`, `2K`, `4K` **默认值**：`1K` - K 必须大写：`2k` 会被拒绝。 - 本页不承诺某个档位对应的精确像素尺寸。如果需要精确画幅，请传 `size`。 - 不能与 `size` 同时使用；`size` 自带尺寸。 **取值有误时** - 取值不在列表中：`"resolution" must be one of: [1K 2K 4K]` - 与 `size` 一起传：`"size" already fixes the output; do not send "resolution" with it`
  - Allowed values: `1K`, `2K`, `4K`
- `size` (string, optional) — 以像素表示的精确输出画幅，格式为 `WIDTHxHEIGHT`，例如 `1536x1024`。它会取代 `resolution` 和 `aspect_ratio`。 - 两条边都必须是 16 的倍数，且在 16 到 3840 px 之间。 - 像素总数必须在 655,360 到 8,294,400 之间，长边最多是短边的三倍。 - 分隔符可以是 `x`、`X` 或 `×`；两侧的空格会被忽略。 - 像素总数会改变输出 token 数，也就改变价格。任务结算前，预扣的是像素总数所属档位的估算价：不超过 2,097,152 像素为 1K，不超过 5,898,240 为 2K，超过则为 4K。 - 不要同时传 `resolution` 或 `aspect_ratio`，即使是默认值也不行。 **说明**：`size` 按所传的值校验，但本页不保证交付的图片恰好是这些像素。如果你的流程依赖精确尺寸，请读取已保存的文件。 **取值有误时** - 不是字符串：`"size" must be a string` - 不是 WIDTHxHEIGHT 形式（单独一个数字、`auto`、逗号）：`"size" must be WIDTHxHEIGHT in pixels, for example 1536x1024` - 某条边不是 16 的倍数：`"size" width and height must be multiples of 16` - 某条边小于 16 或大于 3840：`"size" edges must be between 16 and 3840 pixels` - 像素太少或太多：`"size" must have between 655,360 and 8,294,400 pixels; 512x512 has 262,144` - 宽或高超过 3:1：`"size" must not be wider or taller than 3:1` - 与 `resolution` 一起传：`"size" already fixes the output; do not send "resolution" with it` - 与 `aspect_ratio` 一起传：`"size" already fixes the output; do not send "aspect_ratio" with it` **示例** ```json "size": "1536x1024" ```

## Response

### 201

任务对象。任务成功之前 `output` 为 `null`。标注“运行中”的字段会在任务结束后消失。

- `map from string to any`

## Errors

### 400 Bad Request Error

`bad_request`, `content_policy_violation` 修改请求；message 会点名出错的字段。不要原样重试。

- `map from string to any`

### 401 Unauthorized Error

`missing_api_key`, `invalid_api_key`（旧版客户端可能看到 `unauthorized`） 以 `Authorization: Bearer <key>` 发送有效的密钥。

- `map from string to any`

### 402 Payment Required Error

`insufficient_credits` 充值，或提高密钥的额度，然后重新发送。

- `map from string to any`

### 403 Forbidden Error

`forbidden` 该密钥或账户不能使用此模型（例如免费额度只覆盖部分模型）。不要原样重试。

- `map from string to any`

### 409 Conflict Error

`idempotency_conflict` 换一个新的 `Idempotency-Key`，或等待使用该键的第一个请求完成。

- `map from string to any`

### 429 Too Many Requests Error

`rate_limit_exceeded` 等待 `Retry-After` 秒（也见 `error.retry_after_seconds`）后重试。

- `map from string to any`

### 500 Internal Server Error

`internal_error` 退避重试；若持续出现，请带上 `request_id` 联系支持。

- `map from string to any`

### 503 Service Unavailable Error

`processing_unavailable`, `processing_timeout`, `processing_failed`, `result_transfer_failed` 未扣费。使用指数退避重试。

- `map from string to any`

## Examples

### 文生图

**Request**

```json
{
  "model": "gpt-image-2-std",
  "prompt": "A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field",
  "aspect_ratio": "3:2",
  "quality": "medium",
  "resolution": "2K"
}
```

