{
  "aboutHtml": "<p>GPT Image 2は、テキストと視覚入力から画像を生成・編集するOpenAIのモデルです。文章の制作指示から新しい画像を作り、編集や参照中心の制作には原画像を使えます。イラスト、商品コンセプト、視覚的な構図、既存素材の変更などが実用例です。GPT Image 2.5 SunburstやFlareとは別のエディションで、固有の品質範囲と入力忠実度の動作を持ちます。</p><p>生成では、被写体、シーン、構図、光、意図したスタイルを記述します。編集では変えるものと外観を維持するものを指定します。商品制作なら、淡い面に置いた陶器のランプ、中央の輪郭、キャプション用の余白を依頼し、追加編集でランプの形と視点を保ちながら背景を変えられます。記載された直接の生成・編集ワークフローは最大32,000文字のプロンプトを受け付け、1～10枚の画像を返せます。</p><p>参照を使う編集は最大16枚の入力画像に対応します。被写体、背景、視覚表現が混同されないよう、各参照の目的を指定します。GPT Image 2はすべての画像入力を自動で高忠実度処理します。このエディションでは調整できないため、input_fidelityは省略します。これはGPT Image 1のhighまたはlowの選択や、GPT Image 1 Miniのlow限定の入力忠実度とは異なります。高忠実度の入力処理は原素材の細部を支えますが、すべての細部が変わらず再現される保証ではありません。</p><p>マスクで編集領域を示せます。ガイドの準備要件では、原画像とマスクは同じ形式と寸法で、50 MB未満である必要があります。マスクにはアルファチャンネルも必要です。複数の入力画像がある場合、マスクは最初の画像に適用されます。モデルはマスクを厳密な幾何学的境界ではなく、プロンプトに基づく誘導として扱います。局所的な変更と維持要件を記述し、周囲に意図しない差異がないかを確認します。</p><p>GPT Image 2はlow、medium、high、autoの品質に対応し、標準はautoです。2.5ファミリーのxhighとmaxは、このエディションの品質範囲に含まれません。サイズは正方形、横長、縦長、自動、または有効な独自の幅と高さを選べます。開発元の例は1024 × 1024、1536 × 1024、1024 × 1536、2048 × 2048、2048 × 1152、3840 × 2160、2160 × 3840ピクセルです。品質と寸法を同じ制御として扱わず、実際のレイアウトに合う向きと細部の水準を選びます。</p><p>独自寸法は16ピクセルの倍数、最大辺3840ピクセル、長辺対短辺の比率3:1以下、面積655,360～8,294,400ピクセルが条件です。これらは同時に適用されます。2560 × 1440を超える解像度は実験的とされています。一つの条件を満たすフレームでも別の条件に違反し得るため、有効な縦横寸法の組み合わせを選び、切り取りで失いたくない要素を制作指示に記述します。</p><p>出力の標準はPNGで、JPEGとWebPも利用できます。JPEGとWebPは0～100の圧縮値に対応します。背景は不透明または自動を選べます。現在の個別仕様は、GPT Image 2の透明背景をプレビュー機能として説明しています。透明背景を依頼する場合は、アルファチャンネルを保持できるPNGまたはWebPを使います。記載されたストリーミングは、完成画像の前に最大3枚の部分画像を送れます。進捗プレビューではなく最終素材を保存してください。開発元のインターフェースはバッチ処理にも対応します。</p><p>実際の結果で、文字の明瞭さ、物体の位置、原素材の細部の維持を評価します。GPT Imageは、正確な文字、レイアウトに敏感な構図、別々の生成で視覚的特徴を繰り返し保つことが難しい場合があります。編集を続ける場合は採用した結果を次の原画像に使い、目に見える問題に結びつく具体的な変更を指定します。GPT Image 2の有用な出力は、明確な生成・編集指示に結びついた画像です。その作業に合わせて高忠実度入力、寸法、品質を選びます。</p>",
  "aboutText": "GPT Image 2は、テキストと視覚入力から画像を生成・編集するOpenAIのモデルです。文章の制作指示から新しい画像を作り、編集や参照中心の制作には原画像を使えます。イラスト、商品コンセプト、視覚的な構図、既存素材の変更などが実用例です。GPT Image 2.5 SunburstやFlareとは別のエディションで、固有の品質範囲と入力忠実度の動作を持ちます。\n\n生成では、被写体、シーン、構図、光、意図したスタイルを記述します。編集では変えるものと外観を維持するものを指定します。商品制作なら、淡い面に置いた陶器のランプ、中央の輪郭、キャプション用の余白を依頼し、追加編集でランプの形と視点を保ちながら背景を変えられます。記載された直接の生成・編集ワークフローは最大32,000文字のプロンプトを受け付け、1～10枚の画像を返せます。\n\n参照を使う編集は最大16枚の入力画像に対応します。被写体、背景、視覚表現が混同されないよう、各参照の目的を指定します。GPT Image 2はすべての画像入力を自動で高忠実度処理します。このエディションでは調整できないため、input_fidelityは省略します。これはGPT Image 1のhighまたはlowの選択や、GPT Image 1 Miniのlow限定の入力忠実度とは異なります。高忠実度の入力処理は原素材の細部を支えますが、すべての細部が変わらず再現される保証ではありません。\n\nマスクで編集領域を示せます。ガイドの準備要件では、原画像とマスクは同じ形式と寸法で、50 MB未満である必要があります。マスクにはアルファチャンネルも必要です。複数の入力画像がある場合、マスクは最初の画像に適用されます。モデルはマスクを厳密な幾何学的境界ではなく、プロンプトに基づく誘導として扱います。局所的な変更と維持要件を記述し、周囲に意図しない差異がないかを確認します。\n\nGPT Image 2はlow、medium、high、autoの品質に対応し、標準はautoです。2.5ファミリーのxhighとmaxは、このエディションの品質範囲に含まれません。サイズは正方形、横長、縦長、自動、または有効な独自の幅と高さを選べます。開発元の例は1024 × 1024、1536 × 1024、1024 × 1536、2048 × 2048、2048 × 1152、3840 × 2160、2160 × 3840ピクセルです。品質と寸法を同じ制御として扱わず、実際のレイアウトに合う向きと細部の水準を選びます。\n\n独自寸法は16ピクセルの倍数、最大辺3840ピクセル、長辺対短辺の比率3:1以下、面積655,360～8,294,400ピクセルが条件です。これらは同時に適用されます。2560 × 1440を超える解像度は実験的とされています。一つの条件を満たすフレームでも別の条件に違反し得るため、有効な縦横寸法の組み合わせを選び、切り取りで失いたくない要素を制作指示に記述します。\n\n出力の標準はPNGで、JPEGとWebPも利用できます。JPEGとWebPは0～100の圧縮値に対応します。背景は不透明または自動を選べます。現在の個別仕様は、GPT Image 2の透明背景をプレビュー機能として説明しています。透明背景を依頼する場合は、アルファチャンネルを保持できるPNGまたはWebPを使います。記載されたストリーミングは、完成画像の前に最大3枚の部分画像を送れます。進捗プレビューではなく最終素材を保存してください。開発元のインターフェースはバッチ処理にも対応します。\n\n実際の結果で、文字の明瞭さ、物体の位置、原素材の細部の維持を評価します。GPT Imageは、正確な文字、レイアウトに敏感な構図、別々の生成で視覚的特徴を繰り返し保つことが難しい場合があります。編集を続ける場合は採用した結果を次の原画像に使い、目に見える問題に結びつく具体的な変更を指定します。GPT Image 2の有用な出力は、明確な生成・編集指示に結びついた画像です。その作業に合わせて高忠実度入力、寸法、品質を選びます。",
  "editorialOverlay": {
    "copy_fields": null,
    "copy_sha256": null,
    "copy_source": null,
    "html_sha256": "66588eb3f6c1c683ecfdbdfce052cf0d5329796b413bad7f1e7cbe30e05ab1fe",
    "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06",
    "raw_model_unchanged": true,
    "schema": "ailoot-native-model-editorial-v1"
  },
  "locale": "ja",
  "methods": [
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">O</span><h2 id=\"sheet-title\">OpenAI: GPT Image 2</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"閉じる\">×</button></div><div class=\"idline\"><span>OpenAI /</span><code>gpt-image-2</code><button type=\"button\" id=\"copy-id\">IDをコピー</button></div><nav class=\"card-jump-nav\" aria-label=\"モデルカードのセクション\"><button type=\"button\" data-card-jump=\"overview\">はじめに</button><button type=\"button\" data-card-jump=\"methods\">入力とメソッド</button><button type=\"button\" data-card-jump=\"pricing\">料金</button><button type=\"button\" data-card-jump=\"examples\">例</button><button type=\"button\" data-card-jump=\"results\">結果</button><button type=\"button\" data-card-jump=\"aliases\">エイリアス</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"APIメソッド\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Core|images|/v1/images/generations|gpt-image-2\">画像</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Ultra|images|/v1/images/generations|gpt-image-2\">画像 · Ultra</button></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-0\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">はじめに</h3><p class=\"mdesc-full\">GPT Image 2は、テキストと視覚参照から画像を生成・編集します。柔軟なフレーム寸法に対応し、すべての画像入力を自動で高忠実度処理します。完成素材の品質、形式、背景は個別に制御できます。</p><dl class=\"card-io\" data-card-io><div><dt>対応する入力</dt><dd>テキスト</dd></div><div><dt>結果</dt><dd>画像</dd></div></dl><details class=\"card-about\"><summary>モデルについて</summary><p class=\"note-s\" data-model-method-boundary>この説明はモデルの機能を紹介するものです。Ailootで利用できる入力、出力、オプションは、選択したメソッドごとに以下に記載されています。</p><div class=\"mabout\" id=\"m-about\"><p>GPT Image 2は、テキストと視覚入力から画像を生成・編集するOpenAIのモデルです。文章の制作指示から新しい画像を作り、編集や参照中心の制作には原画像を使えます。イラスト、商品コンセプト、視覚的な構図、既存素材の変更などが実用例です。GPT Image 2.5 SunburstやFlareとは別のエディションで、固有の品質範囲と入力忠実度の動作を持ちます。</p><p>生成では、被写体、シーン、構図、光、意図したスタイルを記述します。編集では変えるものと外観を維持するものを指定します。商品制作なら、淡い面に置いた陶器のランプ、中央の輪郭、キャプション用の余白を依頼し、追加編集でランプの形と視点を保ちながら背景を変えられます。記載された直接の生成・編集ワークフローは最大32,000文字のプロンプトを受け付け、1～10枚の画像を返せます。</p><p>参照を使う編集は最大16枚の入力画像に対応します。被写体、背景、視覚表現が混同されないよう、各参照の目的を指定します。GPT Image 2はすべての画像入力を自動で高忠実度処理します。このエディションでは調整できないため、input_fidelityは省略します。これはGPT Image 1のhighまたはlowの選択や、GPT Image 1 Miniのlow限定の入力忠実度とは異なります。高忠実度の入力処理は原素材の細部を支えますが、すべての細部が変わらず再現される保証ではありません。</p><p>マスクで編集領域を示せます。ガイドの準備要件では、原画像とマスクは同じ形式と寸法で、50 MB未満である必要があります。マスクにはアルファチャンネルも必要です。複数の入力画像がある場合、マスクは最初の画像に適用されます。モデルはマスクを厳密な幾何学的境界ではなく、プロンプトに基づく誘導として扱います。局所的な変更と維持要件を記述し、周囲に意図しない差異がないかを確認します。</p><p>GPT Image 2はlow、medium、high、autoの品質に対応し、標準はautoです。2.5ファミリーのxhighとmaxは、このエディションの品質範囲に含まれません。サイズは正方形、横長、縦長、自動、または有効な独自の幅と高さを選べます。開発元の例は1024 × 1024、1536 × 1024、1024 × 1536、2048 × 2048、2048 × 1152、3840 × 2160、2160 × 3840ピクセルです。品質と寸法を同じ制御として扱わず、実際のレイアウトに合う向きと細部の水準を選びます。</p><p>独自寸法は16ピクセルの倍数、最大辺3840ピクセル、長辺対短辺の比率3:1以下、面積655,360～8,294,400ピクセルが条件です。これらは同時に適用されます。2560 × 1440を超える解像度は実験的とされています。一つの条件を満たすフレームでも別の条件に違反し得るため、有効な縦横寸法の組み合わせを選び、切り取りで失いたくない要素を制作指示に記述します。</p><p>出力の標準はPNGで、JPEGとWebPも利用できます。JPEGとWebPは0～100の圧縮値に対応します。背景は不透明または自動を選べます。現在の個別仕様は、GPT Image 2の透明背景をプレビュー機能として説明しています。透明背景を依頼する場合は、アルファチャンネルを保持できるPNGまたはWebPを使います。記載されたストリーミングは、完成画像の前に最大3枚の部分画像を送れます。進捗プレビューではなく最終素材を保存してください。開発元のインターフェースはバッチ処理にも対応します。</p><p>実際の結果で、文字の明瞭さ、物体の位置、原素材の細部の維持を評価します。GPT Imageは、正確な文字、レイアウトに敏感な構図、別々の生成で視覚的特徴を繰り返し保つことが難しい場合があります。編集を続ける場合は採用した結果を次の原画像に使い、目に見える問題に結びつく具体的な変更を指定します。GPT Image 2の有用な出力は、明確な生成・編集指示に結びついた画像です。その作業に合わせて高忠実度入力、寸法、品質を選びます。</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailootで利用可能 · 入力とメソッド</h3><details class=\"card-method\" open><summary><b>Ailoot · 画像</b> <code>POST /v1/images/generations</code></summary><dl class=\"method-capabilities\"><div><dt>入力の種類</dt><dd><code>text</code></dd></div><div><dt>出力の種類</dt><dd><code>image</code></dd></div><div><dt>出力形式</dt><dd>画像ファイル</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>フィールド</th><th>種類</th><th>要件</th><th>値と制限</th><th>デフォルト</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>必須</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>gpt-image-2</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">prompt</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>必須</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>最小の長さ: 1</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">n</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>integer</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>最小値: 1</div></td><td data-cell-label=\"デフォルト\" data-default=\"known\"><span class=\"card-cell-label\">デフォルト</span>1</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>url, b64_json</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>boolean</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span></td><td data-cell-label=\"デフォルト\" data-default=\"known\"><span class=\"card-cell-label\">デフォルト</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">size</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div class=\"note-s\">モデルによる</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">quality</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div