gpt-image-1.5

Specs & limits

Labelled 'our previous image generation model'. Re-checked 2026-08-05: the only listed snapshot, gpt-image-1.5-2025-12-16, is NOT marked deprecated, and the page 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-1.5

Model returned 1024×1024 latency 20 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-1.5 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-1.5",
    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-1.5",
  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-1.5",
    "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-1.5",
		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-1.5")
        .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-1.5

• It accepts text and image inputs and produces image outputs, with per-image pricing that scales by quality level and resolution across square, portrait, and landscape formats (1024x1024, 1024x1536, and 1536x1024), at low, medium, or high quality.
• It serves both the generation and edits endpoints, supports mask-based inpainting, and is available through the Batch API for bulk jobs.
• The shared image API surface applies here too: PNG, JPEG, or WebP output with an adjustable compression level, transparent or opaque backgrounds where the format allows, selectable moderation sensitivity, streamed partial images during a generation, and edit requests that can carry multiple input images with a choice of input fidelity.
• It ships as a dated snapshot from December 2025 and, despite the "previous" label, carries no formal deprecation banner and no named replacement on its page.
• Requests blocked by moderation return a dedicated error code rather than an empty result, and moderation sensitivity itself is a request parameter.
• It suits work where faithfulness to detailed prompts matters more than raw speed, and it remains the newest of the fixed-size image models, since gpt-image-2 replaced the three-size menu with free-form dimensions.
• Through Synthorai's OpenAI-compatible images API, moving to gpt-image-1.5 is a drop-in model-name swap.

FAQ

Related models

Compare