**Response**

```json
{
  "data": {
    "capability_id": "gpt-image-2-std",
    "capability_version": 1,
    "completed_at": null,
    "created_at": 1791993600,
    "error_code": null,
    "error_message": null,
    "id": "task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ",
    "media_type": "image",
    "model": "gpt-image-2-std",
    "object": "task",
    "output": null,
    "poll_after_seconds": 5,
    "request_id": "req_5f0c2a9e4b7d4e31",
    "stage": "queued",
    "status": "queued",
    "task_kind": "image",
    "updated_at": 1791993600,
    "usage": {
      "credits_charged": 0.069576,
      "credits_refunded": 0,
      "credits_reserved": 0.069576,
      "credits_settled": 0
    }
  }
}
```

**SDK Code**

```python 文生图
import requests

url = "https://api.beatapi.io/v1/images/tasks"

payload = {
    "model": "gpt-image-2-std",
    "prompt": "A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field",
    "aspect_ratio": "3:2",
    "quality": "medium",
    "resolution": "2K"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.json())
```

```javascript 文生图
const url = 'https://api.beatapi.io/v1/images/tasks';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: '{"model":"gpt-image-2-std","prompt":"A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field","aspect_ratio":"3:2","quality":"medium","resolution":"2K"}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go 文生图
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.beatapi.io/v1/images/tasks"

	payload := strings.NewReader("{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field\",\n  \"aspect_ratio\": \"3:2\",\n  \"quality\": \"medium\",\n  \"resolution\": \"2K\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby 文生图
require 'uri'
require 'net/http'

url = URI("https://api.beatapi.io/v1/images/tasks")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field\",\n  \"aspect_ratio\": \"3:2\",\n  \"quality\": \"medium\",\n  \"resolution\": \"2K\"\n}"

response = http.request(request)
puts response.read_body
```

```java 文生图
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.beatapi.io/v1/images/tasks")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field\",\n  \"aspect_ratio\": \"3:2\",\n  \"quality\": \"medium\",\n  \"resolution\": \"2K\"\n}")
  .asString();
```

```php 文生图
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.beatapi.io/v1/images/tasks', [
  'body' => '{
  "model": "gpt-image-2-std",
  "prompt": "A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field",
  "aspect_ratio": "3:2",
  "quality": "medium",
  "resolution": "2K"
}',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp 文生图
using RestSharp;

var client = new RestClient("https://api.beatapi.io/v1/images/tasks");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field\",\n  \"aspect_ratio\": \"3:2\",\n  \"quality\": \"medium\",\n  \"resolution\": \"2K\"\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift 文生图
import Foundation

let headers = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
let parameters = [
  "model": "gpt-image-2-std",
  "prompt": "A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field",
  "aspect_ratio": "3:2",
  "quality": "medium",
  "resolution": "2K"
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.beatapi.io/v1/images/tasks")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```

### 低质量草稿

**Request**

```json
{
  "model": "gpt-image-2-std",
  "prompt": "A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field",
  "aspect_ratio": "3:2",
  "quality": "low",
  "resolution": "1K"
}
```

**Response**

```json
{
  "data": {
    "capability_id": "gpt-image-2-std",
    "capability_version": 1,
    "completed_at": null,
    "created_at": 1791993600,
    "error_code": null,
    "error_message": null,
    "id": "task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ",
    "media_type": "image",
    "model": "gpt-image-2-std",
    "object": "task",
    "output": null,
    "poll_after_seconds": 5,
    "request_id": "req_5f0c2a9e4b7d4e31",
    "stage": "queued",
    "status": "queued",
    "task_kind": "image",
    "updated_at": 1791993600
  }
}
```

**SDK Code**

```python 低质量草稿
import requests

url = "https://api.beatapi.io/v1/images/tasks"

payload = {
    "model": "gpt-image-2-std",
    "prompt": "A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field",
    "aspect_ratio": "3:2",
    "quality": "low",
    "resolution": "1K"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.json())
```

```javascript 低质量草稿
const url = 'https://api.beatapi.io/v1/images/tasks';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: '{"model":"gpt-image-2-std","prompt":"A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field","aspect_ratio":"3:2","quality":"low","resolution":"1K"}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go 低质量草稿
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.beatapi.io/v1/images/tasks"

	payload := strings.NewReader("{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field\",\n  \"aspect_ratio\": \"3:2\",\n  \"quality\": \"low\",\n  \"resolution\": \"1K\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby 低质量草稿
require 'uri'
require 'net/http'

url = URI("https://api.beatapi.io/v1/images/tasks")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field\",\n  \"aspect_ratio\": \"3:2\",\n  \"quality\": \"low\",\n  \"resolution\": \"1K\"\n}"

response = http.request(request)
puts response.read_body
```

```java 低质量草稿
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.beatapi.io/v1/images/tasks")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field\",\n  \"aspect_ratio\": \"3:2\",\n  \"quality\": \"low\",\n  \"resolution\": \"1K\"\n}")
  .asString();
```