class=\"note-s\">モデルによる</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">background</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div class=\"note-s\">モデルによる</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">output_format</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div class=\"note-s\">モデルによる</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">output_compression</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>integer</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div class=\"note-s\">モデルによる</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">moderation</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div class=\"note-s\">モデルによる</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">input_fidelity</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div class=\"note-s\">モデルによる</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">style</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div class=\"note-s\">モデルによる</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">partial_images</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>integer</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div class=\"note-s\">モデルによる</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>入力素材の組み合わせ</summary><p class=\"note-s\"><b>テキストから画像へ</b> · 必須: prompt</p></details><details class=\"note-s\" data-method-contract><summary>メソッドのパラメータとライフサイクル</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>パラメータ</th><th>仕様</th></tr></thead><tbody><tr><th data-cell-label=\"パラメータ\" scope=\"row\"><span class=\"card-cell-label\">パラメータ</span><code>material_types</code></th><td data-cell-label=\"仕様\"><span class=\"card-cell-label\">仕様</span>text</td></tr><tr><th data-cell-label=\"パラメータ\" scope=\"row\"><span class=\"card-cell-label\">パラメータ</span><code>required</code></th><td data-cell-label=\"仕様\"><span class=\"card-cell-label\">仕様</span>model, prompt</td></tr><tr><th data-cell-label=\"パラメータ\" scope=\"row\"><span class=\"card-cell-label\">パラメータ</span><code>optional_controls</code></th><td data-cell-label=\"仕様\"><span class=\"card-cell-label\">仕様</span>null</td></tr><tr><th data-cell-label=\"パラメータ\" scope=\"row\"><span class=\"card-cell-label\">パラメータ</span><code>content_type</code></th><td data-cell-label=\"仕様\"><span class=\"card-cell-label\">仕様</span>application/json</td></tr></tbody></table></div><p>ライフサイクル: <code>synchronous_result_then_owned_library</code></p><p class=\"note-s\"><code>GET /v1/media/tasks/{task_id}</code> · 実際に返された task_id またはメディアライブラリのレコード</p><p class=\"note-s\"><code>GET /v1/media/assets/{asset_id}/content</code></p><p class=\"note-s\"><code>GET /v1/media/assets</code></p><p class=\"note-s\"><code>GET /v1/media/assets/{asset_id}</code></p><p class=\"note-s\">メソッドの形式とIDは正確に記載しています。供給元の対応能力とリクエストの受け入れは別です。</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">料金</h3><h4>Ailootのメソッド料金</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> 画像</b><code>POST /v1/images/generations</code></header><dl><div><dt>テキスト入力</dt><dd>$0.0025 <em>/ 1K</em></dd></div><div><dt>入力、画像</dt><dd>$0.004 <em>/ 1K tokens</em></dd></div><div><dt>出力、画像</dt><dd>$0.015 <em>/ 1K tokens</em></dd></div></dl></section><p class=\"note-s\">Ailootはリクエスト前に見積額を確保します。結果の取得後、実測使用量に基づいて最終料金を精算します。ストリーミング時の精算には最終の使用量記録を使用します。<a href=\"/docs/ja/billing/reserve/\">金額の確保と精算の仕組み →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">リクエスト例</h3><h4>Ailoot · 画像</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"コードの種類\"><button class=\"cg-tab\" id=\"model-code-642-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-642-panel-0\" aria-selected=\"true\" tabindex=\"0\">curl</button><button class=\"cg-tab\" id=\"model-code-642-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-642-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-642-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-642-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"コードをコピー\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-642-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-642-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\nexport AILOOT_API_KEY\nexport AILOOT_API_KEY\n: &quot;${AILOOT_PROMPT_FILE:?Set your actual UTF-8 image brief}&quot;\nexport AILOOT_PROMPT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;gpt-image-2&quot;, &quot;prompt&quot;: &quot;&quot;}&#39;)\nf=Path(os.environ[&quot;AILOOT_PROMPT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 brief&quot;)\np[&#39;prompt&#39;]=f.read_text(encoding=&quot;utf-8&quot;)\nif not p[&#39;prompt&#39;].strip():raise SystemExit(&quot;Brief must contain text&quot;)\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n    if not items: raise SystemExit(&quot;No completed images; retain the full response&quot;)\n    for index, item in enumerate(items):\n        encoded=item.get(&quot;b64_json&quot;)\n        uri=item.get(&quot;url&quot;, &quot;&quot;)\n        if not encoded and uri.startswith(&quot;data:image/&quot;):\n            header, separator, encoded=uri.partition(&quot;,&quot;)\n            if not separator or &quot;;base64&quot; not in header: raise SystemExit(&quot;Unsupported image data URI&quot;)\n        if encoded:\n            raw=base64.b64decode(encoded,validate=True)\n        elif uri:\n            uri=urljoin(&quot;https://api.ailoot.ai&quot;,uri)\n            parsed=urlsplit(uri)\n            if parsed.scheme!=&quot;https&quot; or not parsed.netloc or parsed.username or parsed.password:\n                raise SystemExit(&quot;Invalid returned image URL&quot;)\n            owned=parsed.netloc==&quot;api.ailoot.ai&quot; and parsed.path.startswith(&quot;/v1/media/assets/&quot;) and parsed.path.endswith(&quot;/content&quot;)\n            args=[&quot;curl&quot;,&quot;--fail-with-body&quot;,&quot;--silent&quot;,&quot;--show-error&quot;,uri]\n            if owned: args += [&quot;-H&quot;,&quot;Authorization: Bearer &quot;+os.environ[&quot;AILOOT_API_KEY&quot;]]\n            temporary=Path(f&quot;image-{index}.bin&quot;)\n            subprocess.run(args+[&quot;-o&quot;,str(temporary)],check=True)\n            raw=temporary.read_bytes()\n            temporary.unlink()\n        else: raise SystemExit(&quot;Image has neither bytes nor URL&quot;)\n        if not raw: raise SystemExit(&quot;Empty image result&quot;)\n        ext=&quot;png&quot; if raw.startswith(b&quot;\\x89PNG&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else &quot;svg&quot; if raw.lstrip().startswith((b&quot;&lt;svg&quot;,b&quot;&lt;?xml&quot;)) else &quot;bin&quot;\n        Path(f&quot;image-{index}.{ext}&quot;).write_bytes(raw)\n    print(&quot;Every returned image saved; complete response metadata retained&quot;)\nsave_images(json.loads(Path(&quot;result.json&quot;).read_text())[&quot;data&quot;])\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-642-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-642-tab-1\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n    if not items: raise SystemExit(&quot;No completed images; retain the full response&quot;)\n    for index, item in enumerate(items):\n        encoded=item.get(&quot;b64_json&quot;)\n        uri=item.get(&quot;url&quot;, &quot;&quot;)\n        if not encoded and uri.startswith(&quot;data:image/&quot;):\n            header, separator, encoded=uri.partition(&quot;,&quot;)\n            if not separator or &quot;;base64&quot; not in header: raise SystemExit(&quot;Unsupported image data URI&quot;)\n        if encoded:\n            raw=base64.b64decode(encoded,validate=True)\n        elif uri:\n            uri=urljoin(&quot;https://api.ailoot.ai&quot;,uri)\n            parsed=urlsplit(uri)\n            if parsed.scheme!=&quot;https&quot; or not parsed.netloc or parsed.username or parsed.password:\n                raise SystemExit(&quot;Invalid returned image URL&quot;)\n            owned=parsed.netloc==&quot;api.ailoot.ai&quot; and parsed.path.startswith(&quot;/v1/media/assets/&quot;) and parsed.path.endswith(&quot;/content&quot;)\n            args=[&quot;curl&quot;,&quot;--fail-with-body&quot;,&quot;--silent&quot;,&quot;--show-error&quot;,uri]\n            if owned: args += [&quot;-H&quot;,&quot;Authorization: Bearer &quot;+os.environ[&quot;AILOOT_API_KEY&quot;]]\n            temporary=Path(f&quot;image-{index}.bin&quot;)\n            subprocess.run(args+[&quot;-o&quot;,str(temporary)],check=True)\n            raw=temporary.read_bytes()\n            temporary.unlink()\n        else: raise SystemExit(&quot;Image has neither bytes nor URL&quot;)\n        if not raw: raise SystemExit(&quot;Empty image result&quot;)\n        ext=&quot;png&quot; if raw.startswith(b&quot;\\x89PNG&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else &quot;svg&quot; if raw.lstrip().startswith((b&quot;&lt;svg&quot;,b&quot;&lt;?xml&quot;)) else &quot;bin&quot;\n        Path(f&quot;image-{index}.