AI Image Editing Model
OpenAI's state-of-the-art image generation model with arbitrary resolution up to 4K and strong instruction following
gpt-image-2
Starting from
Prices shown are in USD · Some prices estimated from per-megapixel or per-token pricing
Full pricing detailsFastest generation through openai at 71,008ms median latency with 98.8% success rate.
Aggregated from real API requests over the last 30 days.
| # | Provider | p50 Gen Time | p95 Gen Time | Success Rate | TTFB (p50) |
|---|---|---|---|---|---|
| 1 | openai | 71,008ms | 169,801ms | 98.8% | 68,058ms |
GPT Image 2 is available exclusively through OpenAI, starting at $0.0387/image.
openai/gpt-image-2
https://api.lumenfall.ai/openai/v1
gpt-image-2
curl -X POST \ https://api.lumenfall.ai/openai/v1/images/generations \ -H "Authorization: Bearer $LUMENFALL_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-image-2", "prompt": "", "size": "1024x1024" }'# Response:# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }import OpenAI from 'openai';const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://api.lumenfall.ai/openai/v1'});const response = await client.images.generate({ model: 'gpt-image-2', prompt: '', size: '1024x1024'});// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }console.log(response.data[0].url);from openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://api.lumenfall.ai/openai/v1")response = client.images.generate( model="gpt-image-2", prompt="", size="1024x1024")# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }print(response.data[0].url)curl -X POST \ https://api.lumenfall.ai/openai/v1/images/edits \ -H "Authorization: Bearer $LUMENFALL_API_KEY" \ -F "model=gpt-image-2" \ -F "[email protected]" \ -F "prompt=Add a starry night sky to this image" \ -F "size=1024x1024"# Response:# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }import OpenAI from 'openai';import fs from 'fs';const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://api.lumenfall.ai/openai/v1'});const response = await client.images.edit({ model: 'gpt-image-2', image: fs.createReadStream('source.png'), prompt: 'Add a starry night sky to this image', size: '1024x1024'});// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }console.log(response.data[0].url);from openai import OpenAIclient = OpenAI( api_key="YOUR_API_KEY", base_url="https://api.lumenfall.ai/openai/v1")response = client.images.edit( model="gpt-image-2", image=open("source.png", "rb"), prompt="Add a starry night sky to this image", size="1024x1024")# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }print(response.data[0].url)| Parameter | Type | Description | Modes |
|---|---|---|---|
prompt
|
string | Required. Text prompt for image generation |
T2I
Edit
|
quality
|
string |
Image quality level
high
low
medium
|
T2I
Edit
|
| Parameter | Type | Description | Modes |
|---|---|---|---|
size
|
string |
Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9")
WxH determines both shape and scale (aspect_ratio and resolution are ignored when size is provided). W:H format is equivalent to aspect_ratio.
|
T2I
Edit
|
aspect_ratio
|
string |
Aspect ratio of the output image (e.g. "16:9", "1:1")
Controls shape independently of scale. Use with resolution to control both. If size is also provided, size takes precedence. Any ratio is accepted and mapped to the nearest supported value.
|
T2I
Edit
|
resolution
|
string |
Output resolution tier (e.g. "1K", "4K")
Controls scale independently of shape. Higher tiers produce larger images and cost more. If size is also provided, size takes precedence for scale. Any tier is accepted and mapped to the nearest supported value.
|
T2I
Edit
|
size
Exact pixel dimensions
"1920x1080"
aspect_ratio
Shape only, default scale
"16:9"
resolution
Scale tier, preserves shape
"1K"
size is most specific and always wins. aspect_ratio and resolution control shape and scale independently.
7:1 on a model with
4:1 and 8:1,
you get 8:1.
0.5K 1K 2K 4K)
or megapixel tiers (0.25 1).
If the exact tier isn't available, you get the nearest one.
| Parameter | Type | Description | Modes |
|---|---|---|---|
image
|
file |
Required.
Input image(s) to edit
Supports PNG, JPEG, WebP.
Up to 10 images per request.
|
T2I
Edit
|
| Parameter | Type | Description | Modes |
|---|---|---|---|
response_format
|
string |
How to return the image
url
b64_json
Default:
"url" |
T2I
Edit
|
output_format
|
string |
Output image format
png
jpeg
gif
webp
avif
Gateway converts to requested format if provider doesn't support it natively.
|
T2I
Edit
|
output_compression
|
integer | Compression level for lossy formats (JPEG, WebP, AVIF) |
T2I
Edit
|
n
|
integer |
Number of images to generate
Default:
1Gateway generates multiple images in parallel even if provider only supports 1.
|
T2I
Edit
|
Provider-specific passthrough fields, available only when the request is routed to the listed provider.
| Parameter | Type | Description | Modes |
|---|---|---|---|
|
openai
|
|||
background
|
string |
Background handling. gpt-image-2 does not currently support transparent backgrounds.
opaque
|
T2I
Edit
|
moderation
|
string |
Moderation strictness.
low
|
T2I
Edit
|
user
|
string | Stable end-user identifier used by OpenAI abuse monitoring. |
T2I
Edit
|
How we handle parameters across different providers
Not every provider speaks the same language. When you send a parameter, we handle it in one of four ways depending on what the model supports:
| Behavior | What happens | Example |
|---|---|---|
passthrough |
Sent as-is to the provider | style, quality |
renamed |
Same value, mapped to the field name the provider expects | prompt |
converted |
Transformed to the provider's native format | size |
emulated |
Works even if the provider has no concept of it | n, response_format |
Parameters we don't recognize pass straight through to the upstream API, so provider-specific options still work.