```php 低质量草稿
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.beatapi.io/v1/images/tasks', [
  'body' => '{
  "model": "gpt-image-2-std",
  "prompt": "A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field",
  "aspect_ratio": "3:2",
  "quality": "low",
  "resolution": "1K"
}',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp 低质量草稿
using RestSharp;

var client = new RestClient("https://api.beatapi.io/v1/images/tasks");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field\",\n  \"aspect_ratio\": \"3:2\",\n  \"quality\": \"low\",\n  \"resolution\": \"1K\"\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift 低质量草稿
import Foundation

let headers = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
let parameters = [
  "model": "gpt-image-2-std",
  "prompt": "A minimalist product photo of a glass water bottle on wet black stone, soft rim light, shallow depth of field",
  "aspect_ratio": "3:2",
  "quality": "low",
  "resolution": "1K"
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.beatapi.io/v1/images/tasks")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```

### 编辑一张图片

**Request**

```json
{
  "model": "gpt-image-2-std",
  "prompt": "Keep the bottle exactly as it is. Replace the background with a sunlit kitchen counter and add a soft reflection under the bottle.",
  "aspect_ratio": "1:1",
  "images": [
    "https://cdn.beatapi.io/samples/smart-bottle.png"
  ],
  "resolution": "1K"
}
```

**Response**

```json
{
  "data": {
    "capability_id": "gpt-image-2-std",
    "capability_version": 1,
    "completed_at": null,
    "created_at": 1791993600,
    "error_code": null,
    "error_message": null,
    "id": "task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ",
    "media_type": "image",
    "model": "gpt-image-2-std",
    "object": "task",
    "output": null,
    "poll_after_seconds": 5,
    "request_id": "req_5f0c2a9e4b7d4e31",
    "stage": "queued",
    "status": "queued",
    "task_kind": "image",
    "updated_at": 1791993600
  }
}
```

**SDK Code**

```python 编辑一张图片
import requests

url = "https://api.beatapi.io/v1/images/tasks"

payload = {
    "model": "gpt-image-2-std",
    "prompt": "Keep the bottle exactly as it is. Replace the background with a sunlit kitchen counter and add a soft reflection under the bottle.",
    "aspect_ratio": "1:1",
    "images": ["https://cdn.beatapi.io/samples/smart-bottle.png"],
    "resolution": "1K"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.json())
```

```javascript 编辑一张图片
const url = 'https://api.beatapi.io/v1/images/tasks';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: '{"model":"gpt-image-2-std","prompt":"Keep the bottle exactly as it is. Replace the background with a sunlit kitchen counter and add a soft reflection under the bottle.","aspect_ratio":"1:1","images":["https://cdn.beatapi.io/samples/smart-bottle.png"],"resolution":"1K"}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go 编辑一张图片
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.beatapi.io/v1/images/tasks"

	payload := strings.NewReader("{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"Keep the bottle exactly as it is. Replace the background with a sunlit kitchen counter and add a soft reflection under the bottle.\",\n  \"aspect_ratio\": \"1:1\",\n  \"images\": [\n    \"https://cdn.beatapi.io/samples/smart-bottle.png\"\n  ],\n  \"resolution\": \"1K\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby 编辑一张图片
require 'uri'
require 'net/http'

url = URI("https://api.beatapi.io/v1/images/tasks")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"Keep the bottle exactly as it is. Replace the background with a sunlit kitchen counter and add a soft reflection under the bottle.\",\n  \"aspect_ratio\": \"1:1\",\n  \"images\": [\n    \"https://cdn.beatapi.io/samples/smart-bottle.png\"\n  ],\n  \"resolution\": \"1K\"\n}"

response = http.request(request)
puts response.read_body
```

```java 编辑一张图片
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.beatapi.io/v1/images/tasks")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"Keep the bottle exactly as it is. Replace the background with a sunlit kitchen counter and add a soft reflection under the bottle.\",\n  \"aspect_ratio\": \"1:1\",\n  \"images\": [\n    \"https://cdn.beatapi.io/samples/smart-bottle.png\"\n  ],\n  \"resolution\": \"1K\"\n}")
  .asString();
```

```php 编辑一张图片
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.beatapi.io/v1/images/tasks', [
  'body' => '{
  "model": "gpt-image-2-std",
  "prompt": "Keep the bottle exactly as it is. Replace the background with a sunlit kitchen counter and add a soft reflection under the bottle.",
  "aspect_ratio": "1:1",
  "images": [
    "https://cdn.beatapi.io/samples/smart-bottle.png"
  ],
  "resolution": "1K"
}',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp 编辑一张图片
using RestSharp;

var client = new RestClient("https://api.beatapi.io/v1/images/tasks");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"Keep the bottle exactly as it is. Replace the background with a sunlit kitchen counter and add a soft reflection under the bottle.\",\n  \"aspect_ratio\": \"1:1\",\n  \"images\": [\n    \"https://cdn.beatapi.io/samples/smart-bottle.png\"\n  ],\n  \"resolution\": \"1K\"\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift 编辑一张图片
import Foundation

let headers = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
let parameters = [
  "model": "gpt-image-2-std",
  "prompt": "Keep the bottle exactly as it is. Replace the background with a sunlit kitchen counter and add a soft reflection under the bottle.",
  "aspect_ratio": "1:1",
  "images": ["https://cdn.beatapi.io/samples/smart-bottle.png"],
  "resolution": "1K"
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.beatapi.io/v1/images/tasks")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```

### 合成多张图片

**Request**