{ext}&quot;).write_bytes(raw)\n    print(&quot;Every returned image saved; complete response metadata retained&quot;)\n\nf=Path(os.environ[&quot;AILOOT_PROMPT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Set your actual UTF-8 image brief file&quot;)\nrequest={&#39;model&#39;: &#39;gpt-image-2&#39;, &#39;prompt&#39;: &#39;&#39;}\nrequest[&quot;prompt&quot;]=f.read_text(encoding=&quot;utf-8&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nresult=client.images.generate(**request)\nPath(&quot;sdk-result.txt&quot;).write_text(str(result),encoding=&quot;utf-8&quot;)\nsave_images([{&quot;b64_json&quot;:getattr(item,&quot;b64_json&quot;,None),&quot;url&quot;:getattr(item,&quot;url&quot;,None)} for item in result.data])\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-642-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-642-tab-2\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\nimport { readFileSync, writeFileSync } from &quot;node:fs&quot;;\nconst key=process.env.AILOOT_API_KEY;\nif(!key) throw new Error(&quot;Set your actual Ailoot API key&quot;);\nconst client=new OpenAI({baseURL:&quot;https://api.ailoot.ai/v1&quot;,apiKey:key,maxRetries:0});\nconst request={&quot;model&quot;: &quot;gpt-image-2&quot;, &quot;prompt&quot;: &quot;&quot;};\nif(!process.env.AILOOT_PROMPT_FILE)throw new Error(&quot;Set your actual UTF-8 image brief file&quot;);\nrequest.prompt=readFileSync(process.env.AILOOT_PROMPT_FILE,&quot;utf8&quot;);\nconst result=await client.images.generate(request);\nwriteFileSync(&quot;sdk-result.json&quot;,JSON.stringify(result,null,2));\nif(!result.data?.length) throw new Error(&quot;No completed images&quot;);\nfor(let index=0;index&lt;result.data.length;index++) {\n  const item=result.data[index];let encoded=item.b64_json,uri=item.url||&quot;&quot;,raw;\n  if(!encoded &amp;&amp; uri.startsWith(&quot;data:image/&quot;)) {\n    const comma=uri.indexOf(&quot;,&quot;);if(comma&lt;0 || !uri.slice(0,comma).includes(&quot;;base64&quot;)) throw new Error(&quot;Unsupported image data URI&quot;);\n    encoded=uri.slice(comma+1);\n  }\n  if(encoded) {\n    if(encoded.length%4!==0 || !/^[A-Za-z0-9+/]*={0,2}$/.test(encoded)) throw new Error(&quot;Invalid Base64&quot;);\n    raw=Buffer.from(encoded,&quot;base64&quot;);\n  } else if(uri) {\n    const u=new URL(uri,&quot;https://api.ailoot.ai&quot;);\n    if(u.protocol!==&quot;https:&quot; || u.username || u.password) throw new Error(&quot;Invalid returned URL&quot;);\n    const owned=u.origin===&quot;https://api.ailoot.ai&quot; &amp;&amp; u.pathname.startsWith(&quot;/v1/media/assets/&quot;) &amp;&amp; u.pathname.endsWith(&quot;/content&quot;);\n    const response=await fetch(u,{headers:owned?{Authorization:&quot;Bearer &quot;+key}:{},redirect:&quot;manual&quot;});\n    if(!response.ok) throw new Error(&quot;Image content download failed: &quot;+response.status);\n    raw=Buffer.from(await response.arrayBuffer());\n  } else throw new Error(&quot;Image has neither bytes nor URL&quot;);\n  if(!raw.length) throw new Error(&quot;Empty image result&quot;);\n  const ext=raw.subarray(0,4).equals(Buffer.from([137,80,78,71]))?&quot;png&quot;:raw[0]===255&amp;&amp;raw[1]===216?&quot;jpg&quot;:raw.toString(&quot;ascii&quot;,0,4)===&quot;RIFF&quot;&amp;&amp;raw.toString(&quot;ascii&quot;,8,12)===&quot;WEBP&quot;?&quot;webp&quot;:raw.toString(&quot;utf8&quot;).trimStart().startsWith(&quot;&lt;svg&quot;)||raw.toString(&quot;utf8&quot;).trimStart().startsWith(&quot;&lt;?xml&quot;)?&quot;svg&quot;:&quot;bin&quot;;\n  writeFileSync(`image-${index}.${ext}`,raw);\n}\nconsole.log(&quot;Every returned image saved; sdk-result.json retains complete metadata&quot;);\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">結果を受け取って保存</h3><h4>Ailoot · 画像</h4><p class=\"note-s\">返された画像をすべてダウンロードするか、Base64の内容を保存</p><ul class=\"card-result-paths\"><li><code>GET /v1/media/tasks/{task_id}</code></li><li><code>GET /v1/media/assets/{asset_id}/content</code></li><li><code>GET /v1/media/assets</code></li><li><code>GET /v1/media/assets/{asset_id}</code></li></ul><div class=\"card-result-process\" data-all-results><h5>完了した結果をすべて保存</h5><p class=\"note-s\">完了した画像をすべて保存してください。返された各URLから取得するか、Base64の内容をデコードしてください。</p><p class=\"note-s\">すべてのデータ項目を保存してください。各 b64_json をデコードするか、返された署名付き URL すべてから取得してください。実際の MIME タイプ／バイト列に応じてファイル名の拡張子を選んでください。</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>元のレスポンスを確認する場合</h5><p class=\"note-s\">画像の生成または編集の結果に確認が必要な場合は、元の operation_id/X-Client-Request-ID と、返された結果情報を保存してください。実際の task_id または asset_id の値を使い、メディアライブラリから自分が所有する既存の結果を取得してください。生成／編集リクエストを再送したり、operation_id からポーリング URL を組み立てたりしないでください。</p></div><details class=\"card-about\" data-output-fields><summary>レスポンスのフィールド</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>フィールド</th><th>種類</th></tr></thead><tbody><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">created</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span>integer</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">data[].url</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span>string</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">data[].b64_json</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span>base64 string</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>エラーと次の手順</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>レスポンス</th><th>条件</th><th>次の手順</th></tr></thead><tbody><tr><th data-cell-label=\"レスポンス\" scope=\"row\"><span class=\"card-cell-label\">レスポンス</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"条件\"><span class=\"card-cell-label\">条件</span>必須フィールド、素材の表現形式、またはパラメーター値が不正です</td><td data-cell-label=\"次の手順\"><span class=\"card-cell-label\">次の手順</span>新しい生成リクエストを送る前に、指定されたフィールドを修正してください。</td></tr><tr><th data-cell-label=\"レスポンス\" scope=\"row\"><span class=\"card-cell-label\">レスポンス</span><code>server_error</code></th><td data-cell-label=\"条件\"><span class=\"card-cell-label\">条件</span>返されたレスポンスは、操作または結果の確認が必要であることを示しています</td><td data-cell-label=\"次の手順\"><span class=\"card-cell-label\">次の手順</span>最初に返された操作／タスク ID、リクエストヘッダー、レスポンスを保存し、その元の操作に対してサポートされている読み取りを継続してください。作成リクエストを再送しないでください。</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">エイリアス</h3><h4>モデルのエイリアス</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=openai%2Fgpt-image-2&amp;route=Core&amp;caller=gpt-image-2&amp;fmt=images\"><code>gpt-image-2</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=openai%2Fgpt-image-2&amp;route=Ultra&amp;caller=gpt-image-2&amp;fmt=images\"><code>gpt-image-2</code></a>, <a href=\"#m=openai%2Fgpt-image-2&amp;route=Ultra&amp;caller=openai%2Fgpt-image-2&amp;fmt=images\"><code>openai/gpt-image-2</code></a></span></p><h4>メソッドパスのエイリアス</h4><p class=\"note-s\"><code>/v1/images</code></p><h4>関連する呼び出し用ID</h4><p class=\"note-s\"><a href=\"#m=openai%2Fgpt-image-2&amp;route=Ultra&amp;caller=openai%2Fgpt-image-2&amp;fmt=images\"><code>openai/gpt-image-2</code></a>, <a href=\"#m=openai%2Fgpt-image-2&amp;route=Core&amp;caller=gpt-image-2&amp;fmt=images\"><code>gpt-image-2</code></a>, <a href=\"#m=openai%2Fgpt-image-2&amp;route=Ultra&amp;caller=gpt-image-2&amp;fmt=images\"><code>gpt-image-2</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "gpt-image-2",
        "fmt": "images",
        "http": "POST",
        "path": "/v1/images/generations",
        "request_model_id": "gpt-image-2",
        "route_label": "Core"
      },
      "method_key": "Core|images|/v1/images/generations|gpt-image-2",
      "ordinal": 0,
      "rawMethod": {
        "cache_read": null,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Save every data item. Decode each b64_json or fetch every returned signed URL. Select a filename extension from the actual MIME/bytes.",
            "errors": [
              {
                "code": null,
                "condition": "必須フィールド、素材の表現形式、またはパラメーター値が不正です",
                "http_status": 400,
                "recovery": "新しい生成リクエストを送る前に、指定されたフィールドを修正してください。",
                "type": "invalid_request_error"
              },
              {
                "code": null,
                "condition": "返されたレスポンスは、操作または結果の確認が必要であることを示しています",
                "http_status": null,
                "recovery": "最初に返された操作／タスク ID、リクエストヘッダー、レスポンスを保存し、その元の操作に対してサポートされている読み取りを継続してください。作成リクエストを再送しないでください。",
                "type": "server_error"
              }
            ],
            "hints": [],
            "ignored_fields": [],
            "lifecycle": {
              "all_results": "Follow everyactualreturnedoutputandownedasset; no result is discardedbecauseindex0orcontent_urlalreadyexists.",
              "assets": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets"
                },
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}"
                }
              ],
              "content": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}/content",
                  "url_source": "exact returned signed URL; never construct token"
