Two models, one integration
Flare is the fast everyday model, Sunburst the precision one. They share an endpoint, a request shape and a rate card, so switching between them is a one-word change.
GPT Image 2.5 API / Flare and Sunburst on one token-priced API
Generate and edit images with Flare and Sunburst. Both models use the same token prices through PiAPI.
PiAPI pricing
USD per 1 million tokens. The same rates apply to Flare and Sunburst.
Price per 1 million tokens
| Model | Text input | Image input | Image output |
|---|---|---|---|
gpt-image-2.5-flareFastestEveryday, high-quality image generation. | $3.75 | $6.00 | $22.50 |
gpt-image-2.5-sunburstStrongestImage generation and editing precision. | $3.75 | $6.00 | $22.50 |
Ready to build with GPT Image 2.5?
GPT Image 2.5 models on PiAPI
What you get when you call GPT Image 2.5 through the PiAPI task API.
Four quality levels
The quality parameter accepts auto, low, medium and high, so you trade render time against detail per request instead of per integration.
Generation and editing
Send a prompt for text-to-image, or add reference images to edit an existing picture. Both operations run through the same asynchronous task API.
Token pricing, no minimums
You pay per token for text input, image input and image output. No seat fee, no subscription, and the published rates are in the table above.
Asynchronous tasks
Submit a task, get a task id, then poll the task endpoint or wait for the webhook. Long generations never block your request thread.
API access
Flare and Sunburst are available through the PiAPI API. See the API documentation for endpoints, authentication and request parameters.
Get started
Create your API key
Sign up and grab an API key from the PiAPI workspace — free credits are included on sign-up.
Top up credits
Add credits on the billing page when you are ready to scale beyond the free tier.
Call the API
POST your first task following the API docs, then poll the task until the result is ready.
Iterate in the playground
Prototype prompts and settings in the the playground above before wiring them into your product.
Create a task
curl -X POST 'https://api.piapi.ai/api/v1/images/generations/async' \
-H 'X-API-Key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "gpt-image-2.5-flare",
"prompt": "YOUR_PROMPT",
"size": "1024x1024",
"quality": "low"
}'Retrieve the result
curl 'https://api.piapi.ai/api/v1/task/{task_id}' \
-H 'X-API-Key: YOUR_API_KEY'image_urls / image_url / data
Pricing
- gpt-image-2.5-flare:text_input: $0.00375 / 1k_tokens
- gpt-image-2.5-flare:image_input: $0.006 / 1k_tokens
- gpt-image-2.5-flare:output: $0.0225 / 1k_tokens
Create a task
curl -X POST 'https://api.piapi.ai/api/v1/images/edits/async' \
-H 'X-API-Key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "gpt-image-2.5-flare",
"prompt": "YOUR_PROMPT",
"size": "1024x1024",
"quality": "low",
"image": [
"YOUR_IMAGE_URL"
]
}'Retrieve the result
curl 'https://api.piapi.ai/api/v1/task/{task_id}' \
-H 'X-API-Key: YOUR_API_KEY'image_urls / image_url / data
Pricing
- gpt-image-2.5-flare:text_input: $0.00375 / 1k_tokens
- gpt-image-2.5-flare:image_input: $0.006 / 1k_tokens
- gpt-image-2.5-flare:output: $0.0225 / 1k_tokens
Create a task
curl -X POST 'https://api.piapi.ai/api/v1/images/generations/async' \
-H 'X-API-Key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "gpt-image-2.5-sunburst",
"prompt": "YOUR_PROMPT",
"size": "1024x1024",
"quality": "low"
}'Retrieve the result
curl 'https://api.piapi.ai/api/v1/task/{task_id}' \
-H 'X-API-Key: YOUR_API_KEY'image_urls / image_url / data
Pricing
- gpt-image-2.5-sunburst:text_input: $0.00375 / 1k_tokens
- gpt-image-2.5-sunburst:image_input: $0.006 / 1k_tokens
- gpt-image-2.5-sunburst:output: $0.0225 / 1k_tokens
Create a task
curl -X POST 'https://api.piapi.ai/api/v1/images/edits/async' \
-H 'X-API-Key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "gpt-image-2.5-sunburst",
"prompt": "YOUR_PROMPT",
"size": "1024x1024",
"quality": "low",
"image": [
"YOUR_IMAGE_URL"
]
}'Retrieve the result
curl 'https://api.piapi.ai/api/v1/task/{task_id}' \
-H 'X-API-Key: YOUR_API_KEY'image_urls / image_url / data
Pricing
- gpt-image-2.5-sunburst:text_input: $0.00375 / 1k_tokens
- gpt-image-2.5-sunburst:image_input: $0.006 / 1k_tokens
- gpt-image-2.5-sunburst:output: $0.0225 / 1k_tokens
GPT Image 2.5 API FAQ
Which GPT Image 2.5 models are available?
The API supports gpt-image-2.5-flare and gpt-image-2.5-sunburst for image generation and editing.
How much does GPT Image 2.5 API cost?
USD per 1 million tokens. The same rates apply to Flare and Sunburst.
Which quality values does the API accept?
The quality parameter accepts auto, low, medium and high. The API rejects xhigh, max and standard with HTTP 400.
More questions? See the API docs.
Related reading
Guides and comparisons for the GPT Image family on the PiAPI blog.
GPT Image 2.5 API
GPT Image 2 API Guide: Features, Prompt Tips, Pricing, and Examples
Learn how GPT Image 2 works, explore its key features, prompt tips, pricing, and real examples for production-ready AI image generation.
GPT Image 2.5 API
GPT Image 2 vs GPT Image 1.5 API: What's New in OpenAI Image Generation?
Compare GPT Image 2 vs GPT Image 1.5 API. Discover new features, image quality upgrades, pricing differences, prompt tips, and why GPT Image 2 is the latest choice for AI image generation.
GPT Image 2.5 API
GPT Image 2 vs Nano Banana 2.0: The Ultimate AI Image Generation Showdown
Compare Nano Banana 2.0 vs GPT Image 2 in image quality, prompt accuracy, realism, pricing, and API usage. See real examples, prompt tests, and performance comparisons.