```json
{
  "model": "gpt-image-2-std",
  "prompt": "Place the bottle from the first image on a neon-lit stage like the one in the second image. Keep the bottle label readable.",
  "aspect_ratio": "16:9",
  "images": [
    "https://cdn.beatapi.io/samples/smart-bottle.png",
    "https://cdn.beatapi.io/samples/neon-singer.png"
  ],
  "resolution": "2K"
}
```

**Response**

```json
{
  "data": {
    "capability_id": "gpt-image-2-std",
    "capability_version": 1,
    "completed_at": null,
    "created_at": 1791993600,
    "error_code": null,
    "error_message": null,
    "id": "task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ",
    "media_type": "image",
    "model": "gpt-image-2-std",
    "object": "task",
    "output": null,
    "poll_after_seconds": 5,
    "request_id": "req_5f0c2a9e4b7d4e31",
    "stage": "queued",
    "status": "queued",
    "task_kind": "image",
    "updated_at": 1791993600
  }
}
```

**SDK Code**

```python 合成多张图片
import requests

url = "https://api.beatapi.io/v1/images/tasks"

payload = {
    "model": "gpt-image-2-std",
    "prompt": "Place the bottle from the first image on a neon-lit stage like the one in the second image. Keep the bottle label readable.",
    "aspect_ratio": "16:9",
    "images": ["https://cdn.beatapi.io/samples/smart-bottle.png", "https://cdn.beatapi.io/samples/neon-singer.png"],
    "resolution": "2K"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.json())
```

```javascript 合成多张图片
const url = 'https://api.beatapi.io/v1/images/tasks';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: '{"model":"gpt-image-2-std","prompt":"Place the bottle from the first image on a neon-lit stage like the one in the second image. Keep the bottle label readable.","aspect_ratio":"16:9","images":["https://cdn.beatapi.io/samples/smart-bottle.png","https://cdn.beatapi.io/samples/neon-singer.png"],"resolution":"2K"}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go 合成多张图片
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.beatapi.io/v1/images/tasks"

	payload := strings.NewReader("{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"Place the bottle from the first image on a neon-lit stage like the one in the second image. Keep the bottle label readable.\",\n  \"aspect_ratio\": \"16:9\",\n  \"images\": [\n    \"https://cdn.beatapi.io/samples/smart-bottle.png\",\n    \"https://cdn.beatapi.io/samples/neon-singer.png\"\n  ],\n  \"resolution\": \"2K\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby 合成多张图片
require 'uri'
require 'net/http'

url = URI("https://api.beatapi.io/v1/images/tasks")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"Place the bottle from the first image on a neon-lit stage like the one in the second image. Keep the bottle label readable.\",\n  \"aspect_ratio\": \"16:9\",\n  \"images\": [\n    \"https://cdn.beatapi.io/samples/smart-bottle.png\",\n    \"https://cdn.beatapi.io/samples/neon-singer.png\"\n  ],\n  \"resolution\": \"2K\"\n}"

response = http.request(request)
puts response.read_body
```

```java 合成多张图片
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.beatapi.io/v1/images/tasks")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"Place the bottle from the first image on a neon-lit stage like the one in the second image. Keep the bottle label readable.\",\n  \"aspect_ratio\": \"16:9\",\n  \"images\": [\n    \"https://cdn.beatapi.io/samples/smart-bottle.png\",\n    \"https://cdn.beatapi.io/samples/neon-singer.png\"\n  ],\n  \"resolution\": \"2K\"\n}")
  .asString();
```

