GPT Image 1 Mini

Specs & limits

Re-checked 2026-08-05: the model page carries no deprecation status for the model or any of its snapshots, and names no retirement date or replacement.

per OpenAI official docs ↗

One prompt, measured through the gateway

PROMPT A weathered enamel diner mug on a steel counter, the words "OPEN 24H" stencilled on the mug in worn paint, low winter sun raking in from the left, shallow depth of field.

GPT Image 1 Mini

Model returned 1536×1024 latency 19 s

One prompt, one request per model, no retries and no cherry-picking - the first result each model returned. Neither size nor duration was pinned: each model used its own default, because a request shaped to fit all of them would flatter none. Files here are re-encoded for the web, so judge composition and prompt adherence, not compression.

Use GPT Image 1 Mini in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/images/generations

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.images.generate(
    model="gpt-image-1-mini",
    prompt="a watercolor lighthouse at dawn",
    size="1024x1024",
)
print(resp.data[0].b64_json[:80])

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://synthorai.io/v1",
  apiKey: "sk-syn-...",
});

const resp = await client.images.generate({
  model: "gpt-image-1-mini",
  prompt: "a watercolor lighthouse at dawn",
  size: "1024x1024",
});
console.log(resp.data?.[0]?.b64_json?.slice(0, 80));

curl https://synthorai.io/v1/images/generations \
  -H "Authorization: Bearer sk-syn-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-1-mini",
    "prompt": "a watercolor lighthouse at dawn",
    "size": "1024x1024"
  }'

package main

import (
	"context"
	"fmt"

	"github.com/openai/openai-go/v3"
	"github.com/openai/openai-go/v3/option"
)

func main() {
	client := openai.NewClient(
		option.WithBaseURL("https://synthorai.io/v1"),
		option.WithAPIKey("sk-syn-..."),
	)
	resp, _ := client.Images.Generate(context.TODO(), openai.ImageGenerateParams{
		Model:  "gpt-image-1-mini",
		Prompt: "a watercolor lighthouse at dawn",
		Size:   "1024x1024",
	})
	fmt.Println(resp.Data[0].B64JSON[:80])
}

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.images.*;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .baseUrl("https://synthorai.io/v1")
    .apiKey("sk-syn-...")
    .build();

ImagesResponse resp = client.images().generate(
    ImageGenerateParams.builder()
        .model("gpt-image-1-mini")
        .prompt("a watercolor lighthouse at dawn")
        .size("1024x1024")
        .build());
System.out.println(resp.data().orElseThrow().get(0).b64Json().orElseThrow().substring(0, 80));

About GPT Image 1 Mini

• It supports low, medium, and high quality tiers, three resolution options covering square, portrait, and landscape formats at 1024x1024, 1024x1536, and 1536x1024, and discounted cached text input.
• Notably, cost is the only difference OpenAI's documentation actually asserts between mini and the full model: the two pages describe the same modalities, the same sizes, the same quality tiers, and the same rate-limit structure.
• It serves the image generation and edits endpoints and is available through the Batch API, though the Responses API image path is not listed for it.
• The shared image API applies: PNG, JPEG, or WebP output with adjustable compression, transparent or opaque backgrounds where the format supports it, up to ten images in one request, selectable moderation sensitivity, and streamed partial images during generation.
• OpenAI's guidance on which surface to use applies here as everywhere: reach for the Image API when you need one image from one prompt, and the Responses API when you want a conversational, editable image experience.
• Requests blocked by moderation return a specific error code rather than an empty image, which is worth handling explicitly in a batch pipeline.
• It targets high-volume generation work where unit economics outweigh peak fidelity, such as thumbnails, variants, and preview passes.
• Image jobs sent to Synthorai's OpenAI-compatible /v1/images/generations endpoint can select gpt-image-1-mini directly.

FAQ

Related models

Compare