                }
              ],
              "mode": "synchronous_result_then_owned_library",
              "operation_id_is_not_task_id": true,
              "status": [
                {
                  "http": "GET",
                  "id_source": "actual returned task_id or media library record",
                  "path": "/v1/media/tasks/{task_id}"
                }
              ],
              "unknown": "画像の生成または編集の結果に確認が必要な場合は、元の operation_id/X-Client-Request-ID と、返された結果情報を保存してください。実際の task_id または asset_id の値を使い、メディアライブラリから自分が所有する既存の結果を取得してください。生成／編集リクエストを再送したり、operation_id からポーリング URL を組み立てたりしないでください。"
            },
            "material_combinations": [
              {
                "content_types": [
                  "application/json",
                  "multipart/form-data"
                ],
                "file_id_supported": false,
                "mode": "text_to_image",
                "multipart_part_read_limit_bytes": 20971520,
                "optional_mask": {
                  "json": "mask.image_url",
                  "multipart": "mask"
                },
                "reference_representations": {
                  "json": "images[].image_url",
                  "multipart": [
                    "image",
                    "image[]",
                    "image[index]"
                  ]
                },
                "required": [
                  "prompt"
                ]
              }
            ],
            "media_library": {
              "asset": {
                "fields": [
                  {
                    "description": null,
                    "name": "asset_id",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "task_id",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "output_key",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "family",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "model",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "method",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "status",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "content_type",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "sha256",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "size_bytes",
                    "type": "integer"
                  },
                  {
                    "description": null,
                    "name": "content_url",
                    "type": "string"
                  }
                ],
                "http": "GET",
                "id_source": "actual returned asset_id",
                "path": "/v1/media/assets/{asset_id}"
              },
              "content": {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}/content",
                "range_header_supported": true,
                "url_source": "Use exact returned signed content_url including its token; do not construct a token."
              },
              "expired_link": {
                "code": "link_expired",
                "http_status": 404,
                "recovery": "Read the asset again to obtain its refreshed signed content_url, then fetch that URL. Do not regenerate."
              },
              "list": {
                "all_pages": "Follow every returned next_cursor, then select records by their actual task_id/output_key.",
                "http": "GET",
                "output_fields": [
                  {
                    "description": null,
                    "name": "object",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "data",
                    "type": "asset[]"
                  },
                  {
                    "description": null,
                    "name": "next_cursor",
                    "type": "string|null"
                  }
                ],
                "parameters": [
                  {
                    "availability": "source_interface",
                    "default": null,
                    "default_known": false,
                    "enum": null,
                    "enum_known": false,
                    "name": "family",
                    "required": false,
                    "type": "string"
                  },
                  {
                    "availability": "source_interface",
                    "default": null,
                    "default_known": false,
                    "enum": null,
                    "enum_known": false,
                    "name": "cursor",
                    "required": false,
                    "type": "string"
                  },
                  {
                    "availability": "source_interface",
                    "default": 20,
                    "default_known": true,
                    "enum": null,
                    "enum_known": false,
                    "maximum": 100,
                    "minimum": 1,
                    "name": "limit",
                    "required": false,
                    "type": "integer"
                  }
                ],
                "path": "/v1/media/assets"
              },
              "revoke": {
                "http": "DELETE",
                "meaning": "Revokes/deletes the existing owned file; this is not generation cancellation.",
                "path": "/v1/media/assets/{asset_id}",
                "pending_status": "revoking",
                "success_statuses": [
                  202,
                  204
                ]
              },
              "task": {
                "http": "GET",
                "id_source": "actual returned task_id or media library record; operation_id is not task_id",
                "path": "/v1/media/tasks/{task_id}"
              }
            },
            "operation_modes": [
              "text_to_image"
            ],
            "outputs": {
              "all_results": "すべてのデータ項目を保存してください。各 b64_json をデコードするか、返された署名付き URL すべてから取得してください。実際の MIME タイプ／バイト列に応じてファイル名の拡張子を選んでください。",
              "family": "image",
              "fields": [
                {
                  "description": null,
                  "name": "created",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "data[].url",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "data[].b64_json",
                  "type": "base64 string"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "actual validated raster MIME"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "gpt-image-2"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_length": 1,
                "name": "prompt",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": 1,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "n",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "url",
                  "b64_json"
                ],
                "enum_known": true,
                "name": "response_format",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "size",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "quality",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "background",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_format",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_compression",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "moderation",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input_fidelity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "style",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "partial_images",
                "required": false,
                "type": "integer"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": [
              "images[].file_id",
              "mask.file_id"
            ]
          },
          "hints": [
            "メソッドの形式とIDは正確に記載しています。供給元の対応能力とリクエストの受け入れは別です。"
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "prompt"
            ]
          },
          "lifecycle": {
            "assets": [
              {
                "http": "GET",
                "path": "/v1/media/assets"
              },
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}"
              }
            ],
            "content": [
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}/content",
                "url_source": "exact returned signed URL; never construct token"
              }
            ],
            "mode": "synchronous_result_then_owned_library",
            "operation_id_is_not_task_id": true,
            "status": [
              {
                "http": "GET",
                "id_source": "実際に返された task_id またはメディアライブラリのレコード",
                "path": "/v1/media/tasks/{task_id}"
              }
            ],
            "unknown": "If an image generation or edit result requires a check, keep the original operation_id/X-Client-Request-ID and returned result information. Recover existing owned results through the media library using actual task_id or asset_id values. Do not resubmit the generation/edit request or construct a polling URL from operation_id."
