# GPT Image 1.5

> OpenAI's state-of-the-art image generation model with better instruction following and adherence to prompts

## Quick Reference

- Model ID: gpt-image-1.5
- Creator: OpenAI
- Status: active
- Family: gpt-image
- Base URL: https://api.lumenfall.ai/openai/v1

## Specifications

- Max Resolution: 1536x1536
- Max Output Images: 1
- Max Input Images: 10
- Input Modalities: text, image
- Output Modalities: image
- Supported Modes: Text to Image, Image Edit

## API Parameters

The compiled parameter schema for this model is available via the API: `GET /v1/models/gpt-image-1.5?schema=true`.

### Core Parameters

- `prompt` (string) — REQUIRED: Text prompt for image generation. Modes: Text to Image, Image Edit
- `quality` (string): Image quality level. Values: high, low, medium. Modes: Text to Image

### Size & Layout

- `size` (string): Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9"). Values: 1254x836, 836x1254, 1024x1024, 1536x1024, 1024x1536. Modes: Text to Image, Image Edit
- `aspect_ratio` (string): Aspect ratio of the output image (e.g. "16:9", "1:1"). Values: 2:3, 1:1, 3:2. Modes: Text to Image, Image Edit
- `resolution` (string): Output resolution tier (e.g. "1K", "4K"). Values: 1K. Modes: Text to Image, Image Edit

### Media Inputs

- `image` (file) — REQUIRED: Input image(s) to edit. Modes: Image Edit

### Output & Format

- `response_format` (string): How to return the image. Default: url. Values: url, b64_json. Modes: Text to Image, Image Edit
- `output_format` (string): Output image format. Values: png, jpeg, gif, webp, avif. Modes: Text to Image, Image Edit
- `output_compression` (integer): Compression level (0-100%). Default: 90. Modes: Text to Image, Image Edit. Only available via replicate
- `n` (integer): Number of images to generate. Default: 1. Modes: Text to Image, Image Edit

### Additional Parameters

- `background` (string): Background for the generated image. Values: opaque, transparent. Modes: Text to Image, Image Edit
- `input_fidelity` (string): Input fidelity for the generated image. Values: high, low. Modes: Image Edit, Text to Image
- `mask_image_url` (string): The URL of the mask image to use for the generation. This indicates what part of the image to edit.. Modes: Image Edit. Only available via fal
- `moderation` (string): Content moderation level. Values: low. Modes: Text to Image, Image Edit. Only available via replicate
- `openai_api_key` (string): Your OpenAI API key (optional - uses proxy if not provided). Modes: Text to Image, Image Edit. Only available via replicate
- `sync_mode` (boolean): If `True`, the media will be returned as a data URI and the output data won't be available in the request history.. Modes: Text to Image, Image Edit. Only available via fal
- `user_id` (string): An optional unique identifier representing your end-user. This helps OpenAI monitor and detect abuse.. Modes: Text to Image, Image Edit. Only available via replicate


## Model Identifiers

- Primary Slug: gpt-image-1.5


## Tags

image-generation, text-to-image, image-editing

## Available Providers

### OpenAI

- Config Key: openai/gpt-image-1.5
- Provider Model ID: gpt-image-1.5
- Pricing: $5.00/M input tokens, $1.25/M input tokens, $8.00/M input tokens (image), $2.00/M input tokens (image), $10.00/M output tokens, $32.00/M output tokens (image), $0.0090/image, $0.013/image, $0.013/image, $0.034/image, $0.050/image, $0.050/image, $0.133/image, $0.200/image, $0.200/image
  - Note: Pricing available in both token-based and per-image formats
  - Note: Per-image prices vary by quality (low/medium/high) and size
  - Note: Supports up to 10 input images; first 5 preserved with higher fidelity
  - Source: https://platform.openai.com/docs/pricing

### fal.ai

- Config Key: fal/gpt-image-1.5
- Provider Model ID: fal-ai/gpt-image-1.5
- Pricing: $0.0090/image, $0.013/image, $0.013/image, $0.034/image, $0.051/image, $0.050/image, $0.133/image, $0.200/image, $0.199/image
  - Note: Per-image prices vary by quality (low/medium/high) and size
  - Source: https://fal.ai/models/fal-ai/gpt-image-1.5

