1K
15
credits / image
= $0.015 USD / image
100 images ≈ $1.50 · 1,000 images ≈ $15.00
- resolution
- 1K
OpenAI
Available via APIImage GenerationGPT Image 2.5 API
Generate or edit images with OpenAI's GPT Image 2.5, choosing the faster Flare or the quality-focused Sunburst version at the same price.
- Model ID
gpt-image-2.5- Starts at
- $0.015/image
- Free trial
- $0.20 in credits
New accounts start with $0.20 in free credits, about 13 images at the starting price.
GPT Image 2.5 is developed by OpenAI. Wizzx provides API access to it and does not own the model. All trademarks belong to their respective owners.
Next: turn the image into a video with
Model Guide
About GPT Image 2.5
Generate or edit images with OpenAI's GPT Image 2.5, choosing the faster Flare or the quality-focused Sunburst version at the same price.
Why choose GPT Image 2.5?
GPT Image 2.5 is OpenAI's image model with two versions. According to OpenAI, Flare is the smaller model, optimized for speed, with image quality comparable to GPT Image 2. Sunburst is the base model, optimized for quality, with higher image quality than GPT Image 2. OpenAI says both improve precise editing and subject preservation.
In Wizzx, one workflow covers generation and editing: leave the reference area empty to create an image from the prompt, or add references to edit them.
| Wizzx control | Current behavior |
|---|---|
| Prompt | Required for generation and editing |
| Version | Flare (default) or Sunburst, same price |
| Reference images | Optional, up to 16 JPEG, PNG, or WebP images; not charged |
| Aspect ratio | Auto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9 |
| Resolution | 1K (default), 2K, or 4K |
Choosing a version
Start with Flare when turnaround matters or when GPT Image 2 quality is already enough. Switch to Sunburst for demanding work such as product shots, ad creatives, and multi-turn editing where fine detail and subject preservation matter. Because both versions cost the same in Wizzx, compare them on your own prompts and keep the one that meets your quality bar.
Prompting approach
Describe the subject, composition, style, and constraints. For edits, state what should change and what must stay the same, and refine one thing at a time. When using several references, explain the role of each image instead of relying on their order alone. Repeated edits can drift, so restate the details you want preserved.
Wizzx scope
Wizzx generates one image per request. Resolution sets the per-image price; version, aspect ratio, and reference images do not change it. The live credit amount shown on the page comes from the backend catalog.
OpenAI's API also offers quality levels, transparent backgrounds, custom pixel sizes, and output format controls for GPT Image 2.5. Wizzx does not currently expose quality, background, output_format, or n for this model.
Source
Backend pricing
GPT Image 2.5 API pricing
Model identity, billing unit and every price tier below are read from the backend catalog.
2K
24
credits / image
= $0.024 USD / image
100 images ≈ $2.40 · 1,000 images ≈ $24.00
- resolution
- 2K
4K
35
credits / image
= $0.035 USD / image
100 images ≈ $3.50 · 1,000 images ≈ $35.00
- resolution
- 4K
1 credit = $0.001 USD. The final deduction returned by the API is authoritative.
Back to all modelsIntegrate the GPT Image 2.5 API
Every request is asynchronous: submit the task, keep the task ID, then poll for the result. The body below uses the model's default settings.
- 1
Get a GPT Image 2.5 API key
Sign in and create a key in the dashboard. Set WIZZX_API_KEY in your server environment; never expose it in browser code.
- 2
Submit a task
Send a POST request to the model endpoint. A successful submission returns data.task_id; keep that ID before polling. Submission is not generation completion.
- 3
Retrieve the result
Replace YOUR_TASK_ID with the returned ID and query /api/v1/task/status. Wait for SUCCEEDED and read the output URLs. Stop on FAILED or REVIEW_REQUIRED; do not automatically resubmit an uncertain task.
curl -X POST \
https://api.wizzx.ai/api/v1/task/submit/gpt-image-2.5 \
-H "Authorization: Bearer $WIZZX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"version": "flare",
"aspect_ratio": "auto",
"resolution": "1K",
"prompt": "A product shot of a glass perfume bottle on wet stone"
}'const response = await fetch("https://api.wizzx.ai/api/v1/task/submit/gpt-image-2.5", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.WIZZX_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"version": "flare",
"aspect_ratio": "auto",
"resolution": "1K",
"prompt": "A product shot of a glass perfume bottle on wet stone"
}),
});
const payload = await response.json();
const task = payload.data ?? payload;
const taskId = task.task_id;import os
import requests
response = requests.post(
"https://api.wizzx.ai/api/v1/task/submit/gpt-image-2.5",
headers={
"Authorization": f"Bearer {os.environ['WIZZX_API_KEY']}",
},
json={
"version": "flare",
"aspect_ratio": "auto",
"resolution": "1K",
"prompt": "A product shot of a glass perfume bottle on wet stone"
},
)
payload = response.json()
task = payload.get("data", payload)
task_id = task["task_id"]curl -X POST \
https://api.wizzx.ai/api/v1/task/status \
-H "Authorization: Bearer $WIZZX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"task_id": "YOUR_TASK_ID"
}'const response = await fetch("https://api.wizzx.ai/api/v1/task/status", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.WIZZX_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({ task_id: "YOUR_TASK_ID" }),
});
const payload = await response.json();
const task = payload.data ?? payload;import os
import requests
response = requests.post(
"https://api.wizzx.ai/api/v1/task/status",
headers={
"Authorization": f"Bearer {os.environ['WIZZX_API_KEY']}",
},
json={"task_id": "YOUR_TASK_ID"},
)
payload = response.json()
task = payload.get("data", payload)GPT Image 2.5 API parameters
The fields this endpoint accepts on Wizzx, read from the same schema as the Playground form.
| Parameter | Type | Default | Allowed values | Description |
|---|---|---|---|---|
promptPromptrequired | string | — | ≤ 20,000 | Describe the image to generate or the edit to apply. |
image_urlsReference Images | url[] ≤ 16 | — | — | Optional. Add up to 16 images (JPEG, PNG, or WebP) to switch from generation to image editing. Reference images are not charged. |
versionVersion | string | flare | flare · sunburst | Both versions cost the same. |
aspect_ratioAspect Ratio | string | auto | auto · 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 5:4 · 4:5 · 21:9 | — |
resolutionResolution | string | 1K | 1K · 2K · 4K | — |
API integration questions
- How much does the GPT Image 2.5 API cost?
- On Wizzx the GPT Image 2.5 API starts at $0.015/image (15 credits). Each tier above lists its parameters and billing unit, and failed tasks are refunded.
- What is the GPT Image 2.5 API model ID?
- gpt-image-2.5. Submit tasks to POST /api/v1/task/submit/gpt-image-2.5 with your API key.
- Am I charged if a task fails?
- No. Credits are reserved when you submit a task and refunded if it fails. You are only charged for successful tasks.
- Can I try the GPT Image 2.5 API for free?
- Yes. New accounts start with $0.20 in free credits, about 13 images at the starting price.
- Is this the official GPT Image 2.5 API?
- No. GPT Image 2.5 models are developed by OpenAI. Wizzx is an independent API platform that gives you access to them with one API key, an asynchronous task API and pay-as-you-go credits.
- Does the submit response contain the generated file?
- Generation is asynchronous. The submit response identifies the task. Query its status until it finishes, then use the output URLs in the result. See the API reference for response fields and error handling.
Wizzx API
Start building with the GPT Image 2.5 API
New accounts get $0.20 in free credits. Pay as you go with no subscription, and failed tasks are refunded.