GPT Image 2 is ranked #4 in Text-to-Image with an Elo of 1277 and #5 in Image Editing with an Elo of 1218 on the Lumenfall Arena, where real users pick the better image in blind comparisons. These rankings are based on 6 blind-vote competitions.
1 model without pricing omitted.
7 models waiting for enough speed data.
1 model without pricing omitted.
1 model waiting for enough speed data.
“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”
“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”
“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
“Use Image 1 as the exact pose reference and Image 2 as the character reference. Recreate the person/character from Image 2 in the exact dynamic pose and body position from Image 1. Keep the exact face, hair, clothing style/details, and expression from Image 2. Match the lighting and environment of Image 1. The final image must show the character from Image 2 performing the precise action/pose from Image 1 with perfect anatomy and natural integration.”
“Use Image 1 as the base person. Dress them in the exact elaborate outfit from Image 2 (including all layers, accessories, jewelry, and shoes). Carefully adapt the clothing to the body shape and pose in Image 1 while maintaining realistic fabric behavior, correct proportions, and perfect lighting/shadow matching. Keep the person’s exact face, hair, and background completely unchanged.”
“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”
“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”
“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”
“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”
“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”
“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”
“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
“Use Image 1 as the base person. Dress them in the exact elaborate outfit from Image 2 (including all layers, accessories, jewelry, and shoes). Carefully adapt the clothing to the body shape and pose in Image 1 while maintaining realistic fabric behavior, correct proportions, and perfect lighting/shadow matching. Keep the person’s exact face, hair, and background completely unchanged.”
“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”
“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”
“Use Image 1 as the exact pose reference and Image 2 as the character reference. Recreate the person/character from Image 2 in the exact dynamic pose and body position from Image 1. Keep the exact face, hair, clothing style/details, and expression from Image 2. Match the lighting and environment of Image 1. The final image must show the character from Image 2 performing the precise action/pose from Image 1 with perfect anatomy and natural integration.”
“Use Image 1 as the base person. Dress them in the exact elaborate outfit from Image 2 (including all layers, accessories, jewelry, and shoes). Carefully adapt the clothing to the body shape and pose in Image 1 while maintaining realistic fabric behavior, correct proportions, and perfect lighting/shadow matching. Keep the person’s exact face, hair, and background completely unchanged.”
“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
“Use Image 1 as the base person. Dress them in the exact elaborate outfit from Image 2 (including all layers, accessories, jewelry, and shoes). Carefully adapt the clothing to the body shape and pose in Image 1 while maintaining realistic fabric behavior, correct proportions, and perfect lighting/shadow matching. Keep the person’s exact face, hair, and background completely unchanged.”
“Use Image 1 as the exact pose reference and Image 2 as the character reference. Recreate the person/character from Image 2 in the exact dynamic pose and body position from Image 1. Keep the exact face, hair, clothing style/details, and expression from Image 2. Match the lighting and environment of Image 1. The final image must show the character from Image 2 performing the precise action/pose from Image 1 with perfect anatomy and natural integration.”
“Use Image 1 as the base person. Dress them in the exact elaborate outfit from Image 2 (including all layers, accessories, jewelry, and shoes). Carefully adapt the clothing to the body shape and pose in Image 1 while maintaining realistic fabric behavior, correct proportions, and perfect lighting/shadow matching. Keep the person’s exact face, hair, and background completely unchanged.”
“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”
“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”
“Use Image 1 as the exact pose reference and Image 2 as the character reference. Recreate the person/character from Image 2 in the exact dynamic pose and body position from Image 1. Keep the exact face, hair, clothing style/details, and expression from Image 2. Match the lighting and environment of Image 1. The final image must show the character from Image 2 performing the precise action/pose from Image 1 with perfect anatomy and natural integration.”
See how GPT Image 2 performs head-to-head against other AI models, ranked by community votes in blind comparisons.
GPT Image 2 starts at $0.0387 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.
You can use GPT Image 2 through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "gpt-image-2". Code examples are available in Python, JavaScript, and cURL.
GPT Image 2 is available through OpenAI on Lumenfall. Lumenfall automatically routes requests to the best available provider.
GPT Image 2 supports images up to 3840x2160 resolution.
GPT Image 2 is a high-fidelity image generation model developed by OpenAI, designed to produce visual content from text prompts and existing images. It represents an evolution in the GPT-image family, characterized by its ability to handle arbitrary resolutions up to 4K and its rigorous adherence to complex, multi-part instructions. This model supports both text-to-image generation and granular image editing, allowing users to move from initial concept to refined final asset within a single framework.
GPT Image 2 is built upon OpenAI’s proprietary architecture for visual synthesis, moving beyond fixed-aspect ratio training to support dynamic resolution scaling. The model utilizes a training approach that emphasizes the alignment between dense textual descriptions and high-resolution visual tokens. This allows the model to interpret nuanced natural language prompts as precise spatial and stylistic commands during the generation process.
GPT Image 2 is optimized for professional workflows requiring high-definition assets, such as marketing collateral, detailed concept art, and complex photo manipulation. It is particularly effective for users who need to iterate on an existing image through precise text-based edits rather than regenerating a scene from scratch. This model is available for integration and testing through Lumenfall’s unified API and playground, providing a streamlined environment for experimenting with 4K generation and image editing.
Generate images with custom prompts — no API key needed.