          },
          "method": {
            "http": "POST",
            "path": "/v1/images/generations"
          },
          "operation_modes": [
            "images"
          ],
          "output": {
            "family": [
              "image"
            ],
            "format": null,
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": null,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\nexport AILOOT_API_KEY\n: \"${AILOOT_PROMPT_FILE:?Set your actual UTF-8 image brief}\"\nexport AILOOT_PROMPT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"gpt-image-2\", \"prompt\": \"\"}')\nf=Path(os.environ[\"AILOOT_PROMPT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 brief\")\np['prompt']=f.read_text(encoding=\"utf-8\")\nif not p['prompt'].strip():raise SystemExit(\"Brief must contain text\")\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n    if not items: raise SystemExit(\"No completed images; retain the full response\")\n    for index, item in enumerate(items):\n        encoded=item.get(\"b64_json\")\n        uri=item.get(\"url\", \"\")\n        if not encoded and uri.startswith(\"data:image/\"):\n            header, separator, encoded=uri.partition(\",\")\n            if not separator or \";base64\" not in header: raise SystemExit(\"Unsupported image data URI\")\n        if encoded:\n            raw=base64.b64decode(encoded,validate=True)\n        elif uri:\n            uri=urljoin(\"https://api.ailoot.ai\",uri)\n            parsed=urlsplit(uri)\n            if parsed.scheme!=\"https\" or not parsed.netloc or parsed.username or parsed.password:\n                raise SystemExit(\"Invalid returned image URL\")\n            owned=parsed.netloc==\"api.ailoot.ai\" and parsed.path.startswith(\"/v1/media/assets/\") and parsed.path.endswith(\"/content\")\n            args=[\"curl\",\"--fail-with-body\",\"--silent\",\"--show-error\",uri]\n            if owned: args += [\"-H\",\"Authorization: Bearer \"+os.environ[\"AILOOT_API_KEY\"]]\n            temporary=Path(f\"image-{index}.bin\")\n            subprocess.run(args+[\"-o\",str(temporary)],check=True)\n            raw=temporary.read_bytes()\n            temporary.unlink()\n        else: raise SystemExit(\"Image has neither bytes nor URL\")\n        if not raw: raise SystemExit(\"Empty image result\")\n        ext=\"png\" if raw.startswith(b\"\\x89PNG\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else \"svg\" if raw.lstrip().startswith((b\"<svg\",b\"<?xml\")) else \"bin\"\n        Path(f\"image-{index}.{ext}\").write_bytes(raw)\n    print(\"Every returned image saved; complete response metadata retained\")\nsave_images(json.loads(Path(\"result.json\").read_text())[\"data\"])\nPY_RESULT\n",
            "label": "Create and save every image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n    if not items: raise SystemExit(\"No completed images; retain the full response\")\n    for index, item in enumerate(items):\n        encoded=item.get(\"b64_json\")\n        uri=item.get(\"url\", \"\")\n        if not encoded and uri.startswith(\"data:image/\"):\n            header, separator, encoded=uri.partition(\",\")\n            if not separator or \";base64\" not in header: raise SystemExit(\"Unsupported image data URI\")\n        if encoded:\n            raw=base64.b64decode(encoded,validate=True)\n        elif uri:\n            uri=urljoin(\"https://api.ailoot.ai\",uri)\n            parsed=urlsplit(uri)\n            if parsed.scheme!=\"https\" or not parsed.netloc or parsed.username or parsed.password:\n                raise SystemExit(\"Invalid returned image URL\")\n            owned=parsed.netloc==\"api.ailoot.ai\" and parsed.path.startswith(\"/v1/media/assets/\") and parsed.path.endswith(\"/content\")\n            args=[\"curl\",\"--fail-with-body\",\"--silent\",\"--show-error\",uri]\n            if owned: args += [\"-H\",\"Authorization: Bearer \"+os.environ[\"AILOOT_API_KEY\"]]\n            temporary=Path(f\"image-{index}.bin\")\n            subprocess.run(args+[\"-o\",str(temporary)],check=True)\n            raw=temporary.read_bytes()\n            temporary.unlink()\n        else: raise SystemExit(\"Image has neither bytes nor URL\")\n        if not raw: raise SystemExit(\"Empty image result\")\n        ext=\"png\" if raw.startswith(b\"\\x89PNG\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else \"svg\" if raw.lstrip().startswith((b\"<svg\",b\"<?xml\")) else \"bin\"\n        Path(f\"image-{index}.{ext}\").write_bytes(raw)\n    print(\"Every returned image saved; complete response metadata retained\")\n\nf=Path(os.environ[\"AILOOT_PROMPT_FILE\"])\nif not f.is_file():raise SystemExit(\"Set your actual UTF-8 image brief file\")\nrequest={'model': 'gpt-image-2', 'prompt': ''}\nrequest[\"prompt\"]=f.read_text(encoding=\"utf-8\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.images.generate(**request)\nPath(\"sdk-result.txt\").write_text(str(result),encoding=\"utf-8\")\nsave_images([{\"b64_json\":getattr(item,\"b64_json\",None),\"url\":getattr(item,\"url\",None)} for item in result.data])\n",
            "label": "Python SDK · save all image outputs",
            "language": "python"
          },
          {
            "code": "import OpenAI from \"openai\";\nimport { readFileSync, writeFileSync } from \"node:fs\";\nconst key=process.env.AILOOT_API_KEY;\nif(!key) throw new Error(\"Set your actual Ailoot API key\");\nconst client=new OpenAI({baseURL:\"https://api.ailoot.ai/v1\",apiKey:key,maxRetries:0});\nconst request={\"model\": \"gpt-image-2\", \"prompt\": \"\"};\nif(!process.env.AILOOT_PROMPT_FILE)throw new Error(\"Set your actual UTF-8 image brief file\");\nrequest.prompt=readFileSync(process.env.AILOOT_PROMPT_FILE,\"utf8\");\nconst result=await client.images.generate(request);\nwriteFileSync(\"sdk-result.json\",JSON.stringify(result,null,2));\nif(!result.data?.length) throw new Error(\"No completed images\");\nfor(let index=0;index<result.data.length;index++) {\n  const item=result.data[index];let encoded=item.b64_json,uri=item.url||\"\",raw;\n  if(!encoded && uri.startsWith(\"data:image/\")) {\n    const comma=uri.indexOf(\",\");if(comma<0 || !uri.slice(0,comma).includes(\";base64\")) throw new Error(\"Unsupported image data URI\");\n    encoded=uri.slice(comma+1);\n  }\n  if(encoded) {\n    if(encoded.length%4!==0 || !/^[A-Za-z0-9+/]*={0,2}$/.test(encoded)) throw new Error(\"Invalid Base64\");\n    raw=Buffer.from(encoded,\"base64\");\n  } else if(uri) {\n    const u=new URL(uri,\"https://api.ailoot.ai\");\n    if(u.protocol!==\"https:\" || u.username || u.password) throw new Error(\"Invalid returned URL\");\n    const owned=u.origin===\"https://api.ailoot.ai\" && u.pathname.startsWith(\"/v1/media/assets/\") && u.pathname.endsWith(\"/content\");\n    const response=await fetch(u,{headers:owned?{Authorization:\"Bearer \"+key}:{},redirect:\"manual\"});\n    if(!response.ok) throw new Error(\"Image content download failed: \"+response.status);\n    raw=Buffer.from(await response.arrayBuffer());\n  } else throw new Error(\"Image has neither bytes nor URL\");\n  if(!raw.length) throw new Error(\"Empty image result\");\n  const ext=raw.subarray(0,4).equals(Buffer.from([137,80,78,71]))?\"png\":raw[0]===255&&raw[1]===216?\"jpg\":raw.toString(\"ascii\",0,4)===\"RIFF\"&&raw.toString(\"ascii\",8,12)===\"WEBP\"?\"webp\":raw.toString(\"utf8\").trimStart().startsWith(\"<svg\")||raw.toString(\"utf8\").trimStart().startsWith(\"<?xml\")?\"svg\":\"bin\";\n  writeFileSync(`image-${index}.${ext}`,raw);\n}\nconsole.log(\"Every returned image saved; sdk-result.json retains complete metadata\");\n",
            "label": "Node SDK · save all image outputs",
            "language": "js"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "images",
        "http": "POST",
        "img_in": 4,
        "img_out": 15,
        "in": 2.5,
        "input": [
          "text"
        ],
        "label": "画像",
        "max_out": null,
        "max_tool_calls": null,
        "out": 0,
        "output": [
          "image"
        ],
        "path": "/v1/images/generations",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 2.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 4,
                "amount_unit": "usd_per_million_tokens",
                "key": "img_in",
                "label": "Image input",
                "side": "in"
              },
              {
                "amount": 15,
                "amount_unit": "usd_per_million_tokens",
                "key": "img_out",
                "label": "Image output",
                "side": "out"
              }
            ]
          }
        ],
