Get API

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}/contentget the result URL

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.
qualityenum
Rendering quality of the output; 'auto' lets the provider choose.
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.

Accepted values

aspect_ratio
output_format
resolution
quality
background

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.

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.

Get result

GET /v1/media/jobs/{request_id}/content

Request

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

Response

{
"url": "https://api.dev.pika.art/v1/files/img_8f3a2c91.png"
}

Once the job completes, fetch a download URL for the generated media.

Returns

urlstring
Download URL for the generated file.

Errors

shared across calls

Errors use conventional HTTP status codes with a JSON body of the shape {"message": "..."}. The one exception is validation: a request body that fails validation returns 422 with a plain-text body.

StatusWhenBody
401 UnauthorizedThe API key is missing or invalid.{"message":"Invalid API key"}
403 ForbiddenThe key is not active, or the org balance cannot cover the request.{"message":"Insufficient org balance"}
404 Not FoundNo job with that id exists in your org.{"message":"media job not found"}
409 ConflictThe 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 EntityThe request body failed validation: an invalid enum value, a missing required field, a wrong type, or malformed JSON. Returned as plain text, not JSON. A schema-valid parameter combination that cannot be priced returns the same status with a JSON message.Unprocessable entity
429 Too Many RequestsOrg limit reached: requests per minute or day, or concurrent jobs. Check the Retry-After header.{"message":"rate limit exceeded: rpm"}
503 Service UnavailableThe model rail or a backend dependency is temporarily unavailable. Retry with backoff.{"message":"media dispatch unavailable"}

Pricing

only successful runs are charged

TierPrice
Image output$22.50 / 1M tokens
Input$3.75 / 1M tokens

Per-model pricing

Transparent, usage-based rates for every OpenAI model.

GPT Image 2

Image

Image to Image

Image output$30 / 1M tok
Input$5 / 1M tok
Image input$8 / 1M tok

Text to ImageCurrent

Image output$22.50 / 1M tok
Input$3.75 / 1M tok

Whisper

Audio • Transcription

$0.007 / min

GPT-5.6 Sol

LLM

Input$5 / 1M tok
Output$30 / 1M tok
Cached input$0.50 / 1M tok

OpenAI GPT-5.6 Terra

LLM

Input$2 / 1M tok
Output$12 / 1M tok
Cached input$0.20 / 1M tok

OpenAI GPT-5.6 Luna

LLM

Input$0.20 / 1M tok
Output$1.20 / 1M tok
Cached input$0.02 / 1M tok

GPT-5.5

LLM

Input$2.50 / 1M tok
Output$15 / 1M tok
Cached input$0.25 / 1M tok