GPT Image 2.5 Sunburst

GPT Image 2.5 Sunburst Edit Image is available in the Business API catalog.

openai/gpt-image-2.5-sunburst/image-to-image

Capabilities

Best for

•Concept art and mood boards
•Product and marketing visuals
•Batch generation at scale

Not for

•Exact text rendering at small sizes
•Precise brand-logo reproduction
•Vector output

Authentication

api key header

The Pika API uses API keys to authenticate requests. Send your key in the X-API-Key header. Your API key is a secret. Don't expose it in browsers or other client-side code. Instead, call the API from your server. The signed-in playground uses a portal session and never sends your API key.

header

X-API-Key: YOUR_API_KEY

Endpoint

asynchronous · poll for the result

POSThttps://api.dev.pika.art/v1/media/openai/gpt-image-2.5-sunburst/image-to-imagegenerate endpoint

GEThttps://api.dev.pika.art/v1/media/jobs/{request_id}poll until completed

GEThttps://api.dev.pika.art/v1/media/jobs/{request_id}/contentthe output URL, for clients that only kept the id

Reference Uploads

media inputs

Media inputs accept any public URL. To use a local file, POST its content_type and size_bytes to /v1/media/uploads, PUT the file to the returned upload_url, then pass the url.

upload

# 1. Request a presigned upload URL. Send the file's content
#    type and its exact size in bytes.
curl -X POST https://api.dev.pika.art/v1/media/uploads \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"content_type": "image/png", "size_bytes": 12345}'

# The response returns two URLs:
#   upload_url: a temporary URL to upload the file to. Expires in 5 minutes.
#   url:        the permanent Pika URL. Pass it to the model as the input.
# {
#   "upload_url": "https://upload.r2.pika.art/...?X-Amz-Signature=...",
#   "url": "https://cdn.pika.art/v2/media/uploads/org_abc/9f8e7d.png"
# }

# 2. Upload the file to upload_url, then pass url to the model.
curl -X PUT "<upload_url>" \
  -H "Content-Type: image/png" \
  --data-binary @input.png

Generate

POST /v1/media/openai/gpt-image-2.5-sunburst/image-to-image

Request

curl -X POST https://api.dev.pika.art/v1/media/openai/gpt-image-2.5-sunburst/image-to-image \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "prompt": "Using the supplied photograph as the base, keep its composition, camera angle, framing and lighting, and keep every element not named below exactly as it is. Keep the torn cut-paper collage treatment and the\ntopiary garden. Change only the following. Keep the transparent background and edge of the artwork.\n\nThe existing figure is now in full profile to camera, mid-stride and not looking at the camera, walking a great dane on a lead. Their coat changes from royal blue to a black-and-white cow-print coat.\n\nAdd a second figure walking in the opposite direction: an invented man walking a fluffy ginger cat on a lead, wearing an oversized charcoal peacoat and baggy pale-pink corduroy trousers.\n\nBoth figures and both animals are built from the same torn cut-paper collage material as the rest of the scene — layered fragments of coloured paper with visible torn fibrous edges, slightly offset and\nmis-registered.\n\nLighting stays as it is: one enormous softbox, fully diffused, soft and even, no hard shadows. Fine medium-format film grain. Colour soft but vibrant, never oversaturated, never dull. Any people are entirely fictional invented individuals, anatomically correct and complete. No text, no logos, no\nwatermark.",
  "num_images": 1,
  "aspect_ratio": "16:9",
  "output_format": "png",
  "resolution": "1K",
  "image_urls": [
    "https://cdn.pika.art/v2/media/uploads/a7112d4d-62ed-4a11-8dee-74e89c2ec037/7364d1f8a24840408bedc908790be67e.png"
  ],
  "quality": "medium"
}'

Response

{
  "id": "media_8f3a2c91-5b7d-4e0a-9c26-31d4f2a8e6b0",
  "status": "queued"
}

Request body

promptstringrequired

Text prompt describing the image to generate.

num_imagesinteger1 – 10default: 1

Number of images to generate.

aspect_ratioenum

Output aspect ratio. Ignored when 'size' is set.

output_formatenum

Image file format of the output.

resolutionenum

Output resolution.

backgroundenum

Background of the output. 'transparent' needs a png or webp output_format.

sizestring

Explicit output size as 'WxH' (e.g. '1024x1024'), or 'auto' to let the provider choose. Overrides aspect_ratio and resolution.

image_urlsstring[]1 – 16required

URLs of the source images to edit.

mask_image_urlstring

Mask URL marking the region to edit (transparent areas are edited). Must be a PNG with an alpha channel; the provider rejects masks without one.

qualityenum

Rendering quality of the output.

