Google

Gemini 3.1 Flash Image Preview

Built for image generation and editing, with stronger multimodal understanding, conversational edits, and rapid visual prototyping than earlier Gemini image capabilities. Compared with GPT Image, Qwen Image, and Seedream, it is useful for combining documents, images, and prompts in one visual workflow.

  • 推論
  • マルチモーダル出力

このモデルの説明は現在の言語に未対応のため、英語で表示しています。

コンソールで使うgemini-3.1-flash-image-preview

USD

料金

default
1K$0.0672/image
2K$0.1008/image
4K$0.1344/image

米ドル建ての公開価格です。実際の料金はアカウントグループや利用量により異なる場合があります。

API

コード例

curl --location --request POST 'https://api.tokenhot.cn/v1beta/models/gemini-3.1-flash-image-preview:generateContent' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "contents": [
        {
            "role": "user",
            "parts": [
                {
                    "text": "draw a baby"
                }
            ]
        }
    ],
    "generationConfig": {
        "responseModalities": [
            "IMAGE"
        ],
        "imageConfig": {
            "aspectRatio": "16:9",
            "imageSize": "2k"
        }
    }
}'

Google

関連モデル

GeminiGoogleGemini 3.8 Flash

The flagship Flash model for long-horizon software engineering, autonomous agents, and complex enterprise workflows. It keeps the speed and cost profile of Flash while adding stronger reasoning and tool orchestration. It accepts text, images, video, audio, and PDF input, with about a 1.05M-token context window, search grounding, function calling, code execution, structured outputs, and tunable thinking. Prefer it over Flash-Lite for harder tasks, at higher usage cost.

$0.7874/1M tokens
GeminiGoogleGemini 3 PRO Image Preview

Built for image generation and editing, with stronger multimodal understanding, conversational edits, and rapid visual prototyping than earlier Gemini image capabilities. Compared with GPT Image, Qwen Image, and Seedream, it is useful for combining documents, images, and prompts in one visual workflow.

$0.134/image
GeminiGoogleGemini 4 Argon

Built for complex software engineering, mathematical and scientific problems, and long tasks requiring multi-step agent work. It accepts text, images, video, audio, and PDFs, with a unified context of about 1.05 million tokens, plus thinking, tool use, and code execution. It is a flagship reasoning model; routine short Q&A usually does not need this much context or reasoning.

$2.1/1M tokens
GeminiGoogleGemini Nano Banana 2.1

A fast choice for image creation and conversational editing. Compared with Nano Banana 2, it improves visual quality, text and infographic layout, wide-format images, and character consistency across edits. It supports multiple reference images and 1K, 2K, or 4K output; consider Nano Banana Pro for the most demanding brand and precision work.

$0.0096/call

FAQ

よくある質問

Gemini 3.1 Flash Image Preview はどの用途に適していますか?

Gemini 3.1 Flash Image Preview は、このページに記載された入出力と機能に適しています。重要なシステムでは実際の負荷で事前に検証してください。

Gemini 3.1 Flash Image Preview の料金体系は?

料金は上の料金セクションに表示されています。実際の費用は利用量、アカウントグループ、リクエスト内容によって異なります。

Gemini 3.1 Flash Image Preview を呼び出すには?

上記のモデル ID と対応 API プロトコルを使用します。利用データがある場合はコード例も表示されます。

はじめる

Gemini 3.1 Flash Image Preview で構築する

コンソールで使う