Gemini 3 Pro Image

Specs & limits

• Google's stable model code for Nano Banana Pro
• the gateway served it as gemini-3-pro-image-preview until 2026-10-09. Caching, function calling and structured outputs are not supported
• Search grounding and batch are. It reasons before every image and has no thinking-level control. Billed per token at three rates: input, image output, and text and reasoning output
• an output image is 1,120 tokens at 1K and 2K and 2,000 at 4K, and a reference image is 560 input tokens

per Google 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.

Gemini 3 Pro Image

Model returned 1408×768 latency 18 s

One prompt, one request per model, no retries and no cherry-picking. This is 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 Gemini 3 Pro Image 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="gemini-3-pro-image",
    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: "gemini-3-pro-image",
  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": "gemini-3-pro-image",
    "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:  "gemini-3-pro-image",
		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("gemini-3-pro-image")
        .prompt("a watercolor lighthouse at dawn")
        .size("1024x1024")
        .build());
System.out.println(resp.data().orElseThrow().get(0).b64Json().orElseThrow().substring(0, 80));

About Gemini 3 Pro Image

• It targets graphic design, product mockups, and data visualization, and Google calls it the premium choice for the most complex visual tasks, citing the highest level of world knowledge, advanced localization, brand consistency, and precision creative control.
• The model accepts image and text input and returns interleaved image and text output, with 65,536 input and 32,768 output tokens, at 1K, 2K, or 4K across ten aspect ratios from 1:1 to 21:9.
• Thinking is the differentiator: the model generates up to two interim images to test composition and logic, and the last of those is the delivered render.
• Google Search grounding lets it pull real-time facts, such as current weather or market data, into a chart or layout before drawing.
• It accepts up to six object reference images, five character references, and three style references, and Google names it as its best model for legible in-image text, including localizing and translating copy across fonts and calligraphy.
• Batch processing is supported, and output carries SynthID plus C2PA Content Credentials.
• Synthorai delivers it through the same OpenAI-compatible endpoint as its other image models.

FAQ

Related models

Compare