Loading…
base_url="https://api.codegateway.dev/v1" with your standard OpenAI SDK. Five lines to early image.Spec | Value |
|---|---|
Resolutions | 1024×1024, 1536×1024, 1024×1536 (1K); 2048×2048 (2K); 4096×4096 (4K) |
Output formats | JPEG, PNG, WebP |
Transparent background |
Image editing (inpainting) | Supported |
Batch generation | Up to 10 per request |
Official pricing | $0.011/image (low quality 1K) to $0.167/image (high quality 4K) |
Source: OpenAI API documentation (May 2026). Check OpenAI's pricing page for current rates.
CodeGateway multiplies official prices by the applicable tier rate (1.2x–1.5x). See CodeGateway pricing tiers.
pip install openaifrom openai import OpenAI
client = OpenAI(
api_key="your-codegateway-api-key",
base_url="https://api.codegateway.dev/v1"
)
response = client.images.generate(
model="gpt-image-2",
prompt="An orange cat sitting on a stack of books, reading under warm lamplight, watercolor illustration style",
n=1,
size="1024x1024"
)
image_url = response.data[0].url
print(f"Image URL: {image_url}") # Valid for 60 minutesimport base64
response = client.images.generate(
model="gpt-image-2",
prompt="Minimalist app UI screenshot, blue theme, clean white background",
n=1,
size="1024x1024",
quality="high",
output_format="png"
)
img_bytes = base64.b64decode(response.data[0].b64_json)
with open("output.png", "wb") as f:
f.write(img_bytes)
print("Saved to output.png")response = client.images.generate(
model="gpt-image-2",
prompt="Clean app icon representing a code gateway, deep blue, logo style",
n=1,
size="1024x1024",
quality="high",
output_format="png",
background="transparent" # requires PNG or WebP
)Value | Resolution | strong for |
|---|---|---|
| 1K square | Social media, avatars, product images |
| 1K landscape | Blog headers, website banners |
| 1K portrait | Phone wallpapers, posters |
| 2K square | Print-quality illustrations |
| 4K square | Ultra-high resolution (high cost) |
Value | Characteristics | Use when |
|---|---|---|
| Fast, less detail | Drafts, rapid iteration |
| Default, balanced | General commercial use |
| Highest detail, ~20–30s | Final product images, detailed illustrations |
Quality | Official price | CodeGateway (new user 1.5x) |
|---|---|---|
low | $0.011/image | $0.017 |
medium | $0.042/image | $0.063 |
high | $0.080/image | $0.120 |
Generating 100 medium-quality images per day: ~$190/month at new-user rate. Multiplier drops as cumulative spend grows — see tier pricing.
GPT-Image-2 supports text-guided inpainting — modify part of an existing image while keeping the rest intact.
import base64
with open("original.png", "rb") as f:
original_b64 = base64.b64encode(f.read()).decode()
with open("mask.png", "rb") as f:
mask_b64 = base64.b64encode(f.read()).decode()
response = client.images.edit(
model="gpt-image-2",
image=original_b64,
mask=mask_b64, # White = areas to replace; Black = keep as-is
prompt="Replace the background with a sunset beach scene",
n=1,
size="1024x1024"
)Mask format: PNG, same dimensions as the original. White pixels mark areas to regenerate; black pixels preserve the original.
response = client.images.generate(
model="gpt-image-2",
prompt="Data visualization dashboard, neon blue glow effect, dark background, tech aesthetic",
n=4, # 4 variations in one API call
size="1024x1024",
quality="medium"
)
for i, img in enumerate(response.data):
print(f"Variant {i+1}: {img.url}")Dimension | GPT-Image-2 | Imagen 4 |
|---|---|---|
Text rendering | Strong (accurate logo/poster text) | Weaker |
Photorealism | High | Very high (Imagen 4 Ultra) |
Artistic style range | Wide | Wide |
Transparent background | Supported | Not supported |
Image editing | Supported (inpainting) | Not supported (Standard/Fast) |
Lowest cost entry | $0.011/image (low quality) | Similar at Fast tier |
When to pick which:
Full comparison: Image Generation API Comparison: Imagen, Gemini, and GPT-Image.
Q: How long are generated image URLs valid?
A: A: 60 minutes. For persistent storage, request response_format="b64_json" and store the bytes yourself.
Q: Does GPT-Image-2 support non-English prompts?
A: A: Yes, including Chinese and most major languages. English prompts tend to give more precise control over stylistic nuances.
Q: How fast is generation?
A: A: Low quality: 5–10s. Medium: 10–20s. High: 20–40s. Server load and network conditions vary.
Q: Can it generate faces?
A: A: Yes, with OpenAI's standard content policy applied. Generating likenesses of specific real people is rejected.
Q: Can I reuse an OpenAI API key with CodeGateway?
A: A: No — CodeGateway API keys work only with base_url="https://api.codegateway.dev/v1". They're separate credentials.