### fal.ai

- Config Key: fal/gpt-image-1.5-edit
- Provider Model ID: fal-ai/gpt-image-1.5/edit
- Pricing: $0.0090/image, $0.013/image, $0.013/image, $0.034/image, $0.051/image, $0.050/image, $0.133/image, $0.200/image, $0.199/image
  - Note: Per-image prices vary by quality (low/medium/high) and size
  - Source: https://fal.ai/models/fal-ai/gpt-image-1.5

### Replicate

- Config Key: replicate/gpt-image-1.5
- Provider Model ID: openai/gpt-image-1.5
- Pricing: $0.013/image, $0.050/image, $0.136/image
  - Note: Per-image prices vary by quality level
  - Source: https://replicate.com/openai/gpt-image-1.5


## Performance Metrics

Provider performance over the last 30 days.

### replicate

- Median Generation Time (p50): 37600ms
- 95th Percentile Generation Time (p95): 52967ms
- Average Generation Time: 34292ms
- Success Rate: 95.8%
- Total Requests: 24
- Time to First Byte (p50): 37600ms
- Time to First Byte (p95): 53353ms

### openai

- Median Generation Time (p50): 42701ms
- 95th Percentile Generation Time (p95): 59687ms
- Average Generation Time: 39273ms
- Success Rate: 61.4%
- Total Requests: 386
- Time to First Byte (p50): 41987ms
- Time to First Byte (p95): 55295ms

### fal

- Median Generation Time (p50): 49948ms
- 95th Percentile Generation Time (p95): 79316ms
- Average Generation Time: 53107ms
- Success Rate: 100.0%
- Total Requests: 24
- Time to First Byte (p50): 49847ms
- Time to First Byte (p95): 77822ms


## Arena Benchmarks

### Man and Car in California

- Elo: 1291
- Record: 40W / 28L / 1T (69 battles)
- Rank: #1 of 13

### Neutral Expression to Genuine Smile

- Elo: 1285
- Record: 20W / 6L / 4T (30 battles)
- Rank: #2 of 14

### Vintage Cafe Logo

- Elo: 1272
- Record: 14W / 5L / 0T (19 battles)
- Rank: #1 of 21

### Victorian Greenhouse Oasis

- Elo: 1267
- Record: 14W / 10L / 1T (25 battles)
- Rank: #2 of 17

### Modern Clean Menu

- Elo: 1261
- Record: 27W / 1L / 3T (31 battles)
- Rank: #2 of 19

### Over-the-top cartoon caricature

- Elo: 1251
- Record: 16W / 6L / 4T (26 battles)
- Rank: #2 of 13

### Night Sky Transformation

- Elo: 1248
- Record: 25W / 17L / 7T (49 battles)
- Rank: #2 of 16

### Adorable Baby Animals in Sunny Meadow

- Elo: 1227
- Record: 20W / 3L / 0T (23 battles)
- Rank: #3 of 25

### Golden Hour Stroll

- Elo: 1222
- Record: 20W / 6L / 0T (26 battles)
- Rank: #3 of 13

### Fantasy Warrior

- Elo: 1218
- Record: 14W / 6L / 1T (21 battles)
- Rank: #8 of 21

### Heroic Super Hero Portrait

- Elo: 1207
- Record: 18W / 5L / 2T (25 battles)
- Rank: #6 of 21

### Apollo 11: Journey to Tranquility

- Elo: 1205
- Record: 17W / 6L / 1T (24 battles)
- Rank: #7 of 19

### Geometric Composition

- Elo: 1185
- Record: 25W / 20L / 11T (56 battles)
- Rank: #10 of 22

### Studio Ghibli Anime Style

- Elo: 1183
- Record: 9W / 19L / 1T (29 battles)
- Rank: #12 of 14

### Bald man challenge

- Elo: 1181
- Record: 17W / 14L / 1T (32 battles)
- Rank: #11 of 15

### Candid Street Photography

- Elo: 1174
- Record: 15W / 5L / 0T (20 battles)
- Rank: #11 of 24

### Intricate Floral Mandala

- Elo: 1145
- Record: 8W / 11L / 6T (25 battles)
- Rank: #13 of 15

### Fantasy Warrior

- Elo: 1126
- Record: 4W / 0L / 0T (4 battles)
- Rank: #4 of 14


## Use Cases & Category Performance

### Text Rendering (Text-to-Image)

- Rank: #2 of 23
- Elo: 1289
- Record: 58W / 11L / 2T (71 battles)
- Win Rate: 81.7%

