OpenAI GPT Image 2 delivers next-gen AI image generation from text prompts with near-perfect text rendering, native 4K output, and deep world knowledge. As the latest in the GPT Image series, this GPT Image API supports model, prompt, and other parameters — ideal for production workflows.
Transparent pricing with no hidden fees. Pay only for what you use.
gpt-image-2-officialEstimated Price
Save 20%Showing: Gold member price
Price is calculated from token usage — this configuration uses about 196 tokens.
gpt-image-2-ext(gpt-image-2)| Tier | GoldCurrent price | Platinum | Diamond | Official | Your savings |
|---|---|---|---|---|---|
| 1K | 0.085Credits/ image~$0.0085/ image | 0.0808Credits/ image~$0.0081/ image | 0.0765Credits/ image~$0.0077/ image | 2.109Credits/ image~$0.2109/ image | 95.9% |
| 2K | 0.15Credits/ image~$0.015/ image | 0.1425Credits/ image~$0.0143/ image | 0.135Credits/ image~$0.0135/ image | 4.283Credits/ image~$0.4283/ image | 96.4% |
| 4K | 0.22Credits/ image~$0.022/ image | 0.209Credits/ image~$0.0209/ image | 0.198Credits/ image~$0.0198/ image | 7.117Credits/ image~$0.7117/ image | 96.9% |
* Actual costs are subject to final output.
APIMart provides the most affordable and reliable access to OpenAI GPT Image 2. Generate high-quality images with the GPT Image API using model, prompt, and other parameters. Save 20% or more with membership.
50K+
Active Users
99.9%
Uptime
2x
Faster
70%
Cost Savings
Call the gpt-image-2 model on APIMart with one POST request. Generation is asynchronous: submit a task, then poll the task endpoint to get the GPT Image 2 image URL.
Save the key you created above in the APIMART_API_KEY environment variable and send it as Authorization: Bearer <key> on every request.
POST /v1/images/generations with model gpt-image-2, your prompt, size and resolution. The response returns a task_id.
Send GET /v1/tasks/{task_id} until status is completed, then read the image URL from data.result.images[0].url[0]. Image URLs expire at expires_at, so download the files if you need to keep them. A failed task returns the reason in error.message.
See the GPT Image 2 API reference for every parameter and response field.
curl -X POST https://api.apimart.ai/v1/images/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-2",
"prompt": "A neon sign that reads OPEN 24/7 above a rainy Tokyo street at night",
"n": 1,
"size": "16:9",
"resolution": "2k"
}'import os
import time
import requests
API_BASE = "https://api.apimart.ai"
headers = {"Authorization": f"Bearer {os.environ['APIMART_API_KEY']}"}
# 1. Submit the generation task
payload = {
"model": "gpt-image-2",
"prompt": "A neon sign that reads OPEN 24/7 above a rainy Tokyo street at night",
"n": 1,
"size": "16:9",
"resolution": "2k"
}
resp = requests.post(f"{API_BASE}/v1/images/generations", headers=headers, json=payload, timeout=60)
resp.raise_for_status()
task_id = resp.json()["data"][0]["task_id"]
# 2. Poll the task until it finishes
for _ in range(200):
task_resp = requests.get(f"{API_BASE}/v1/tasks/{task_id}", headers=headers, timeout=30)
task_resp.raise_for_status()
task = task_resp.json()["data"]
if task["status"] == "completed":
print(task["result"]["images"][0]["url"][0])
break
if task["status"] == "failed":
raise RuntimeError(task.get("error", {}).get("message", "generation failed"))
time.sleep(3)
else:
raise TimeoutError(f"task {task_id} did not finish in time")curl -X POST https://api.apimart.ai/v1/images/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-2",
"prompt": "Place this product on a marble kitchen counter in soft morning light and keep the label text unchanged",
"n": 1,
"image_urls": [
"https://example.com/product.jpg"
],
"resolution": "2k"
}'TASK_ID="task_xxx" # replace with the task_id returned by the POST request
curl "https://api.apimart.ai/v1/tasks/$TASK_ID" \
-H "Authorization: Bearer $APIMART_API_KEY"| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Required | Default: gpt-image-2 | Model ID. Use gpt-image-2. |
prompt | string | Required | Default: — | Text description of the image, in English or Chinese. Prompts are moderated before submission. |
n | integer | Optional | Default: 1 | Number of images per request. Only 1 is supported; send it as a number, not a string. |
size | string | Optional | Default: 1:1 | Aspect ratio: auto, 1:1, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 16:9, 9:16, 2:1, 1:2, 3:1, 1:3, 21:9, 9:21, or a pixel size such as 1881x836. auto falls back to 1:1. |
resolution | string | Optional | Default: 1k | Output resolution tier: 1k, 2k or 4k. |
image_urls | array | Optional | Default: — | Up to 15 reference images as public URLs or base64 data URIs. Adding them switches GPT Image 2 to image-to-image editing. Max 20 MB per image and 256 MB in total. |
nsfw_check | boolean | Optional | Default: false | Moderate the prompt and input images before the task is submitted. |
official_fallback | boolean | Optional | Default: false | Set to true to use the official channel; false or omitted does not. |
Compare every GPT Image model on APIMart. One API key calls all of them; GPT Image 2.5 Flare and Sunburst share the same parameters and pricing.