Accepted values

aspect_ratio
output_format
resolution
background
quality

Input modes

Image urlsimage_urls

Use a public URL directly, or POST { content_type, size_bytes } to /v1/media/uploads, PUT the image to the returned upload_url with the returned headers, then pass the url.

Mask image urlmask_image_url

Use a public URL directly, or POST { content_type, size_bytes } to /v1/media/uploads, PUT the image to the returned upload_url with the returned headers, then pass the url.

Returns

Returns a job object with status , not the final output. Store the id from the response and poll the job until it completes.

Poll status

GET /v1/media/jobs/{request_id}

Request

curl https://api.dev.pika.art/v1/media/jobs/{request_id} \
  -H "X-API-Key: YOUR_API_KEY"

Response

{
  "id": "media_8f3a2c91-5b7d-4e0a-9c26-31d4f2a8e6b0",
  "status": "running"
}

Poll the job by id until it reaches a terminal state: completed or failed. A completed job carries its download URL in output, and GET /v1/media/jobs/{request_id}/content returns that same URL as { "url" } for clients that only kept the id.

The job object

idstring

Unique identifier for the job.

statusenum

The status of the job.One of:

object

The generation output. Present once the job completes.

errorstring

If the job failed, the reason for the failure.

usageobject

Units the provider reported for the job, such as video_output_tokens or image_output_tokens. Present once the job is terminal, carries only the units the job reports, and is null when nothing was reported.

object

What the job charged. Present once the job is terminal; null on the submit response and on webhooks.

Errors

shared across calls

Errors use conventional HTTP status codes with a JSON body of the shape {"message": "..."}. Validation failures return 422 with a message naming the offending field. Submit rejections after the job row exists (balance, rate limit) return the failed job envelope — branch on error.code.

Status	When	Body
401 Unauthorized	The API key is missing or invalid.	{"message":"Invalid API key"}
403 Forbidden	An inactive key is rejected with a {"message"} body. A submit that the org balance or postpaid cycle limit cannot cover is rejected after the job row exists and returns the failed job envelope. GET /billing/balance separates the two: a 200 means the key is active, so the rejection was the balance or the cycle limit.	{"id":"media_8f3a2c91-5b7d-4e0a-9c26-31d4f2a8e6b0","status":"failed","error":{"code":"insufficient_balance","message":"Insufficient org balance"}}
404 Not Found	No job with that id exists in your org, or the media path names an unknown vendor/model/function.	{"message":"media job not found"}
409 Conflict	The result was requested before the job completed, or an Idempotency-Key header was reused with a different body.	{"message":"media job is not ready"}
422 Unprocessable Entity	The request body failed validation: an invalid enum value, a missing required field, a wrong type, or malformed JSON. The JSON message names the offending field. A schema-valid parameter combination that cannot be priced instead fails after job creation and returns the failed job envelope with error code invalid_input.	{"message":"duration: Input should be less than or equal to 15"}
429 Too Many Requests	Org limit reached: requests per minute or day, or concurrent jobs. Returned as the failed job envelope; check the Retry-After header and retry with a fresh Idempotency-Key.	{"id":"media_8f3a2c91-5b7d-4e0a-9c26-31d4f2a8e6b0","status":"failed","error":{"code":"rate_limited","message":"rate limit exceeded: rpm"}}
503 Service Unavailable	The model rail or a backend dependency is temporarily unavailable. Returned as the failed job envelope; retry with backoff and a fresh Idempotency-Key.	{"id":"media_8f3a2c91-5b7d-4e0a-9c26-31d4f2a8e6b0","status":"failed","error":{"code":"provider_unavailable","message":"media dispatch unavailable"}}

# 1. Request a presigned upload URL. Send the file's content

# type and its exact size in bytes.

curl -X POST https://api.dev.pika.art/v1/media/uploads \

-H "X-API-Key: YOUR_API_KEY" \

-H "Content-Type: application/json" \

-d '{"content_type": "image/png", "size_bytes": 12345}'