### Photorealism (Text-to-Image)

- Rank: #2 of 23
- Elo: 1246
- Record: 14W / 4L / 0T (18 battles)
- Win Rate: 77.8%

### Photorealism (Image Editing)

- Rank: #2 of 16
- Elo: 1254
- Record: 117W / 68L / 13T (198 battles)
- Win Rate: 59.1%

### Portrait (Text-to-Image)

- Rank: #3 of 21
- Elo: 1229
- Record: 14W / 4L / 1T (19 battles)
- Win Rate: 73.7%

### Product, Branding & Commercial (Text-to-Image)

- Rank: #3 of 21
- Elo: 1240
- Record: 14W / 5L / 0T (19 battles)
- Win Rate: 73.7%

### Portrait (Image Editing)

- Rank: #5 of 15
- Elo: 1249
- Record: 35W / 17L / 5T (57 battles)
- Win Rate: 61.4%

### Anime (Image Editing)

- Rank: #13 of 14
- Elo: 1166
- Record: 9W / 19L / 1T (29 battles)
- Win Rate: 31.0%


## Image Gallery

23 images available for this model. Browse all at https://lumenfall.ai/models/openai/gpt-image-1.5/gallery

### Curated Examples

- [A grand, cinematic wide-shot of a high-end, sun-drenched European atelier where a master artisan ...](https://assets.lumenfall.ai/teWZuRteykrmNNbx2tXkR_IVPTNn4niZvmNEVhNYYW8/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/smrqb2wbhk0i4u4ohelcgqbob0og@jpeg)
- [A wide, cinematic shot of a sophisticated high-end creative studio during golden hour. In the cen...](https://assets.lumenfall.ai/T08LMy0sG1j1-vR6PZjsvlQmFYC2F1Fi2zhvkC3JNL4/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/p6o5jhryr41ejft9r01zi52ayevw@jpeg)
- [A hyper-realistic close-up of a weathered craftsman's workbench, featuring a handheld vintage mag...](https://assets.lumenfall.ai/4g8lZ8fKqZ-Bm0BPi-DrHvy3yj3bSlYeEMZlGf0bvTI/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/w365avze8but6543t5sokt4q7nsh@jpeg)
- [A hyper-realistic cinematic close-up of an elderly watchmaker’s workspace, sunlight streaming thr...](https://assets.lumenfall.ai/xussVA3TPkntJc1gxhE0Y7vpYU8OCpsfU3VaQ2QJnOw/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/v589ktalgmr1mise6k0ccpqfz7wi@jpeg)
- [A charming neighborhood bakery called "THE GOLDEN CRUST" with elegant gold lettering on the windo...](https://assets.lumenfall.ai/J9WtKkMYTGBdF8OOSuP0Mxsrr0X94Kt0s184_D1oEEQ/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/xumd0mr0pg6e4ewcte2x5xiqh1im@jpeg)

