Skip to main content
gpt-image-2-c is the cost-effective variant of GPT Image 2, available through Anyfast API. It keeps GPT Image 2’s autoregressive + reasoning hybrid architecture — flexible resolution up to 4K and near-perfect text rendering — while supporting response_format and offering a lower price point. Unlike the official gpt-image-2, it does not support the n parameter (one image per request).

​
Key capabilities

  • Text-to-Image — Generate images from natural language descriptions
  • Image editing — Edit an existing image with a text prompt via /v1/images/edits
  • Flexible resolution — Any custom size up to 4K (3840px), edges must be multiples of 16
  • Near-perfect text rendering — ~99% character-level accuracy across 12+ languages
  • response_format support — Return generated/edited images as a pre-signed url or base64 (b64_json)
  • Cost-effective — A lower-cost alternative to gpt-image-2
gpt-image-2-c does not support the n parameter — each request returns a single image. For multi-image output (n), use gpt-image-2.

​
Output specifications

PropertyValue
SizesFlexible resolution (e.g. 1024x1024, 2048x2048, 3840x2160)
Size constraintsEdges: multiples of 16, aspect ratio ≤ 3:1, total pixels 655,360–8,294,400
Qualitylow, medium, high
Output formatspng, jpeg
Input formats (edits)png, jpeg

​
Quick example

curl https://www.anyfast.ai/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2-c",
    "prompt": "A futuristic city skyline at sunset with flying cars",
    "size": "2048x2048",
    "quality": "high",
    "response_format": "url"
  }'

​
Parameters

ParameterTypeRequiredDescription
modelstringYesMust be gpt-image-2-c
promptstringYesText description of the desired image
sizestringNo{width}x{height} format. Edges must be multiples of 16, aspect ratio ≤ 3:1, total pixels 655,360–8,294,400, max edge 3,840px. Default: 1024x1024
qualitystringNolow, medium, high. Default: medium
output_formatstringNopng, jpeg. Default: png
moderationstringNoauto or low. Default: auto
output_compressionintegerNoCompression level for jpeg (0–100).
response_formatstringNourl, b64_json. Default: url
gpt-image-2-c does not support the n parameter. To generate multiple images in one request, use gpt-image-2.

​
Image editing

Edit an existing image with a text prompt via POST /v1/images/edits. Use multipart/form-data and pass images as file uploads. Supports up to 16 input images per request (image[]).

​
Input image formats

Supported formats: PNG, JPEG. Images must be provided as multipart/form-data file uploads. 
curl https://www.anyfast.ai/v1/images/edits \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "image=@/path/to/source.jpeg" \
  -F model="gpt-image-2-c" \
  -F prompt="Change the background to a sunset over the ocean" \
  -F size="1024x1024"

​
Edit parameters

ParameterTypeRequiredDescription
imagefileYesSingle source image (PNG or JPEG, multipart upload)
image[]file arrayYes*Multiple source images — up to 16 images (PNG or JPEG). Use instead of image for multi-image input
maskfileNoMask image with an alpha channel. Same format and size as source (< 50MB). Applied to the first image when multiple images are provided. Requires selecting the Direct group.
modelstringYesMust be gpt-image-2-c
promptstringYesEdit instruction text
sizestringNo{width}x{height}. Default: 1024x1024
output_formatstringNopng, jpeg. Default: png
output_compressionintegerNoCompression level for jpeg (0–100)
response_formatstringNourl, b64_json. Default: url
Use either image (single file) or image[] (array) — not both.

​
Mask editing

Provide a mask image with an alpha channel to control which areas of the source image to edit. Pixels with white (opaque) alpha are preserved; pixels with black (transparent) alpha are edited. Requirements:
  • The mask must contain an Alpha channel
  • Must be the same image format and same dimensions as the source image
  • File size limit: < 50MB
Mask editing requires selecting the Direct group in the console.
cURL
curl https://www.anyfast.ai/v1/images/edits \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F image=@/path/to/source.jpeg \
  -F mask=@/path/to/mask.png \
  -F model="gpt-image-2-c" \
  -F prompt="Replace the background with a futuristic cityscape" \
  -F size="2048x2048"
If your mask is a black-and-white image without an alpha channel, convert it first:
Python
from PIL import Image
import numpy as np

img = Image.open("bw_mask.png").convert("L")
alpha = np.array(img)
rgba = np.zeros((*alpha.shape, 4), dtype=np.uint8)
rgba[alpha > 0] = [255, 255, 255, 255]
Image.fromarray(rgba).save("mask.png")

Generate API Reference

Interactive playground for POST /v1/images/generations.

Edit API Reference

Interactive playground for POST /v1/images/edits.