模型市场支持← 返回应用

GPT Image

GPT Image 模型通过一个统一的异步任务 API 调用。用 POST /api/generate 发起任务，再轮询 GET /api/generate/{taskId} 直到完成。本系列提供 4 个端点。

概览

每个端点共享相同的外层结构 —— 只有 model 和 input 字段不同。可在模型市场的 playground 中运行任意一个。

认证

在 /api-keys 创建 API 密钥，然后作为 Bearer token 发送。已登录时从浏览器发起的请求也可通过会话 cookie 生效。

Authorization: Bearer <YOUR_API_KEY>

创建任务

POST
POST https://api.lithovas.com/api/generate

请求体：{ "model": "<slug>", "input": { … } }

响应：{ "taskId": "<id>", "state": "waiting" }

查询结果

GET
GET https://api.lithovas.com/api/generate/<taskId>

响应：{ "taskId", "state": "waiting" | "success" | "fail", "resultUrls": [ … ], "creditsConsumed", "failMsg", "balance" }

异步
创建任务返回 200 只表示任务已被接受 —— 并非已完成。请轮询此端点，直到 state 变为 success 或 fail。失败任务不计费。

端点

模型任务model slug
GPT Image 1.5Text to Imagegpt-image/1-5-text-to-image
GPT Image 1.5Image to Imagegpt-image/1-5-image-to-image
GPT Image 2Text to Imagegpt/gpt-image-2-text-to-image
GPT Image 2Image to Imagegpt/gpt-image-2-image-to-image

GPT Image 1.5 · Text to Image

POSTText to Imagegpt-image/1-5-text-to-image
input 字段
promptstring必填

Text description of the image to generate

aspect_ratioenum<string>必填

Width-height ratio determining visual form

qualityenum<string>必填

Medium for balanced output; high for detailed

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-image/1-5-text-to-image",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "aspect_ratio": "1:1",
    "quality": "medium"
  }
}'

GPT Image 1.5 · Image to Image

POSTImage to Imagegpt-image/1-5-image-to-image
input 字段
input_urlsarray<string>必填

Input image file URLs (max 16 URLs)

promptstring必填

Text description of desired image generation or edit

aspect_ratioenum<string>必填

Width-height ratio of the image

qualityenum<string>必填

Quality: medium for balanced, high for detailed

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-image/1-5-image-to-image",
  "input": {
    "input_urls": [
      "https://example.com/file"
    ],
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "aspect_ratio": "3:2",
    "quality": "medium"
  }
}'

GPT Image 2 · Text to Image

POSTText to Imagegpt/gpt-image-2-text-to-image
input 字段
promptstring必填

Text prompt for image generation (max 20000 chars)

aspect_ratioenum<string>可选

Image aspect ratio (some ratios unavailable for 2K/4K)

resolutionenum<string>可选

Output image resolution

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt/gpt-image-2-text-to-image",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "aspect_ratio": "auto",
    "resolution": "1K"
  }
}'

GPT Image 2 · Image to Image

POSTImage to Imagegpt/gpt-image-2-image-to-image
input 字段
promptstring必填

Text prompt for image generation, up to 20000 characters

input_urlsarray<string>必填

Array of input image URLs (max 16 images)

aspect_ratioenum<string>可选

Output aspect ratio (5:4 and 4:5 limited to 1K)

resolutionenum<string>可选

Image resolution (1:1 cannot use 4K; auto limited to 1K)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt/gpt-image-2-image-to-image",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "input_urls": [
      "https://example.com/file"
    ],
    "aspect_ratio": "auto",
    "resolution": "1K"
  }
}'