| Model | Best for | Resolution / size |
|---|---|---|
| GPT Image 2.5 API | Flare and Sunburst on one page, with up to 16 reference images, masks and transparent backgrounds | 1K / 2K / 4K |
| GPT Image 2.5 Flare API | Fast everyday images, batch generation and rapid prototyping | 1K / 2K / 4K |
| GPT Image 2.5 Sunburst API | Precise edits for production assets, ad creatives and multi-turn editing | 1K / 2K / 4K |
| GPT Image 2 APIThis page | Text-to-image and editing with up to 16 reference images and 15 aspect ratios | 1K / 2K / 4K |
| GPT Image 1.5 API | Text-to-image and editing with up to 5 reference images and masks | 1:1 / 3:2 / 2:3 |
| GPT Image 1 API | Previous generation: text-to-image and editing with up to 5 reference images and masks | 1:1 / 3:2 / 2:3 |
Guides, comparisons and pricing analysis from the APIMart blog.
Next-generation GPT Image API for professional workflows
Transform workflows across industries
Follow these simple steps to set up your account, add funds, and start generating images
Create your free APIMart account to begin. One account unlocks every GPT Image model in the catalog.
Top up your account balance to get started. Your balance can be used across all models on the platform.
Create an access key in your console — you'll need it to authenticate every API request.
What developers and businesses say about GPT Image
“Text rendering is finally production-ready on GPT Image. Signage and UI labels sit inside scenes correctly — previous models always felt like stickers pasted on top.”
Chloe Evans
Digital Media Director
“Integration into our GPT Image workflow was seamless. Flexible parameters — no complex setup. Works with our existing tools without any technical hiccups.”
Henry Walker
Operations Manager
“The portraits have fooled three people in our team — hands, reflections, skin texture. GPT Image photorealism is a real step change, not a half-version bump.”
Bethany Cruz
Staff Engineer
“Native 4K output removes the upscale-and-repair step from our GPT Image marketing pipeline. We added it to our product in a single afternoon.”
Samantha Gray
Technical Lead
“World knowledge is where GPT Image pulls ahead. The GPT Image API draws real storefronts, app UIs, and game interfaces — not approximations. Less prompt engineering for faster iteration.”
Lucas Bennett
Marketing Analyst
“Native 4K output changes what kind of GPT Image product you can build. Print-ready key art, detailed UI mockups, on-demand ad variants — with no upscaling step in between.”
Michael Chen
CTO
Everything you need to know about GPT Image 2 and the GPT Image API
GPT Image 2 (also called GPT Image 2.0, model ID gpt-image-2) is OpenAI's image generation and editing model, built for complex visual work with stronger text rendering, layouts and instruction-following than earlier OpenAI image models. On APIMart you can call it with one API key and pay-as-you-go billing.
OpenAI released gpt-image-2 on April 21, 2026, making it available in the API and Codex alongside the launch of ChatGPT Images 2.0. Its successor, GPT Image 2.5 (Flare and Sunburst), is also available on APIMart.
It gives you OpenAI's GPT Image 2 model (model ID gpt-image-2) through APIMart. Send a text prompt with model, prompt and other optional parameters, and receive high-quality generated images — no complex configuration needed.
Compared with earlier GPT Image models, GPT Image 2 renders text inside images far more reliably (about 99% character-level accuracy on labels, UI and signage), outputs native 4K sizes such as 2880×2880 and 3840×2160 without upscaling, draws real brands, UIs and environments with deeper world knowledge, and follows complex prompts more closely. On APIMart you call it by setting model to gpt-image-2.