### Arena Competition Results

- [Man and Car in California](https://assets.lumenfall.ai/gxt4ZuiCSO3stPFe3OUO9nFYfMBwXIXO9GXlbDUGZLc/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/fyuw6a7zp2625oefdeeio4iaqnn8@jpeg): #1 of 13 (Elo 1291)
- [Neutral Expression to Genuine Smile](https://assets.lumenfall.ai/6uum-wJILbd6YFnxYs3AI7MEMQeLRG606K7l5Zz2VW4/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/msbmb21081kcovjh3iwytqbwcbic@jpeg): #2 of 14 (Elo 1285)
- [Vintage Cafe Logo](https://assets.lumenfall.ai/mJE-0j26onGfa54M4UCmhXOSZKw32cH03G_eqSbKojM/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/giap3nyex4k9n8t6xoogbdzwig68@jpeg): #1 of 21 (Elo 1272)
- [Victorian Greenhouse Oasis](https://assets.lumenfall.ai/ixEYDInF_qBkgmyJSOTmgfALdkDheKRsyJdy0DzX8qY/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/hirpu16uqafb393p1tqsmfw9wrxe@jpeg): #2 of 17 (Elo 1267)
- [Modern Clean Menu](https://assets.lumenfall.ai/2sbCAwTO-Ju0Esq7plfIhq6N1PiJ6rAPKndADUCsfRM/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/vx00kl6lx8vfhlw7hg2h8tq0n52h@jpeg): #2 of 19 (Elo 1261)
- [Over-the-top cartoon caricature](https://assets.lumenfall.ai/ss_vhmLT_ogYrvSZDoprcAYCyD--mXJOeduD9O1YbNc/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/bcm2hdio0kjyihq3mvd2sj156hvm@jpeg): #2 of 13 (Elo 1251)
- [Night Sky Transformation](https://assets.lumenfall.ai/SBMAxPXGL4YoAKRGyBINmj24mi-FVMDmCDpf-0NKfQM/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/ee4j6a5axz15bl3aotipebqd6qep@jpeg): #2 of 16 (Elo 1248)
- [Adorable Baby Animals in Sunny Meadow](https://assets.lumenfall.ai/AaXeecYQJtiSJVMQYusqgzTBF4t4YVLMDMlJj4IHepc/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/k9aqr1qr9s9lojm1y3nmnv6e0x18@jpeg): #3 of 25 (Elo 1227)
- [Golden Hour Stroll](https://assets.lumenfall.ai/x43dqo_1iRISPA5UVWncFHMrT9u637t9dlG7aD8NfYs/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/bbtd9i2vnpnuos86r5tbba2w4202@jpeg): #3 of 13 (Elo 1222)
- [Fantasy Warrior](https://assets.lumenfall.ai/9mv6w0AXfPFlWl2vJhWjL4Vbf4YC0MrfZYADEz9Qykg/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/xktceo1nvx53uh3huuawoft005dx@jpeg): #8 of 21 (Elo 1218)
- [Heroic Super Hero Portrait](https://assets.lumenfall.ai/h-WWlFSxrK-C16BVLOht-UyU9ZbW2XSGRAIruKcPr84/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/bxjbk2d31vqeetuytui54scatkwb@jpeg): #6 of 21 (Elo 1207)
- [Apollo 11: Journey to Tranquility](https://assets.lumenfall.ai/9O2-Auey-ZzPYvWjzpnA5rF9u3pHFIBnPNP13zcmvF0/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/hvt8uwhywaokn7y0ym7sc1vmsau2@jpeg): #7 of 19 (Elo 1205)
- [Geometric Composition](https://assets.lumenfall.ai/FKiJGTv0yOlNPWZX1G0EFNUhWMRcRSSFuRLqWF5AdeE/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/wwclvmmkm9g6vm3dlvzhiz70cj0j@jpeg): #10 of 22 (Elo 1185)
- [Studio Ghibli Anime Style](https://assets.lumenfall.ai/U6nKJGsIMzsaj0CjdgcVmfnrry-KUxoOVKBSpbSLqUo/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/iwq0zlzmlvvi9ck1jsxd4d4qw8n2@jpeg): #12 of 14 (Elo 1183)
- [Bald man challenge](https://assets.lumenfall.ai/0uwRgJgG0UBIqpeX88arJb76wpqCxVPXtR1_I9p35rg/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/283wjarnggsjmm24o1wbwp1zbg4t@jpeg): #11 of 15 (Elo 1181)
- [Candid Street Photography](https://assets.lumenfall.ai/uf3p_VKqstwJ_Pg2O43I3YpFN5du-Lk9a9qCDG942hc/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/lb0gfvfdx60quqt8fgatt5y0oh41@jpeg): #11 of 24 (Elo 1174)
- [Intricate Floral Mandala](https://assets.lumenfall.ai/TD9BqFhY_ZeN-zPG82SWOb6MFEU4lZxE1HU99WozN74/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/ubvewanwd9awnxnu1akujul40szx@jpeg): #13 of 15 (Elo 1145)
- [Fantasy Warrior](https://assets.lumenfall.ai/QoEjMQqHBm9XDbhLKmwL5jd7V3eBwmlpKn_-sdUagcI/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/ro09jx78xrzvxk75pxwtqkpsc5ky@jpeg): #4 of 14 (Elo 1126)

## Example Prompt

The following prompt was used to generate an example image in our playground:

A charming neighborhood bakery called "THE GOLDEN CRUST" with elegant gold lettering on the window. Inside, a baker holds a fresh sourdough loaf. On the sidewalk, a capybara waits patiently by the door next to a wooden chalkboard sign.

