GPT Image 1 API: Call OpenAI's Image Model, One Key

gpt-image-1 is OpenAI's native multimodal image model — the one behind ChatGPT's in-chat image generation, good at following detailed prompts and rendering text inside an image. Calling it directly means an OpenAI account, its own billing, and its own SDK. Through the Aigenway gateway it sits behind the openai_image provider instead — one API key, one prepaid USD balance, the same request shape you use for every other model.

What you get

openai_image covers the whole OpenAI image lineup — gpt-image-1, its newer sibling gpt-image-2, and the legacy dall-e-3 / dall-e-2 — behind two methods: text_to_image and image_edit. OpenAI can ship new codes or retire old ones on its own schedule, so pull the live list instead of hardcoding one:

curl "https://api.aigenway.com/v1/methods?provider=openai_image" \
  -H "Authorization: Bearer sk_live_..."

The response gives you the current model codes, the method names each supports, and per-image pricing on your account right now — confirm gpt-image-1 is listed before you build against it.

Generate an image from text

POST to /v1/generations with provider, model, method and params. The Idempotency-Key header makes retries safe — resend the same key on a dropped connection and you get the same result back, not a second charge:

curl -X POST https://api.aigenway.com/v1/generations \
  -H "Authorization: Bearer sk_live_..." \
  -H "Idempotency-Key: $(uuidgen)" \
  -H "Content-Type: application/json" \
  -d '{
    "provider": "openai_image",
    "model": "gpt-image-1",
    "method": "text_to_image",
    "params": {
      "prompt": "a hand-lettered coffee shop sign reading OPEN 7AM, warm morning light",
      "resolution": "1024x1024",
      "mode": "medium"
    }
  }'

mode sets the quality tier for gpt-image-1 (low / medium / high / auto), and resolution picks the output size (1024x1024, 1024x1536, 1536x1024, or auto). Both are worth reading off /v1/methods too, since the accepted values differ across the OpenAI models sharing this provider.

Edit an existing image

gpt-image-1 also handles composite edits — up to six input images plus a prompt describing the change, with an optional PNG mask to constrain the region:

curl -X POST https://api.aigenway.com/v1/generations \
  -H "Authorization: Bearer sk_live_..." \
  -H "Idempotency-Key: $(uuidgen)" \
  -H "Content-Type: application/json" \
  -d '{
    "provider": "openai_image",
    "model": "gpt-image-1",
    "method": "image_edit",
    "params": {
      "prompt": "add a small orange cat sleeping on the windowsill",
      "input_images": ["https://example.com/kitchen.png"],
      "resolution": "1024x1024"
    }
  }'

background is another gpt-image-1-specific option worth knowing — set it to transparent when you need a cutout instead of a filled background, or leave it auto otherwise.

Poll or webhook for the result

Both methods return a task, not a finished image inline. Read the task ID off the response, then get the output one of two ways:

1. Poll. GET /v1/generations/{task_id} until status flips to succeeded (or failed), then read the image URL off the response.
2. Webhook. Set a callback_url on the request and the gateway POSTs the finished task to your endpoint the moment it's ready — no polling loop to write or rate-limit yourself.

The task shape, status values and webhook signature are identical across every model on the gateway — the code you write for gpt-image-1 also drives Nano Banana, Imagen 4 and every video model unchanged. Full contract in the task lifecycle and webhooks docs.

Why one gateway beats a provider-only account

• No separate OpenAI account. No API key to provision on platform.openai.com, no separate invoice to reconcile — sign up once and call the endpoint.
• One integration, every model. The same provider/model/method/params shape that calls gpt-image-1 also calls DALL·E, Imagen, Nano Banana and the video models — swap a string, not your SDK.
• Real USD billing. A prepaid balance replaces per-provider invoicing; check what's left from the API at any time.
• Idempotency and webhooks included. Retry-safe requests and signed callbacks are already built into the task contract, not something you bolt on yourself.

When OpenAI ships gpt-image-2 or retires a tier, pull the new code from /v1/methods and change one string — no new account, no new contract.