POST/api/v1/imagine2 creditsSynchronous

GPT-4o Image

Provider · OpenAIType · T2I / EditModel ID · gpt-4o-imageUpstream ID · gpt-4o-image

Reverse-engineered ChatGPT image generation (not the official OpenAI API). Same price as GPT-Image-1 but uses the ChatGPT internal pipeline. May have stricter and less predictable content moderation.

Request Parameters

Parameter	Type	Required	Description
prompt	`string`	Required	The text prompt describing the image to generate.
model	`string`	Optional	Set to `gpt-4o-image` to use this model.Default: `gpt-4o-image`
image_url	`string`	Optional	Reference image URL for image-to-image generation. Optional — omit for pure text-to-image.
aspect_ratio	`string`	Optional	Output aspect ratio. Allowed: 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3.Default: `1:1`
webhook_url	`string`	Optional	URL where we POST the completed task result.
webhook_secret	`string`	Optional	Sent as x-webhook-secret header in webhook delivery for verification.

Example Request

cURL

curl -X POST https://api.journeyapi.com/api/v1/imagine \
  -H "Authorization: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-image",
    "prompt": "a whimsical illustration of a cat astronaut floating in space",
    "aspect_ratio": "1:1"
  }'

Response

This model is synchronous — the response includes the finished image_url directly. No polling required.

200 OK

{
  "task_id": "550e8400-e29b-41d4-a716-446655440000",
  "status": "finished",
  "image_url": "https://cdn.example.com/output.png"
}

Quirks & Gotchas

This uses the unofficial ChatGPT pipeline, not the official OpenAI API. Content policy enforcement is stricter and more unpredictable than gpt-image-1.

If your prompt gets rejected unexpectedly, try gpt-image-1 instead.