GPT Image 2

Specs & limits

• State-of-the-art image generation and editing tier
• partial-image streaming via partial_images parameter (100 extra image tokens per partial)

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 2

Model returned 1402×1122 latency 18 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 2 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-2",
    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-2",
  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-2",
    "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-2",
		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-2")
        .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 2

• Versus its predecessors it adds flexible image sizes and high-fidelity image inputs, and it serves both the image generation and image edit endpoints while rating in the highest performance tier on the official model page.
• Sizes are no longer a fixed menu: any edge up to 3840px is allowed provided both edges are multiples of 16 and the long-to-short ratio stays within 3:1, which brings 4K output within reach alongside the familiar square, portrait, and landscape presets.
• OpenAI's launch material aims it at production workflows where images must be accurate, readable, on-brand, localized, and usable without heavy cleanup, and names apps, ads, product flows, social, presentations, and documents, plus diagrams, infographics, charts, posters, and comics.
• Two behaviours differ from earlier models and will break copied code: the input fidelity parameter must be omitted because every image input is already processed at high fidelity, and transparent backgrounds are not supported on this model.
• Mask-based inpainting, partial-image streaming, selectable moderation, and Batch submission all carry over.
• It is the current default recommendation for new image workloads.
• Synthorai supports gpt-image-2 on its OpenAI-compatible /v1/images/generations route, keeping request and response shapes identical to upstream.

FAQ

Related models

Compare