GPT Image Hub API Doc

Tutti gli endpoint v1, ad eccezione dell'elenco dei modelli, richiedono una chiave API nell'intestazione Authorization. La chiave grezza viene mostrata una volta al momento della creazione; il server memorizza solo un hash.

Authorization: Bearer gih_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

L'endpoint dei modelli restituisce ID modello, fornitori, proporzioni supportate, qualità supportate, limiti di immagini di riferimento e crediti per immagine.

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": "gpt-image-2",
    "prompt": "A cinematic product photo with premium studio lighting",
    "size": "1024x1024",
    "quality": "high",
    "n": 1
  }'

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"

L'endpoint dei crediti restituisce il saldo, il tipo di conto e la prossima scadenza del credito per l'utente che possiede la chiave API.

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

The image generation endpoint waits for completion by default. Set async to true to receive a generation id immediately and poll /api/v1/generations/:generationId for the result. Credits are charged before provider generation and refunded automatically when the provider fails or returns fewer images than requested.

JSON richiesta

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
  }'

Async task

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 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": 8
  },
  "poll_url": "https://www.gptimagehub.com/api/v1/generations/clx_generation_log_id"
}

Richiesta immagine di riferimento

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"

Risposta

{
  "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": 8
  },
  "balance": {
    "credits": 112,
    "account_type": "PRO",
    "next_expiration": null
  }
}

Utilizza l'ID restituito dall'endpoint di generazione per recuperare il log e l'immagine salvati URLs. Le chiavi API possono leggere solo generazioni possedute dallo stesso utente.

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

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

• Synchronous generation can run for up to 800 seconds on production.
• n must be between 1 and 4.
• Reference images support PNG, JPG, JPEG, and WebP. Each file can be up to 50MB.
• The maximum reference image count is defined by each model's reference_image_limit.
• Async mode returns 202 with poll_url. Webhooks and a separate API rate limit are not included yet.