GPT Image 2
GPT Image 2 is an image generation and editing model supporting text-to-image, multi-image editing, multiple sizes and quality tiers, and batches of one to eight images. It is suited to product visuals, advertising assets, concept design, image editing, and automated creative workflows that need repeatable API access. Use the playground below to test representative prompts, reference images, dimensions, quality settings, output formats, and image counts that are available for this model. Before production rollout, compare visual quality, instruction following, subject consistency, processing time, failure handling, and estimated cost with your actual workload. The controls shown on this page describe the currently supported integration options.

- Model ID
- gpt-image-2
- Provider
- OpenAI
- API endpoint
- /v1/images/generations
- Pricing
- 5
- Last updated
- 2026-08-13
Capabilities
- Image generation through the current public endpoint
- Editing or reference-image controls when exposed by the live schema
- Current parameters including prompt, image_urls, size
Limitations
- Capabilities and parameter ranges can change; pin and validate the parameter set used in production
- Do not assume support for parameters absent from the live request schema
- Asynchronous jobs require explicit polling, failure, timeout, and safety-status handling
Use cases
- Product prototypes and automated content workflows
- Batch media generation and programmatic creative tooling
- Multi-model applications that need unified authentication, billing, and usage records
Pricing and billing examples
- Input tokens | 5 | 1M tokens
- Output tokens | 30 | 1M tokens
- Image tokens | 8 | 1M tokens
Request parameters
| Parameter | Type | Required | Default | Options |
|---|---|---|---|---|
| model | string | Yes | ||
| prompt | textarea | Yes | ||
| image_urls | asset_list | No | ||
| size | size | Yes | auto | auto, 1024x1024, 1024x1536, 1536x1024 |
| quality | select | Yes | auto | auto, low, medium, high |
| n | integer | Yes | 1 | |
| output_format | select | Yes | png | png, jpeg, webp |
API examples
cURL
curl -X POST 'https://api.uniall.ai/v1/images/generations' \
-H 'Authorization: Bearer $UNIALL_API_KEY' \
-H 'Content-Type: application/json' \
-d '{"model":"gpt-image-2","n":1,"output_format":"png","prompt":"Describe the output you want","quality":"auto","size":"auto"}'Python
import json
import requests
payload = json.loads(r'''{"model":"gpt-image-2","n":1,"output_format":"png","prompt":"Describe the output you want","quality":"auto","size":"auto"}''')
response = requests.post(
"https://api.uniall.ai/v1/images/generations",
headers={"Authorization": "Bearer " + UNIALL_API_KEY},
json=payload,
)
response.raise_for_status()
result = response.json()JavaScript
const response = await fetch("https://api.uniall.ai/v1/images/generations", {
method: 'POST',
headers: {
Authorization: `Bearer ${process.env.UNIALL_API_KEY}`,
'Content-Type': 'application/json',
},
body: JSON.stringify({"model":"gpt-image-2","n":1,"output_format":"png","prompt":"Describe the output you want","quality":"auto","size":"auto"}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
const result = await response.json();Frequently asked questions
What API endpoint does gpt-image-2 use?
The endpoint is resolved from the current model capabilities and request schema and shown on this page.
How is gpt-image-2 priced?
The pricing section reads the current structured billing configuration, so editorial text does not need a rewrite after a price change.
Can I use Python?
Yes. The example uses the current endpoint and exact model identifier.
Are JavaScript and cURL examples included?
Yes. All examples share the same live request structure.
Which resolution, duration, or reference-image controls are supported?
Supported controls come from the current request schema. Do not assume fields that are not listed.
What should I validate before production use?
Validate parameters, timeouts, error handling, and asynchronous generation status behavior after model updates.