        "request_model_id": "gpt-image-2",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">O</span><h2 id=\"sheet-title\">OpenAI: GPT Image 2</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"閉じる\">×</button></div><div class=\"idline\"><span>OpenAI /</span><code>gpt-image-2</code><button type=\"button\" id=\"copy-id\">IDをコピー</button></div><nav class=\"card-jump-nav\" aria-label=\"モデルカードのセクション\"><button type=\"button\" data-card-jump=\"overview\">はじめに</button><button type=\"button\" data-card-jump=\"methods\">入力とメソッド</button><button type=\"button\" data-card-jump=\"pricing\">料金</button><button type=\"button\" data-card-jump=\"examples\">例</button><button type=\"button\" data-card-jump=\"results\">結果</button><button type=\"button\" data-card-jump=\"aliases\">エイリアス</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"APIメソッド\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|images|/v1/images/generations|gpt-image-2\">画像</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-1\" data-card-method=\"Ultra|images|/v1/images/generations|gpt-image-2\">画像 · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">モデルID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Ultra|images|/v1/images/generations|gpt-image-2\" selected>gpt-image-2</option><option value=\"Ultra|images|/v1/images/generations|openai%2Fgpt-image-2\">openai/gpt-image-2</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-1\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">はじめに</h3><p class=\"mdesc-full\">GPT Image 2は、テキストと視覚参照から画像を生成・編集します。柔軟なフレーム寸法に対応し、すべての画像入力を自動で高忠実度処理します。完成素材の品質、形式、背景は個別に制御できます。</p><dl class=\"card-io\" data-card-io><div><dt>対応する入力</dt><dd>テキスト</dd></div><div><dt>結果</dt><dd>画像</dd></div></dl><details class=\"card-about\"><summary>モデルについて</summary><p class=\"note-s\" data-model-method-boundary>この説明はモデルの機能を紹介するものです。Ailootで利用できる入力、出力、オプションは、選択したメソッドごとに以下に記載されています。</p><div class=\"mabout\" id=\"m-about\"><p>GPT Image 2は、テキストと視覚入力から画像を生成・編集するOpenAIのモデルです。文章の制作指示から新しい画像を作り、編集や参照中心の制作には原画像を使えます。イラスト、商品コンセプト、視覚的な構図、既存素材の変更などが実用例です。GPT Image 2.5 SunburstやFlareとは別のエディションで、固有の品質範囲と入力忠実度の動作を持ちます。</p><p>生成では、被写体、シーン、構図、光、意図したスタイルを記述します。編集では変えるものと外観を維持するものを指定します。商品制作なら、淡い面に置いた陶器のランプ、中央の輪郭、キャプション用の余白を依頼し、追加編集でランプの形と視点を保ちながら背景を変えられます。記載された直接の生成・編集ワークフローは最大32,000文字のプロンプトを受け付け、1～10枚の画像を返せます。</p><p>参照を使う編集は最大16枚の入力画像に対応します。被写体、背景、視覚表現が混同されないよう、各参照の目的を指定します。GPT Image 2はすべての画像入力を自動で高忠実度処理します。このエディションでは調整できないため、input_fidelityは省略します。これはGPT Image 1のhighまたはlowの選択や、GPT Image 1 Miniのlow限定の入力忠実度とは異なります。高忠実度の入力処理は原素材の細部を支えますが、すべての細部が変わらず再現される保証ではありません。</p><p>マスクで編集領域を示せます。ガイドの準備要件では、原画像とマスクは同じ形式と寸法で、50 MB未満である必要があります。マスクにはアルファチャンネルも必要です。複数の入力画像がある場合、マスクは最初の画像に適用されます。モデルはマスクを厳密な幾何学的境界ではなく、プロンプトに基づく誘導として扱います。局所的な変更と維持要件を記述し、周囲に意図しない差異がないかを確認します。</p><p>GPT Image 2はlow、medium、high、autoの品質に対応し、標準はautoです。2.5ファミリーのxhighとmaxは、このエディションの品質範囲に含まれません。サイズは正方形、横長、縦長、自動、または有効な独自の幅と高さを選べます。開発元の例は1024 × 1024、1536 × 1024、1024 × 1536、2048 × 2048、2048 × 1152、3840 × 2160、2160 × 3840ピクセルです。品質と寸法を同じ制御として扱わず、実際のレイアウトに合う向きと細部の水準を選びます。</p><p>独自寸法は16ピクセルの倍数、最大辺3840ピクセル、長辺対短辺の比率3:1以下、面積655,360～8,294,400ピクセルが条件です。これらは同時に適用されます。2560 × 1440を超える解像度は実験的とされています。一つの条件を満たすフレームでも別の条件に違反し得るため、有効な縦横寸法の組み合わせを選び、切り取りで失いたくない要素を制作指示に記述します。</p><p>出力の標準はPNGで、JPEGとWebPも利用できます。JPEGとWebPは0～100の圧縮値に対応します。背景は不透明または自動を選べます。現在の個別仕様は、GPT Image 2の透明背景をプレビュー機能として説明しています。透明背景を依頼する場合は、アルファチャンネルを保持できるPNGまたはWebPを使います。記載されたストリーミングは、完成画像の前に最大3枚の部分画像を送れます。進捗プレビューではなく最終素材を保存してください。開発元のインターフェースはバッチ処理にも対応します。</p><p>実際の結果で、文字の明瞭さ、物体の位置、原素材の細部の維持を評価します。GPT Imageは、正確な文字、レイアウトに敏感な構図、別々の生成で視覚的特徴を繰り返し保つことが難しい場合があります。編集を続ける場合は採用した結果を次の原画像に使い、目に見える問題に結びつく具体的な変更を指定します。GPT Image 2の有用な出力は、明確な生成・編集指示に結びついた画像です。その作業に合わせて高忠実度入力、寸法、品質を選びます。</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailootで利用可能 · 入力とメソッド</h3><details class=\"card-method\" open><summary><b>Ailoot Ultra · 画像</b> <code>POST /v1/images/generations</code></summary><dl class=\"method-capabilities\"><div><dt>入力の種類</dt><dd><code>text</code></dd></div><div><dt>出力の種類</dt><dd><code>image</code></dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>フィールド</th><th>種類</th><th>要件</th><th>値と制限</th><th>デフォルト</th></tr></thead><tbody><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>必須</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>gpt-image-2</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">prompt</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>必須</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>最大の長さ: 32,000</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">size</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>条件: autoまたはWIDTHxHEIGHTを使用し、幅と高さの両方を16で割り切れる値にしてください。長辺は最大3,840ピクセル、総画素数は最大8,300,000ピクセルです。</div></td><td data-cell-label=\"デフォルト\" data-default=\"known\"><span class=\"card-cell-label\">デフォルト</span>auto</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">background</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>transparent, opaque, auto</div></td><td data-cell-label=\"デフォルト\" data-default=\"known\"><span class=\"card-cell-label\">デフォルト</span>auto</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">moderation</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>low, auto</div><div>条件: 標準のコンテンツモデレーションにはautoを使用してください。</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">n</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>integer</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>最小値: 1</div><div>最大値: 10</div></td><td data-cell-label=\"デフォルト\" data-default=\"known\"><span class=\"card-cell-label\">デフォルト</span>1</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">quality</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>auto, high, medium, low</div></td><td data-cell-label=\"デフォルト\" data-default=\"known\"><span class=\"card-cell-label\">デフォルト</span>auto</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">output_compression</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>integer</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>最小値: 0</div><div>最大値: 100</div><div>条件: JPEGとWebPの出力に適用されます。文書に記載された整数値を送信してください。</div></td><td data-cell-label=\"デフォルト\" data-default=\"known\"><span class=\"card-cell-label\">デフォルト</span>100</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">output_format</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>webp, png, jpeg</div></td><td data-cell-label=\"デフォルト\" data-default=\"known\"><span class=\"card-cell-label\">デフォルト</span>png</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>boolean</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>false</div><div>条件: このルートは、完了したJSONレスポンスを一件返します。</div></td><td data-cell-label=\"デフォルト\" data-default=\"known\"><span class=\"card-cell-label\">デフォルト</span>false</td></tr></tbody></table></div><details class=\"note-s\" data-method-contract><summary>メソッドのパラメータとライフサイクル</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>パラメータ</th><th>仕様</th></tr></thead><tbody><tr><th data-cell-label=\"パラメータ\" scope=\"row\"><span class=\"card-cell-label\">パラメータ</span><code>content_type</code></th><td data-cell-label=\"仕様\"><span class=\"card-cell-label\">仕様</span>application/json</td></tr><tr><th data-cell-label=\"パラメータ\" scope=\"row\"><span class=\"card-cell-label\">パラメータ</span><code>required</code></th><td data-cell-label=\"仕様\"><span class=\"card-cell-label\">仕様</span>prompt, model</td></tr><tr><th data-cell-label=\"パラメータ\" scope=\"row\"><span class=\"card-cell-label\">パラメータ</span><code>material_types</code></th><td data-cell-label=\"仕様\"><span class=\"card-cell-label\">仕様</span>text</td></tr><tr><th data-cell-label=\"パラメータ\" scope=\"row\"><span class=\"card-cell-label\">パラメータ</span><code>optional</code></th><td data-cell-label=\"仕様\"><span class=\"card-cell-label\">仕様</span>size, background, moderation, n, quality, output_compression, output_format, stream</td></tr><tr><th data-cell-label=\"パラメータ\" scope=\"row\"><span class=\"card-cell-label\">パラメータ</span><code>conditions</code></th><td data-cell-label=\"仕様\"><span class=\"card-cell-label\">仕様</span>透過背景にはPNGまたはWebPが必要です。, 出力圧縮はJPEGまたはWebPに適用されます。, 選択したメソッドはテキストから生成します。メーカーの説明に記載されている編集およびストリーミングの制御は、別の機能です。</td></tr></tbody></table></div><p>ライフサイクル: <code>synchronous_result_then_owned_library</code></p><p class=\"note-s\"><code>GET /v1/media/tasks/{task_id}</code> · 実際に返された task_id またはメディアライブラリのレコード</p><p class=\"note-s\"><code>GET /v1/media/assets/{asset_id}/content</code></p><p class=\"note-s\"><code>GET /v1/media/assets</code></p><p class=\"note-s\"><code>GET /v1/media/assets/{asset_id}</code></p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">料金</h3><div class=\"card-result-process\" data-billing-basis><h5>最終料金の計算方法</h5><p class=\"note-s\">表示料金は生成前の費用の見積もりです。最終請求額は、元の生成処理に記録された費用から計算されます。実測された出力時間や予測数量が、そのまま最終的な課金数量になるわけではありません。</p></div><div data-native-semantic-method=\"v1\" data-tariff-reference-only><p class=\"note-s\" data-rate-support-note>料金情報はリクエストの機能を追加しません。対応するパラメーターは選択したメソッドに記載されています。</p><dl data-price-conditions><dt>高速モード</dt><dd>未指定 <span class=\"note-s\">高速モードが選択されている場合</span></dd><dt>Flex モード</dt><dd>未指定 <span class=\"note-s\">flex モードが選択されている場合</span></dd><dt>最大推論量</dt><dd>未指定 <span class=\"note-s\">推論量が最大で、調整に既定値（default）を使用する場合</span></dd></dl></div><div data-declared-tariff-pricing><h4>比較用の推定料金</h4><h4>設定別の価格</h4><p class=\"note-s\">各料金を表示された条件と照合してください。選択肢となる設定の各組には、いずれか1つの料金を適用します。