# The response returns two URLs:

# upload_url: a temporary URL to upload the file to. Expires in 5 minutes.

# url: the permanent Pika URL. Pass it to the model as the input.

# {

# "upload_url": "https://upload.r2.pika.art/...?X-Amz-Signature=...",

# "url": "https://cdn.pika.art/v2/media/uploads/org_abc/9f8e7d.png"

# }

# 2. Upload the file to upload_url, then pass url to the model.

curl -X PUT "<upload_url>" \

-H "Content-Type: image/png" \

--data-binary @input.png

curl -X POST https://api.dev.pika.art/v1/media/openai/gpt-image-2.5-sunburst/image-to-image \

-H "X-API-Key: YOUR_API_KEY" \

-H "Content-Type: application/json" \

-d '{

"prompt": "Using the supplied photograph as the base, keep its composition, camera angle, framing and lighting, and keep every element not named below exactly as it is. Keep the torn cut-paper collage treatment and the\ntopiary garden. Change only the following. Keep the transparent background and edge of the artwork.\n\nThe existing figure is now in full profile to camera, mid-stride and not looking at the camera, walking a great dane on a lead. Their coat changes from royal blue to a black-and-white cow-print coat.\n\nAdd a second figure walking in the opposite direction: an invented man walking a fluffy ginger cat on a lead, wearing an oversized charcoal peacoat and baggy pale-pink corduroy trousers.\n\nBoth figures and both animals are built from the same torn cut-paper collage material as the rest of the scene — layered fragments of coloured paper with visible torn fibrous edges, slightly offset and\nmis-registered.\n\nLighting stays as it is: one enormous softbox, fully diffused, soft and even, no hard shadows. Fine medium-format film grain. Colour soft but vibrant, never oversaturated, never dull. Any people are entirely fictional invented individuals, anatomically correct and complete. No text, no logos, no\nwatermark.",

"num_images": 1,

"aspect_ratio": "16:9",

"output_format": "png",

"resolution": "1K",

"image_urls": [

"https://cdn.pika.art/v2/media/uploads/a7112d4d-62ed-4a11-8dee-74e89c2ec037/7364d1f8a24840408bedc908790be67e.png"

"quality": "medium"

Status

When

Body

401 Unauthorized

The API key is missing or invalid.

{"message":"Invalid API key"}

403 Forbidden

An inactive key is rejected with a {"message"} body. A submit that the org balance or postpaid cycle limit cannot cover is rejected after the job row exists and returns the failed job envelope. GET /billing/balance separates the two: a 200 means the key is active, so the rejection was the balance or the cycle limit.

{"id":"media_8f3a2c91-5b7d-4e0a-9c26-31d4f2a8e6b0","status":"failed","error":{"code":"insufficient_balance","message":"Insufficient org balance"}}

404 Not Found

No job with that id exists in your org, or the media path names an unknown vendor/model/function.

{"message":"media job not found"}

409 Conflict

The result was requested before the job completed, or an Idempotency-Key header was reused with a different body.

{"message":"media job is not ready"}

422 Unprocessable Entity

The request body failed validation: an invalid enum value, a missing required field, a wrong type, or malformed JSON. The JSON message names the offending field. A schema-valid parameter combination that cannot be priced instead fails after job creation and returns the failed job envelope with error code invalid_input.

{"message":"duration: Input should be less than or equal to 15"}

429 Too Many Requests

Org limit reached: requests per minute or day, or concurrent jobs. Returned as the failed job envelope; check the Retry-After header and retry with a fresh Idempotency-Key.

{"id":"media_8f3a2c91-5b7d-4e0a-9c26-31d4f2a8e6b0","status":"failed","error":{"code":"rate_limited","message":"rate limit exceeded: rpm"}}

503 Service Unavailable

The model rail or a backend dependency is temporarily unavailable. Returned as the failed job envelope; retry with backoff and a fresh Idempotency-Key.

{"id":"media_8f3a2c91-5b7d-4e0a-9c26-31d4f2a8e6b0","status":"failed","error":{"code":"provider_unavailable","message":"media dispatch unavailable"}}

GPT Image 2.5 Sunburst

Capabilities

Authentication

Endpoint

Reference Uploads

Generate

Poll status

Errors

Join the club

GPT Image 2.5 Sunburst

Capabilities

Authentication

Endpoint

Reference Uploads

Generate

Poll status

Errors