GPT Image 2 API requests need two fields: model (gpt-image-2) and prompt. Optional parameters are n (1 image per request), size (auto, 1:1, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 16:9, 9:16, 2:1, 1:2, 3:1, 1:3, 21:9, 9:21, or a pixel size such as 1881x836; default 1:1), resolution (1k, 2k or 4k; default 1k), image_urls (up to 15 reference images for image-to-image editing), nsfw_check and official_fallback. The parameter table on this page lists types and defaults.
Yes. Add reference images to the same POST /v1/images/generations request through image_urls (public URLs or base64 data URIs) and describe the change in the prompt. The Ext channel (gpt-image-2) accepts up to 15 images, the official channel (gpt-image-2-official) accepts up to 16 and also supports mask_url for inpainting. Each image can be up to 20 MB, with 256 MB in total.
Both call GPT Image 2 through the same POST /v1/images/generations endpoint with the same size and resolution options. gpt-image-2 (the Ext channel) returns 1 image per request, accepts up to 15 reference images and can switch to the official channel with official_fallback. gpt-image-2-official is OpenAI's official model and adds n from 1 to 4, quality (auto, low, medium, high), output_format (png, jpeg or webp, with transparent backgrounds in png and webp), moderation, up to 16 reference images and mask_url for inpainting. The two are billed separately; compare both in the live pricing table above.
Be specific about visual details (colors, lighting, composition), specify artistic style, and describe the scene clearly. The model's deep world knowledge means brand names, UI elements, and real environments render accurately when explicitly described.
Create an API key on APIMart, then send POST https://api.apimart.ai/v1/images/generations with model gpt-image-2, your prompt and optional size and resolution. The response returns a task_id: poll GET /v1/tasks/{task_id} until status is completed, then read the image URL from the result. Copy-ready cURL and Python examples are on this page, and the full GPT Image 2 API reference is in the APIMart docs (docs.apimart.ai).
The GPT Image 2 API is pay-as-you-go on APIMart, with no subscription, hidden fees or monthly minimums, and one balance works across every model. See this page's live pricing table for current rates: the prices shown are Gold member prices (20% off), and Platinum and Diamond members save up to 28%.
No. APIMart offers no free quota or free trial for the GPT Image 2 API. It is pay-as-you-go with no subscription: you only pay for successful requests, and every price is 20% off (Platinum and Diamond members save up to 28%). To check quality first, run a few paid requests in the Playground before scaling up.
Yes. Prices shown on this page are Gold member prices, already 20% off. Platinum and Diamond members save even more, up to 28%, and you only pay for successful requests.
Sign up for APIMart, open the API Keys page in your dashboard and create a new key. The same key calls the OpenAI GPT Image 2 API and every other model on the platform, with pay-as-you-go billing and no subscription.
GPT Image 2.0 and GPT Images 2 are common ways to refer to this OpenAI model, which APIMart serves as gpt-image-2. ChatGPT Images 2.0 is the image experience inside ChatGPT that OpenAI launched alongside it; developers reach the model through the API. If you searched for a ChatGPT Image 2 API or an image2 API (also written GPT-Image2 or GPT Image-2) to use in your own product, send model gpt-image-2 and your prompt with your APIMart API key.
Explore more models in the same category.

Qwen Image 2.0
Qwen-Image-2.0 is an AI image model that combines “generation and editing” capabilities, supports extremely long descriptions, and delivers high-quality 2K output. It is particularly well-suited for image creation that requires clear text and professional design aesthetics.

GPT Image 1 Official
GPT-Image-1 is an AI generative model that integrates text and image understanding, specializing in high-quality image creation and editing.

Qwen Image 2.0 Pro
Qwen-Image-2.0-Pro is the highest-fidelity variant of Alibaba’s Qwen image model, designed to generate and edit production-quality visuals from text or reference images. It delivers native 2K resolution with strong detail, accurate composition, and advanced text rendering, making it suitable for infographics, posters, and marketing assets. 

Grok Imagine 1.5 Ext(grok Imagine 1.5 Apimart)
Grok Imagine 1.5 (grok-imagine-1.5) is xAI's latest text-to-image model built for photorealistic detail and strong prompt adherence. It renders vivid, coherent scenes fast, and pairs with Grok Imagine's edit and image-to-video variants for a full creative workflow.