</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>設定</th><th>料金表</th><th>予測数量</th><th>料金</th></tr></thead><tbody><tr><th data-cell-label=\"設定\" scope=\"row\"><span class=\"card-cell-label\">設定</span>基本トークン料金</th><td data-cell-label=\"料金表\"><span class=\"card-cell-label\">料金表</span>基本料金</td><td data-cell-label=\"予測数量\"><span class=\"card-cell-label\">予測数量</span>—</td><td data-cell-label=\"料金\"><span class=\"card-cell-label\">料金</span><div><span>入力 · 入力トークン · 比較専用の見積もり</span> <b>—</b> <span class=\"price-unit\">/ 1K トークン</span></div><div><span>出力 · 出力トークン · 比較専用の見積もり</span> <b>—</b> <span class=\"price-unit\">/ 1K トークン</span></div><div><span>入力 · キャッシュ読み取り · 比較専用の見積もり</span> <b>—</b> <span class=\"price-unit\">/ 1K トークン</span></div><div><span>入力 · キャッシュ書き込み · 比較専用の見積もり</span> <b>—</b> <span class=\"price-unit\">/ 1K トークン</span></div><div><span>入力 · キャッシュ書き込み、1時間 · 比較専用の見積もり</span> <b>—</b> <span class=\"price-unit\">/ 1K トークン</span></div></td></tr><tr><th data-cell-label=\"設定\" scope=\"row\"><span class=\"card-cell-label\">設定</span>生成費用の見積もり</th><td data-cell-label=\"料金表\"><span class=\"card-cell-label\">料金表</span>—</td><td data-cell-label=\"予測数量\"><span class=\"card-cell-label\">予測数量</span>生成1回分の概算</td><td data-cell-label=\"料金\"><span class=\"card-cell-label\">料金</span><div><span>出力 · 推定生成コスト · 比較専用の見積もり</span> <b>$0.24576</b> <span class=\"price-unit\">生成前の見積もり</span></div><p class=\"note-s\">この見積もりは追加料金ではなく、完了した生成処理に対する固定料金でもありません。</p></td></tr></tbody></table></div></div><p class=\"note-s\">Ailootはリクエスト前に見積額を確保します。結果の取得後、実測使用量に基づいて最終料金を精算します。ストリーミング時の精算には最終の使用量記録を使用します。<a href=\"/docs/ja/billing/reserve/\">金額の確保と精算の仕組み →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">リクエスト例</h3><h4>Ailoot Ultra · 画像</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"コードの種類\"><button class=\"cg-tab\" id=\"model-code-643-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-643-panel-0\" aria-selected=\"true\" tabindex=\"0\">curl</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"コードをコピー\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-643-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-643-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\nexport AILOOT_API_KEY\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np={&#39;prompt&#39;: &#39;A cute baby sea otter&#39;, &#39;model&#39;: &#39;gpt-image-2&#39;, &#39;size&#39;: &#39;1024x1024&#39;, &#39;n&#39;: 1, &#39;background&#39;: &#39;auto&#39;, &#39;moderation&#39;: &#39;auto&#39;, &#39;output_format&#39;: &#39;png&#39;}\n\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n    if not items: raise SystemExit(&quot;No completed images; retain the full response&quot;)\n    for index, item in enumerate(items):\n        encoded=item.get(&quot;b64_json&quot;)\n        uri=item.get(&quot;url&quot;, &quot;&quot;)\n        if not encoded and uri.startswith(&quot;data:image/&quot;):\n            header, separator, encoded=uri.partition(&quot;,&quot;)\n            if not separator or &quot;;base64&quot; not in header: raise SystemExit(&quot;Unsupported image data URI&quot;)\n        if encoded:\n            raw=base64.b64decode(encoded,validate=True)\n        elif uri:\n            uri=urljoin(&quot;https://api.ailoot.ai&quot;,uri)\n            parsed=urlsplit(uri)\n            if parsed.scheme!=&quot;https&quot; or not parsed.netloc or parsed.username or parsed.password:\n                raise SystemExit(&quot;Invalid returned image URL&quot;)\n            owned=parsed.netloc==&quot;api.ailoot.ai&quot; and parsed.path.startswith(&quot;/v1/media/assets/&quot;) and parsed.path.endswith(&quot;/content&quot;)\n            args=[&quot;curl&quot;,&quot;--fail-with-body&quot;,&quot;--silent&quot;,&quot;--show-error&quot;,uri]\n            if owned: args += [&quot;-H&quot;,&quot;Authorization: Bearer &quot;+os.environ[&quot;AILOOT_API_KEY&quot;]]\n            temporary=Path(f&quot;image-{index}.bin&quot;)\n            subprocess.run(args+[&quot;-o&quot;,str(temporary)],check=True)\n            raw=temporary.read_bytes()\n            temporary.unlink()\n        else: raise SystemExit(&quot;Image has neither bytes nor URL&quot;)\n        if not raw: raise SystemExit(&quot;Empty image result&quot;)\n        ext=&quot;png&quot; if raw.startswith(b&quot;\\x89PNG&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else &quot;svg&quot; if raw.lstrip().startswith((b&quot;&lt;svg&quot;,b&quot;&lt;?xml&quot;)) else &quot;bin&quot;\n        Path(f&quot;image-{index}.{ext}&quot;).write_bytes(raw)\n    print(&quot;Every returned image saved; complete response metadata retained&quot;)\nsave_images(json.loads(Path(&quot;result.json&quot;).read_text())[&quot;data&quot;])\nPY_RESULT\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">結果を受け取って保存</h3><h4>Ailoot Ultra · 画像</h4><p class=\"note-s\">返された画像をすべてダウンロードするか、Base64の内容を保存</p><ul class=\"card-result-paths\"><li><code>GET /v1/media/tasks/{task_id}</code></li><li><code>GET /v1/media/assets/{asset_id}/content</code></li><li><code>GET /v1/media/assets</code></li><li><code>GET /v1/media/assets/{asset_id}</code></li></ul><details class=\"card-about\"><summary>その他のコンテンツ取得</summary><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"コードの種類\"><button class=\"cg-tab\" id=\"model-code-644-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-644-panel-0\" aria-selected=\"true\" tabindex=\"0\">自分が所有する既存のアセットを読み取る</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"コードをコピー\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-644-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-644-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -o owned-assets.json\n# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.\n</code></pre></div></div></div></details><div class=\"card-result-process\" data-all-results><h5>完了した結果をすべて保存</h5><p class=\"note-s\">完了した画像をすべて保存してください。返された各URLから取得するか、Base64の内容をデコードしてください。</p><p class=\"note-s\">レスポンスとヘッダーの全体、実際の出力すべて、最初に返された識別子、使用量フィールドすべてを保存してください。作成リクエストを再送せずに、元の操作を復旧してください。</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>元のレスポンスを確認する場合</h5><p class=\"note-s\">照合のため、返された X-Client-Request-ID を保存してください。実際に返された task_id/asset_id の値、または自分が所有するメディアライブラリだけを使って読み取ってください。操作 ID からタスクの URL を組み立てたり、作成リクエストを再送したりしないでください。</p></div><details class=\"card-about\" data-output-fields><summary>レスポンスのフィールド</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>フィールド</th><th>種類</th></tr></thead><tbody><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">created</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span></td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">data[].url</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span></td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">data[].b64_json</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span></td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span></td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">エイリアス</h3><h4>モデルのエイリアス</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=openai%2Fgpt-image-2&amp;route=Core&amp;caller=gpt-image-2&amp;fmt=images\"><code>gpt-image-2</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=openai%2Fgpt-image-2&amp;route=Ultra&amp;caller=gpt-image-2&amp;fmt=images\"><code>gpt-image-2</code></a>, <a href=\"#m=openai%2Fgpt-image-2&amp;route=Ultra&amp;caller=openai%2Fgpt-image-2&amp;fmt=images\"><code>openai/gpt-image-2</code></a></span></p><h4>メソッドパスのエイリアス</h4><p class=\"note-s\"><code>/v1/images</code></p><h4>関連する呼び出し用ID</h4><p class=\"note-s\"><a href=\"#m=openai%2Fgpt-image-2&amp;route=Ultra&amp;caller=openai%2Fgpt-image-2&amp;fmt=images\"><code>openai/gpt-image-2</code></a>, <a href=\"#m=openai%2Fgpt-image-2&amp;route=Core&amp;caller=gpt-image-2&amp;fmt=images\"><code>gpt-image-2</code></a>, <a href=\"#m=openai%2Fgpt-image-2&amp;route=Ultra&amp;caller=gpt-image-2&amp;fmt=images\"><code>gpt-image-2</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "gpt-image-2",
        "fmt": "images",
        "http": "POST",
        "path": "/v1/images/generations",
        "request_model_id": "gpt-image-2",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|images|/v1/images/generations|gpt-image-2",
      "ordinal": 1,
      "rawMethod": {
        "billing_basis": {
          "basis": "original_invoice_usd",
          "description": "表示料金は生成前の費用の見積もりです。最終請求額は、元の生成処理に記録された費用から計算されます。実測された出力時間や予測数量が、そのまま最終的な課金数量になるわけではありません。",
          "forecast_quantity_is_estimate": true,
          "physical_output_is_billable_quantity": false,
          "version": "original_invoice_usd_v1"
        },
        "cache_read": null,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.",
            "lifecycle": {
              "assets": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets"
                },
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}"
                }
              ],
              "content": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}/content",
                  "url_source": "exact returned signed URL; never construct token"
                }
              ],
              "mode": "synchronous_result_then_owned_library",
              "operation_id_is_not_task_id": true,
              "status": [
                {
                  "http": "GET",
                  "id_source": "actual returned task_id or media library record",
                  "path": "/v1/media/tasks/{task_id}"
                }
              ],
