GPT Image Hub API 文件

除模型列表外，所有 v1 端點都需要在 Authorization 請求標頭中攜帶 API 金鑰。原始金鑰只會在建立時顯示一次；伺服器只保存雜湊值。

Authorization: Bearer gih_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

模型端點會傳回模型 ID、服務商、支援的畫幅比例、支援的畫質、參考圖限制和每張圖的點數消耗。

curl https://www.gptimagehub.com/api/v1/models

curl https://www.gptimagehub.com/api/v1/images/generations \
  -H "Authorization: Bearer gih_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-image-turbo",
    "prompt": "A cinematic product photo with premium studio lighting",
    "size": "1024x1024",
    "quality": "high",
    "n": 1
  }'

點數端點會傳回該 API 金鑰所屬使用者的餘額、帳戶類型和即將到期的點數資訊。

curl https://www.gptimagehub.com/api/v1/credits \
  -H "Authorization: Bearer gih_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"

圖像生成端點預設會等待生成完成。將 async 設為 true 即可立即取得 generation id，並透過 /api/v1/generations/:generationId 輪詢結果。生成前會扣除點數；如果服務商生成失敗或傳回的圖片少於請求數量，會自動退還相應點數。

JSON 請求

curl https://www.gptimagehub.com/api/v1/images/generations \
  -H "Authorization: Bearer gih_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A cinematic product photo of a transparent perfume bottle on black marble",
    "size": "1024x1024",
    "quality": "high",
    "n": 1
  }'

非同步任務

curl https://www.gptimagehub.com/api/v1/images/generations \
  -H "Authorization: Bearer gih_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: order-1042-hero-image" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A cinematic product photo with premium studio lighting",
    "size": "1024x1024",
    "quality": "high",
    "n": 1,
    "async": true
  }'

{
  "object": "image_generation",
  "id": "clx_generation_log_id",
  "status": "queued",
  "model": "gpt-image-2",
  "aspect_ratio": "1:1",
  "quality": "1K",
  "created_at": "2026-04-30T08:00:00.000Z",
  "images": [],
  "usage": {
    "credits": 0,
    "credits_requested": 7
  },
  "poll_url": "https://www.gptimagehub.com/api/v1/generations/clx_generation_log_id"
}

參考圖請求

curl https://www.gptimagehub.com/api/v1/images/generations \
  -H "Authorization: Bearer gih_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
  -F "model=gpt-image-2" \
  -F "prompt=Use the reference image and render it as a premium studio product shot" \
  -F "size=1024x1024" \
  -F "quality=high" \
  -F "n=1" \
  -F "reference_image=@./reference.png"

回應

{
  "object": "image_generation",
  "id": "clx_generation_log_id",
  "status": "succeeded",
  "model": "gpt-image-2",
  "aspect_ratio": "1:1",
  "quality": "1K",
  "images": [
    {
      "id": "clx_image_id",
      "object": "image",
      "url": "https://cdn.example.com/generations/user/image.png",
      "created_at": "2026-04-30T08:00:00.000Z"
    }
  ],
  "usage": {
    "credits": 7
  },
  "balance": {
    "credits": 113,
    "account_type": "PRO",
    "next_expiration": null
  }
}

使用生成端點傳回的 ID 查詢保存的生成日誌和圖片 URL。API 金鑰只能讀取同一使用者名下的生成記錄。

curl https://www.gptimagehub.com/api/v1/generations/clx_generation_log_id \
  -H "Authorization: Bearer gih_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"

{
  "error": {
    "message": "Invalid request body",
    "code": "invalidRequest"
  }
}

• 在正式環境中，同步生成最長可執行 800 秒。
• n 必須介於 1 到 4 之間。
• 參考圖片支援 PNG、JPG、JPEG 和 WebP。包含所有參考圖片在內的整個請求大小必須低於 4.5MB（圖片總計請保持在 4MB 以下）。過大的請求會在抵達 API 之前被託管平台以純文字 413 拒絕，因此請先調整圖片大小或進行壓縮。
• 參考圖片的數量上限由各模型的 reference_image_limit 定義。
• 速率限制：每個 API key 每分鐘 60 次生成請求，每個 IP 位址每分鐘 120 次。每個回應皆帶有 RateLimit-Limit、RateLimit-Remaining 與 RateLimit-Reset 標頭；429 回應亦會帶有 Retry-After。
• 若要安全地重試生成，請傳送 Idempotency-Key 標頭（最多 120 個字元）。使用相同的 API key 重複傳送相同的 key 將回傳原先的生成結果，而不會再次計費。
• 非同步模式會回傳 202 與 poll_url。目前尚未支援 Webhook。