```php 合成多张图片
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.beatapi.io/v1/images/tasks', [
  'body' => '{
  "model": "gpt-image-2-std",
  "prompt": "Place the bottle from the first image on a neon-lit stage like the one in the second image. Keep the bottle label readable.",
  "aspect_ratio": "16:9",
  "images": [
    "https://cdn.beatapi.io/samples/smart-bottle.png",
    "https://cdn.beatapi.io/samples/neon-singer.png"
  ],
  "resolution": "2K"
}',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp 合成多张图片
using RestSharp;

var client = new RestClient("https://api.beatapi.io/v1/images/tasks");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"Place the bottle from the first image on a neon-lit stage like the one in the second image. Keep the bottle label readable.\",\n  \"aspect_ratio\": \"16:9\",\n  \"images\": [\n    \"https://cdn.beatapi.io/samples/smart-bottle.png\",\n    \"https://cdn.beatapi.io/samples/neon-singer.png\"\n  ],\n  \"resolution\": \"2K\"\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift 合成多张图片
import Foundation

let headers = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
let parameters = [
  "model": "gpt-image-2-std",
  "prompt": "Place the bottle from the first image on a neon-lit stage like the one in the second image. Keep the bottle label readable.",
  "aspect_ratio": "16:9",
  "images": ["https://cdn.beatapi.io/samples/smart-bottle.png", "https://cdn.beatapi.io/samples/neon-singer.png"],
  "resolution": "2K"
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.beatapi.io/v1/images/tasks")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```

### 精确尺寸

**Request**

```json
{
  "model": "gpt-image-2-std",
  "prompt": "A flat illustration of a lighthouse on a cliff at dawn, pastel colours, clean shapes",
  "size": "1536x1024"
}
```

**Response**

```json
{
  "data": {
    "capability_id": "gpt-image-2-std",
    "capability_version": 1,
    "completed_at": null,
    "created_at": 1791993600,
    "error_code": null,
    "error_message": null,
    "id": "task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ",
    "media_type": "image",
    "model": "gpt-image-2-std",
    "object": "task",
    "output": null,
    "poll_after_seconds": 5,
    "request_id": "req_5f0c2a9e4b7d4e31",
    "stage": "queued",
    "status": "queued",
    "task_kind": "image",
    "updated_at": 1791993600
  }
}
```

**SDK Code**

```python 精确尺寸
import requests

url = "https://api.beatapi.io/v1/images/tasks"

payload = {
    "model": "gpt-image-2-std",
    "prompt": "A flat illustration of a lighthouse on a cliff at dawn, pastel colours, clean shapes",
    "size": "1536x1024"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.json())
```

```javascript 精确尺寸
const url = 'https://api.beatapi.io/v1/images/tasks';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: '{"model":"gpt-image-2-std","prompt":"A flat illustration of a lighthouse on a cliff at dawn, pastel colours, clean shapes","size":"1536x1024"}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go 精确尺寸
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.beatapi.io/v1/images/tasks"

	payload := strings.NewReader("{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"A flat illustration of a lighthouse on a cliff at dawn, pastel colours, clean shapes\",\n  \"size\": \"1536x1024\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby 精确尺寸
require 'uri'
require 'net/http'

url = URI("https://api.beatapi.io/v1/images/tasks")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"A flat illustration of a lighthouse on a cliff at dawn, pastel colours, clean shapes\",\n  \"size\": \"1536x1024\"\n}"

response = http.request(request)
puts response.read_body
```

```java 精确尺寸
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.beatapi.io/v1/images/tasks")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"A flat illustration of a lighthouse on a cliff at dawn, pastel colours, clean shapes\",\n  \"size\": \"1536x1024\"\n}")
  .asString();
```

```php 精确尺寸
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.beatapi.io/v1/images/tasks', [
  'body' => '{
  "model": "gpt-image-2-std",
  "prompt": "A flat illustration of a lighthouse on a cliff at dawn, pastel colours, clean shapes",
  "size": "1536x1024"
}',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp 精确尺寸
using RestSharp;

var client = new RestClient("https://api.beatapi.io/v1/images/tasks");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"A flat illustration of a lighthouse on a cliff at dawn, pastel colours, clean shapes\",\n  \"size\": \"1536x1024\"\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift 精确尺寸
import Foundation

let headers = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
let parameters = [
  "model": "gpt-image-2-std",
  "prompt": "A flat illustration of a lighthouse on a cliff at dawn, pastel colours, clean shapes",
  "size": "1536x1024"
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.beatapi.io/v1/images/tasks")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```

### 透明背景

**Request**

