Edit source images with GPT Image 2 through the SeeAPI or Replicate provider. Provide image URLs and a text prompt, configure the aspect ratio and resolution, then use the returned generation ID to track the asynchronous task.
Developer API pricing
Provider: SeeAPI
USD estimate: $0.0037 / credit · Estimated equivalent, not an additional charge.
1K: 10 credits/gen (≈ $0.037/gen)
After submitting a task, use the unified query endpoint to check progress and retrieve results:
Manage the secret used to verify generation webhook signatures. Callback URLs are supplied when you create each generation.
Callback URL per generation.
/v1/generationsA unique key for this generation request. Reuse the same value only when retrying the identical request body.
order-20260818-001The public model ID documented on this page. Use gpt-image-2 for this Endpoint.
gpt-image-2gpt-image-2gpt-image-2The public Endpoint ID for the selected model. Use the Endpoint whose input schema matches this request.
image-to-imageimage-to-imageimage-to-imageOptional public Provider ID. Omit it to use `seeapi`, or set it to `replicate` to use the Replicate-specific input rules.
seeapireplicateseeapiseeapiProvider-specific image-editing parameters. Use the field group for the selected `provider`; unsupported fields or combinations are rejected.
Provider parameters
seeapiDefault ProviderDescribe how the source images should be edited, including the desired subject, composition, style, lighting, and other important details. Up to 20,000 characters.
A cinematic city at nightSource images used by this Endpoint. Provide reachable image URLs and follow the count and format limits shown for this Provider.
["https://client.example.com/input.png"]Select the output width-to-height ratio. Use `auto` to let SeeAPI determine the ratio.
16:99:16auto1:14:33:4autoSelect `1K`, `2K`, or `4K`. Available values depend on `aspect_ratio`.
1K2K4K1KThis parameter is only supported when the resolution is 1K. Available when resolution is "1K".
autoopaquetransparentreplicateDescribe how the source images should be edited, including the desired subject, composition, style, lighting, and other important details. Up to 20,000 characters.
A cinematic city at nightSource images used by this Endpoint. Provide reachable image URLs and follow the count and format limits shown for this Provider.
["https://client.example.com/input.png"]Select the output width-to-height ratio. Use `auto` to let Replicate determine the ratio.
16:99:16auto1:13:22:34:33:4autoSelect `1K`, `2K`, or `4K` for the requested output resolution.
1K2K4K1KChoose the output image format. Some values depend on background.
webppngjpegpngSet the output compression level from 0 to 100.
30Choose automatic, transparent, or opaque background.
autotransparentopaqueautoOptional absolute HTTPS URL that receives terminal generation updates. If omitted, query the task-details endpoint with the returned generation ID.
https://client.example.com/webhooks/seeapitask_xxxgpt-image-2image-to-imageseeapireplicateseeapi: SeeAPIreplicate: ReplicateseeapiprocessingprocessingEstimated public credits. Values can include up to three decimal places.
10Consumed public credits, with up to three decimal places.
0Refunded public credits, with up to three decimal places.
02026-08-18T10:00:00Z2026-08-18T10:00:00ZWhether this response is an idempotent replay of an earlier request.
falsetask_xxxgpt-image-2image-to-imageseeapireplicateseeapi: SeeAPIreplicate: ReplicateseeapiprocessingprocessingEstimated public credits. Values can include up to three decimal places.
10Consumed public credits, with up to three decimal places.
0Refunded public credits, with up to three decimal places.
02026-08-18T10:00:00Z2026-08-18T10:00:00ZWhether this response is an idempotent replay of an earlier request.
falseInvalid JSON, parameters, Schema, or API Policy
Invalid API Key or authentication failed
Insufficient credits
The current request is not allowed
Model, Endpoint, or task not found
Idempotency conflict or the same request is still being created
Request body is too large
Too many requests
Service temporarily unavailable
const response = await fetch("https://api.seeapi.com/v1/generations", {
method: "POST",
headers: {
"Authorization": "Bearer YOUR_API_KEY",
"Idempotency-Key": "order-20260818-001",
"Content-Type": "application/json"
},
body: JSON.stringify({
"model": "gpt-image-2",
"endpoint": "image-to-image",
"provider": "seeapi",
"input": {
"prompt": "A cinematic city at night",
"input_images": [
"https://client.example.com/input.png"
],
"aspect_ratio": "auto",
"resolution": "1K",
"background": "auto"
},
"callback_url": "https://client.example.com/webhooks/seeapi"
})
});
const result = await response.json();{
"generation": {
"id": "task_xxx",
"model": "gpt-image-2",
"endpoint": "image-to-image",
"provider": "seeapi",
"status": "processing",
"estimated_credits": 10,
"consumed_credits": 0,
"refunded_credits": 0,
"created_at": "2026-08-18T10:00:00Z",
"updated_at": "2026-08-18T10:00:00Z"
},
"idempotent": false
}