Text to image
Elo · text-to-image arena
GPT Image 1.5 overview
GPT Image 1.5 by OpenAI
GPT Image 1.5 is OpenAI’s image generation model, built to produce crisp images that closely follow your prompt and to support dependable editing and variations.
GPT Image 1.5 specs
- Model ID
openai/gpt-image-1-5- Developer
- OpenAI
- Input
- Text, Image
- Output
- Image
- Endpoint
POST https://api.aimlapi.com/v1/images/generations
Fast, controllable image generation that actually follows the brief
GPT Image 1.5 is OpenAI’s latest image-generation model available via the OpenAI API, designed for teams that need repeatable outputs and editable images inside real products, not just one-off creations. OpenAI positions it around stronger instruction-following, better edit preservation (composition/lighting/detail), and faster generation for tighter iteration loops.
If you’re building an “image tool” into your app – brand creatives, product shots, marketing variants, game assets, avatars, UI illustrations, or content automation, GPT Image 1.5 is built to behave like an API-first creative engine: predictable, controllable, and scalable.
Stronger prompt adherence (less prompt wrestling)
GPT Image 1.5 is explicitly optimized for better instruction following and adherence to prompts, which is crucial when you need layouts, constraints, and consistent outputs across many generations.
Faster generation for higher throughput
Rollout coverage highlights major speed gains (often summarized as “up to ~4× faster”), which matters when your workflow is “generate → adjust → regenerate” at scale.
Editing that preserves what matters
OpenAI’s positioning emphasizes edits that keep identity, lighting, and composition stable across changes, useful for iterative production (swap background, update wardrobe, reframe, adjust style) without visual drift.
API controls and limitations
GPT Image 1.5 supports practical controls that map to real product needs:
- Sizes: 1024x1024, 1536x1024 (landscape), 1024x1536 (portrait), or auto
- Quality: high, medium, low, or auto
- Output format: png, jpeg, webp
- Compression: output_compression from 0–100
- Transparency: background = transparent, opaque, or auto
- Streaming + partial images: stream plus partial_images (0–3) for perceived latency improvements
GPT Image 1.5 vs Black Forest Labs FLUX.2
GPT Image 1.5 focuses on fast, prompt-driven generation with strong support for readable text, UI-style graphics, and tight integration into the OpenAI and Microsoft ecosystems, making it easier to drop into existing apps and enterprise pipelines. FLUX.2, by contrast, is an open-weight, locally deployable model that emphasizes high-end photographic realism and advanced features like multi-image conditioning, but it typically demands more setup, tuning, and tooling knowledge to get consistent results.
Use cases
GPT Image 1.5 benchmarks by 
Artificial Analysis
Human-preference results for GPT Image 1.5 in text to image, next to models available on AI/ML API. Data retrieved Nov 3, 2026.
Models on AI/ML API
Arena results for models you can call with the same API key.
Text to image
Blind pairwise human votes on images generated from text prompts. GPT Image 1.5 ranks #9 of 98.
GPT Image 1.5 API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $5 | 1M tokens |
| Output | $32 | 1M tokens |
| Cached input | $1.25 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
GPT Image 1.5 vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 GPT Image 1.5 | $5 | $32 |
| GPT Image 1 Mini | $2 | $8 |
| GPT Image 2.5 Flare | $5 | $30 |
| GPT Image 2.5 Sunburst | $5 | $30 |
| GPT Image 2 | $5 | $30 |
How to use the GPT Image 1.5 API
View docs
Build with your agent
Give your agent the model details, code and documentation.
Paste it into your coding agent to build the integration.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/images/generations' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "openai/gpt-image-1-5",
"prompt": "A ginger cat asleep on a stack of exactly three hardcover books in a rainy bookshop window at dusk. Gold lettering on the glass reads OPEN LATE. Warm lamp light inside, raindrops and blurred neon reflections outside, 35mm film photo."
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "openai/gpt-image-1-5",
"prompt": "A ginger cat asleep on a stack of exactly three hardcover books in a rainy bookshop window at dusk. Gold lettering on the glass reads OPEN LATE. Warm lamp light inside, raindrops and blurred neon reflections outside, 35mm film photo."
}
response = requests.post("https://api.aimlapi.com/v1/images/generations", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/images/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "openai/gpt-image-1-5",
"prompt": "A ginger cat asleep on a stack of exactly three hardcover books in a rainy bookshop window at dusk. Gold lettering on the glass reads OPEN LATE. Warm lamp light inside, raindrops and blurred neon reflections outside, 35mm film photo."
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Models similar to GPT Image 1.5
.svg){kind=small}
Related articles
.webp)
GPT Image 1.5 FAQ
How much does GPT Image 1.5 cost?
GPT Image 1.5 costs $5 input and $32 output per 1M tokens on AI/ML API, billed as you go with no subscription.
How to use gpt-image-1.5 API?
1. Register on our platform
2. Verify your account
3. Create an API key
4. Copy the code from this page
5. Paste it in your project
How long does Chat GPT take to make an image?
GPT-Image-1.5 is 4x Faster than the previous models – DALL-E 3 and GPT-Image-1. Detailed high resolution images now take near 30 seconds to be generated.
Which GPT is best for image generation?
GPT-image-1.5 is OpenAI's most advanced image generation model, capable of creating and editing high-quality, detailed images from text descriptions and reference images.
When was gpt-image-1.5 released?
GPT-Image-1.5 was released on December 16, 2025. OpenAI made the model available globally to all ChatGPT users and through the API on this date, marking a significant upgrade to their image generation capabilities.
What is the GPT Image 1.5 model ID?
Use openai/gpt-image-1-5 as the model parameter. Requests go to https://api.aimlapi.com/v1/images/generations with your AI/ML API key.