```json
{
  "model": "gpt-image-2-std",
  "prompt": "A single cartoon red fox sitting, sticker style, thick white outline, isolated on a transparent background",
  "aspect_ratio": "1:1",
  "background": "transparent",
  "resolution": "1K"
}
```

**Response**

```json
{
  "data": {
    "capability_id": "gpt-image-2-std",
    "capability_version": 1,
    "completed_at": null,
    "created_at": 1791993600,
    "error_code": null,
    "error_message": null,
    "id": "task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ",
    "media_type": "image",
    "model": "gpt-image-2-std",
    "object": "task",
    "output": null,
    "poll_after_seconds": 5,
    "request_id": "req_5f0c2a9e4b7d4e31",
    "stage": "queued",
    "status": "queued",
    "task_kind": "image",
    "updated_at": 1791993600
  }
}
```

**SDK Code**

```python 透明背景
import requests

url = "https://api.beatapi.io/v1/images/tasks"

payload = {
    "model": "gpt-image-2-std",
    "prompt": "A single cartoon red fox sitting, sticker style, thick white outline, isolated on a transparent background",
    "aspect_ratio": "1:1",
    "background": "transparent",
    "resolution": "1K"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.json())
```

```javascript 透明背景
const url = 'https://api.beatapi.io/v1/images/tasks';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: '{"model":"gpt-image-2-std","prompt":"A single cartoon red fox sitting, sticker style, thick white outline, isolated on a transparent background","aspect_ratio":"1:1","background":"transparent","resolution":"1K"}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go 透明背景
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.beatapi.io/v1/images/tasks"

	payload := strings.NewReader("{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"A single cartoon red fox sitting, sticker style, thick white outline, isolated on a transparent background\",\n  \"aspect_ratio\": \"1:1\",\n  \"background\": \"transparent\",\n  \"resolution\": \"1K\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby 透明背景
require 'uri'
require 'net/http'

url = URI("https://api.beatapi.io/v1/images/tasks")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"A single cartoon red fox sitting, sticker style, thick white outline, isolated on a transparent background\",\n  \"aspect_ratio\": \"1:1\",\n  \"background\": \"transparent\",\n  \"resolution\": \"1K\"\n}"

response = http.request(request)
puts response.read_body
```

```java 透明背景
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.beatapi.io/v1/images/tasks")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"A single cartoon red fox sitting, sticker style, thick white outline, isolated on a transparent background\",\n  \"aspect_ratio\": \"1:1\",\n  \"background\": \"transparent\",\n  \"resolution\": \"1K\"\n}")
  .asString();
```

```php 透明背景
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.beatapi.io/v1/images/tasks', [
  'body' => '{
  "model": "gpt-image-2-std",
  "prompt": "A single cartoon red fox sitting, sticker style, thick white outline, isolated on a transparent background",
  "aspect_ratio": "1:1",
  "background": "transparent",
  "resolution": "1K"
}',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp 透明背景
using RestSharp;

var client = new RestClient("https://api.beatapi.io/v1/images/tasks");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"model\": \"gpt-image-2-std\",\n  \"prompt\": \"A single cartoon red fox sitting, sticker style, thick white outline, isolated on a transparent background\",\n  \"aspect_ratio\": \"1:1\",\n  \"background\": \"transparent\",\n  \"resolution\": \"1K\"\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift 透明背景
import Foundation

let headers = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
let parameters = [
  "model": "gpt-image-2-std",
  "prompt": "A single cartoon red fox sitting, sticker style, thick white outline, isolated on a transparent background",
  "aspect_ratio": "1:1",
  "background": "transparent",
  "resolution": "1K"
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.beatapi.io/v1/images/tasks")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```