GPT Image 2 Image Generation
GPT Image 2 Image Generation is available in the Business API catalog.
openai/gpt-image-2/text-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/text-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
DELETEhttps://api.dev.pika.art/v1/media/jobs/{request_id}erase the stored media and prompt
REST Setup
plain HTTPS
Image generation runs through the REST endpoint shown above. The API is plain JSON over HTTPS, so any HTTP client works. No provider-specific SDK is required.
Generate
POST /v1/media/openai/gpt-image-2/text-to-image
Request
curl -X POST https://api.dev.pika.art/v1/media/openai/gpt-image-2/text-to-image \-H "X-API-Key: YOUR_API_KEY" \-H "Content-Type: application/json" \-d '{"prompt": "The single lowercase word \"pause\" rendered as thick transparent liquid glass floating over a heavily defocused peach-cream curtain lit by soft evening window light — letterforms visible only through refraction bending the fabric folds behind them, crisp caustic white speculars on glyph edges, refraction strongest at the edges, a thin glass ring looping behind and in front of the letters to prove real 3D. Rounded soft letterforms, loose kerning. Palette: peach haze #E8C4A8, cream whites, powder grey. Heavy gaussian softness on the ground, fine grain preventing banding, slight bloom on speculars. Slightly desaturated filmic grade, low contrast while maintaining color, light film grain, warmed whites, editorial print finish, generous negative space. No hard drop shadows, no neon glow, no extra decoration, no other text.","num_images": 1,"aspect_ratio": "3:4","output_format": "png","resolution": "1K","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.qualityenum
Rendering quality of the output; 'auto' lets the provider choose.Accepted values
- aspect_ratio
- output_format
- resolution
- background
- quality
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.
DELETE /v1/media/jobs/{request_id} erases the stored media for a job, and the request captured at submit (the prompt and parameters). The job then reports deleted_at and no output, and the content endpoint answers 410.
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.deleted_atnumber
When you deleted the job's stored media, in epoch seconds. Null until then, and output is null once it is set.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"}} |