## Code Examples

### Text to Image (/v1/images/generations)

#### cURL

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-1.5",
    "prompt": "",
    "size": "1024x1024"
  }'

# Response:
# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

#### JavaScript

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-1.5',
  prompt: '',
  size: '1024x1024'
});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
console.log(response.data[0].url);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.generate(
    model="gpt-image-1.5",
    prompt="",
    size="1024x1024"
)

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)

### Image Edit (/v1/images/edits)

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/edits \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -F "model=gpt-image-1.5" \
  -F "image=@source.png" \
  -F "prompt=Add a starry night sky to this image" \
  -F "size=1024x1024"

# Response:
# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

#### JavaScript

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-1.5',
  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);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.edit(
    model="gpt-image-1.5",
    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)


## About

## Overview
GPT Image 1.5 is OpenAI’s latest flagship image generation model, designed to transform complex text descriptions into high-fidelity visual assets. It represents a significant iteration in the GPT-image family, focusing on narrowing the gap between user intent and generated output. The model is distinctive for its high level of steerability, allowing users to define specific spatial arrangements and intricate details that previous iterations often elided.

## Strengths
*   **Complex Instruction Following:** The model excels at parsing long, multi-part prompts, ensuring that every requested element is present in the final composition without losing track of secondary details.
*   **Spatial and Relational Accuracy:** It maintains high consistency when placing objects in specific locations (e.g., "in the bottom left corner") or defining relationships between subjects (e.g., "leaning against" or "half-obscured by").
*   **Text Rendering Accuracy:** GPT Image 1.5 shows marked improvement in rendering legible, correctly spelled text within images, making it suitable for graphic design mockups and signage.
*   **Diverse Aspect Ratios:** Unlike earlier generative models restricted to square outputs, this model natively supports a wide range of aspect ratios while maintaining structural integrity and avoiding anatomical distortion.

## Limitations
*   **Photorealistic Nuance:** While highly capable, it may still struggle with specific "uncanny valley" effects in human skin textures or micro-expressions compared to specialized diffusion models tuned specifically for photography.
*   **Prompt Literalism:** Because the model prioritizes strict adherence to instructions, it can occasionally lack the "artistic flair" or unexpected creativity found in models that interpret prompts more loosely.
*   **Inference Latency:** Given the complexity of the architecture required to achieve high instruction following, generation times may be slightly higher than smaller, distilled latent diffusion models.

## Technical Background
GPT Image 1.5 is built upon a transformer-based diffusion architecture, leveraging OpenAI’s advancements in large-scale multimodal pre-training. By utilizing a sophisticated text encoder similar to those found in the GPT-4 family, the model can internalize nuanced semantic meanings before translating them into the visual latent space. This architecture enables the model to treat image generation as a sequence-informed task, improving the alignment between the text tokens and the resulting pixels.

## Best For
GPT Image 1.5 is ideal for professional workflows including advertising concept art, architectural visualization, and detailed character design where precision is non-negotiable. Its ability to follow strict formatting makes it a strong candidate for automated content pipelines and social media asset generation. 

You can experiment with GPT Image 1.5 and compare its outputs with other top-tier models through the Lumenfall playground or integrate it into your production environment using the Lumenfall unified API.

## Frequently Asked Questions

### How much does GPT Image 1.5 cost?

GPT Image 1.5 starts at $0.009 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

### How do I use GPT Image 1.5 via API?

You can use GPT Image 1.5 through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "gpt-image-1.5". Code examples are available in Python, JavaScript, and cURL.

### Which providers offer GPT Image 1.5?

GPT Image 1.5 is available through OpenAI, fal.ai, and Replicate on Lumenfall. Lumenfall automatically routes requests to the best available provider.

### What is the maximum resolution for GPT Image 1.5?

GPT Image 1.5 supports images up to 1536x1536 resolution.

## Links

- Model Page: https://lumenfall.ai/models/openai/gpt-image-1.5
- About: https://lumenfall.ai/models/openai/gpt-image-1.5/about
- Providers, Pricing & Performance: https://lumenfall.ai/models/openai/gpt-image-1.5/providers
- API Reference: https://lumenfall.ai/models/openai/gpt-image-1.5/api
- Benchmarks: https://lumenfall.ai/models/openai/gpt-image-1.5/benchmarks
- Use Cases: https://lumenfall.ai/models/openai/gpt-image-1.5/use-cases
- Gallery: https://lumenfall.ai/models/openai/gpt-image-1.5/gallery
- Playground: https://lumenfall.ai/playground?model=gpt-image-1.5
- API Documentation: https://docs.lumenfall.ai