GPT Image 1 is OpenAI's earlier natively multimodal image generation model: it accepts both text and image inputs and produces image outputs, with low, medium, and high quality tiers and three resolution options.
- Input
- text image $5/M
- Output
- image $40/M
Benchmarks
GPT Image 1: 22 published, but no benchmark it shares with enough other models to compare.
Price in context
Where the price sits among 8 comparable models
The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.
Specs & limits
Image
| Sizes |
|
|---|---|
| Input modes | text-to-image, image edit with mask inpainting |
| Format | png, jpeg, webp |
| Images per request | 10 |
| Image capabilities |
|
Model
| Modalities | text + image → image |
|---|
Labelled 'our previous image generation model' on the model page. Re-checked 2026-08-05: no deprecation notice, no retirement date and no named replacement - 'previous generation' is a positioning label, not a lifecycle status.
Use GPT Image 1 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",
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",
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",
"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",
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")
.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
- Those sizes are 1024x1024, 1024x1536, and 1536x1024, covering square, portrait, and landscape, and quality also accepts auto.
- It serves both image endpoints (generation and edits), and its edit path supports mask-based inpainting, where the image and mask must share a format and size and stay under 50MB.
- Uniquely among OpenAI's image models it also lists the Responses API among its endpoints, which is the surface OpenAI recommends when you want conversational, editable image experiences rather than one prompt in and one file out.
- Output can be returned as PNG, JPEG, or WebP with an adjustable compression level, backgrounds can be transparent or opaque when the format allows it, moderation sensitivity is selectable, and partial images can be streamed while a generation is still running.
- Now labelled a previous-generation model behind gpt-image-1.5 and gpt-image-2, it carries no formal deprecation date and remains available for backward compatibility and for pipelines tuned to its output characteristics.
- Synthorai keeps gpt-image-1 selectable through its OpenAI-compatible image generation endpoint, so legacy integrations keep working without changes.
FAQ
Is the GPT Image 1 API free to try?
Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. That's enough to try GPT Image 1 against your real workload before adding a payment method.
What is GPT Image 1 best at?
Natively multimodal text and image inputs; three quality tiers and resolution options; kept available for backward compatibility. See the About section for the full picture from the vendor's own release notes.
How much does GPT Image 1 cost?
GPT Image 1 costs $5 per million input tokens and $40 per million output tokens on Synthorai. That is the provider's list price, with no platform markup.
How do I generate images with the GPT Image 1 API?
POST to /v1/images/generations on Synthorai with model="gpt-image-1". It follows the OpenAI images API shape, so no vendor SDK is needed. Supported sizes: 1024x1024, 1536x1024, 1024x1536, auto.
How do I get access to GPT Image 1?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="gpt-image-1", and you're done. One API key covers every model on the gateway.
Related models
Compare
Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.