GPT Image 1 Mini is an optimized, cost-efficient version of the GPT Image 1 model designed for fast, high-quality image generation from text prompts. It produces photorealistic or illustrative images at high resolution and is ideal for large-scale image generation tasks such as mass previews, UI icons, and teaser visuals.
n (number of images generated per prompt)size (image resolution control)quality (low, medium, high balancing speed, cost, and fidelity)style (adjusts image stylistic preferences)Low Quality:
Medium Quality:
High Quality:
vs DALL·E 3: GPT-Image-1-Mini excels in cost efficiency and speed, optimized for bulk generation, while DALL·E 3 delivers superior creativity and artistry with complex prompt fidelity. GPT-Image-1-Mini supports inpainting and style matching, whereas DALL·E 3 focuses on highly accurate text following and visual storytelling.
vs Imagen 3: Imagen 3 leads in hyperrealistic detail and lighting effects, often outperforming on photorealism benchmarks, but GPT-Image-1-Mini offers faster responses and better text rendering within images. GPT-Image-1-Mini provides more flexible style control and efficient bulk generation at lower cost.
vs Midjourney: Midjourney specializes in creative, visually stunning artwork with strong stylistic flair, often preferred for unique illustrations. GPT-Image-1-Mini trades some artistic nuance for faster, cost-effective generation, making it ideal for pragmatic, high-volume use cases like previews and UI assets.
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
import requests r = requests.post( "https://api.aimlapi.com/v1/images/generations", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "openai/gpt-image-1-mini", "prompt": "A cat holding a sign that says hello" }, ) print(r.json())
const r = 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-mini", "prompt": "A cat holding a sign that says hello" }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/images/generations \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"openai/gpt-image-1-mini","prompt":"A cat holding a sign that says hello"}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
Text prompt $2.6/1M · cached text $0.26/1M · generated image tokens $10.4/1M (image input tokens $3.25/1M, cached image tokens $0.325/1M).
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Text-to-Image Arena | 914 | Human preference Elo from blind pairwise comparisons of generated images, measured independently by Artificial Analysis | Source | September 28, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
GPT Image 1 Mini This page | Image generation at scale | |||
| Image generation at scale | ||||
| Image generation at scale | ||||
| Image generation at scale | ||||
| Image generation at scale |
GPT Image 1 Mini takes image, text as input and returns image.
GPT Image 1 Mini is priced at input $2.6 / 1M tokens, output $10.4 / 1M tokens, cached input $0.26 / 1M tokens.
GPT Image 1 Mini is billed per token, charged separately for input and output.
Yes, GPT Image 1 Mini accepts image input as well as a text prompt.
GPT Image 1 Mini was built by OpenAI.
Send a request to https://api.aimlapi.com/v1/images/generations with openai/gpt-image-1-mini as the model id.
Yes. GPT Image 1 Mini is served through AI/ML API, so the same key and endpoint format used for other models applies.
It generates images from text prompts, functioning as a text-to-image model.