              "unknown": "照合のため、返された X-Client-Request-ID を保存してください。実際に返された task_id/asset_id の値、または自分が所有するメディアライブラリだけを使って読み取ってください。操作 ID からタスクの URL を組み立てたり、作成リクエストを再送したりしないでください。"
            },
            "outputs": {
              "all_results": "レスポンスとヘッダーの全体、実際の出力すべて、最初に返された識別子、使用量フィールドすべてを保存してください。作成リクエストを再送せずに、元の操作を復旧してください。",
              "family": "image",
              "fields": [
                {
                  "description": null,
                  "name": "created",
                  "type": null
                },
                {
                  "description": null,
                  "name": "data[].url",
                  "type": null
                },
                {
                  "description": null,
                  "name": "data[].b64_json",
                  "type": null
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": null
                }
              ]
            },
            "parameters": [
              {
                "enum": [
                  "gpt-image-2"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "maxLength": 32000,
                "maximum_length": 32000,
                "name": "prompt",
                "required": true,
                "type": "string"
              },
              {
                "conditions": "autoまたはWIDTHxHEIGHTを使用し、幅と高さの両方を16で割り切れる値にしてください。長辺は最大3,840ピクセル、総画素数は最大8,300,000ピクセルです。",
                "default": "auto",
                "default_known": true,
                "description": "Use auto or WIDTHxHEIGHT with both dimensions divisible by 16. The longest side is at most 3,840 pixels and total size at most 8,300,000 pixels.",
                "name": "size",
                "required": false,
                "type": "string"
              },
              {
                "default": "auto",
                "default_known": true,
                "enum": [
                  "transparent",
                  "opaque",
                  "auto"
                ],
                "enum_known": true,
                "name": "background",
                "required": false,
                "type": "string"
              },
              {
                "conditions": "標準のコンテンツモデレーションにはautoを使用してください。",
                "description": "Use auto for standard content moderation.",
                "enum": [
                  "low",
                  "auto"
                ],
                "enum_known": true,
                "name": "moderation",
                "required": false,
                "type": "string"
              },
              {
                "default": 1,
                "default_known": true,
                "maximum": 10,
                "minimum": 1,
                "name": "n",
                "required": false,
                "type": "integer"
              },
              {
                "default": "auto",
                "default_known": true,
                "enum": [
                  "auto",
                  "high",
                  "medium",
                  "low"
                ],
                "enum_known": true,
                "name": "quality",
                "required": false,
                "type": "string"
              },
              {
                "conditions": "JPEGとWebPの出力に適用されます。文書に記載された整数値を送信してください。",
                "default": 100,
                "default_known": true,
                "description": "Applies to JPEG and WebP output; send the documented integer value.",
                "maximum": 100,
                "minimum": 0,
                "name": "output_compression",
                "required": false,
                "type": "integer"
              },
              {
                "default": "png",
                "default_known": true,
                "enum": [
                  "webp",
                  "png",
                  "jpeg"
                ],
                "enum_known": true,
                "name": "output_format",
                "required": false,
                "type": "string"
              },
              {
                "conditions": "このルートは、完了したJSONレスポンスを一件返します。",
                "default": false,
                "default_known": true,
                "description": "This route returns one completed JSON response.",
                "enum": [
                  false
                ],
                "enum_known": true,
                "name": "stream",
                "required": false,
                "type": "boolean"
              }
            ],
            "request_schema": {
              "properties": {
                "background": {
                  "default": "auto",
                  "enum": [
                    "transparent",
                    "opaque",
                    "auto"
                  ],
                  "type": "string"
                },
                "model": {
                  "enum": [
                    "gpt-image-2"
                  ],
                  "type": "string"
                },
                "moderation": {
                  "description": "Use auto for standard content moderation.",
                  "enum": [
                    "low",
                    "auto"
                  ],
                  "type": "string"
                },
                "n": {
                  "default": 1,
                  "maximum": 10,
                  "minimum": 1,
                  "type": "integer"
                },
                "output_compression": {
                  "default": 100,
                  "description": "Applies to JPEG and WebP output; send the documented integer value.",
                  "maximum": 100,
                  "minimum": 0,
                  "type": "integer"
                },
                "output_format": {
                  "default": "png",
                  "enum": [
                    "webp",
                    "png",
                    "jpeg"
                  ],
                  "type": "string"
                },
                "prompt": {
                  "maxLength": 32000,
                  "type": "string"
                },
                "quality": {
                  "default": "auto",
                  "enum": [
                    "auto",
                    "high",
                    "medium",
                    "low"
                  ],
                  "type": "string"
                },
                "size": {
                  "default": "auto",
                  "description": "Use auto or WIDTHxHEIGHT with both dimensions divisible by 16. The longest side is at most 3,840 pixels and total size at most 8,300,000 pixels.",
                  "type": "string"
                },
                "stream": {
                  "default": false,
                  "description": "This route returns one completed JSON response.",
                  "enum": [
                    false
                  ],
                  "type": "boolean"
                }
              },
              "required": [
                "prompt",
                "model"
              ],
              "type": "object"
            },
            "schema_template": {
              "actual_file_preparation_required": false,
              "body": {
                "background": "auto",
                "model": "gpt-image-2",
                "moderation": "auto",
                "n": 1,
                "output_format": "png",
                "prompt": "A cute baby sea otter",
                "size": "1024x1024"
              },
              "content_type": "application/json"
            }
          },
          "input": {
            "conditions": [
              "透過背景にはPNGまたはWebPが必要です。",
              "出力圧縮はJPEGまたはWebPに適用されます。",
              "選択したメソッドはテキストから生成します。メーカーの説明に記載されている編集およびストリーミングの制御は、別の機能です。"
            ],
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional": [
              "size",
              "background",
              "moderation",
              "n",
              "quality",
              "output_compression",
              "output_format",
              "stream"
            ],
            "required": [
              "prompt",
              "model"
            ]
          },
          "lifecycle": {
            "assets": [
              {
                "http": "GET",
                "path": "/v1/media/assets"
              },
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}"
              }
            ],
            "content": [
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}/content",
                "url_source": "exact returned signed URL; never construct token"
              }
            ],
            "mode": "synchronous_result_then_owned_library",
            "operation_id_is_not_task_id": true,
            "status": [
              {
                "http": "GET",
                "id_source": "実際に返された task_id またはメディアライブラリのレコード",
                "path": "/v1/media/tasks/{task_id}"
              }
            ],
            "unknown": "Keep the returned X-Client-Request-ID for reconciliation. Read only actual returned task_id/asset_id values or the owned media library; never build a task URL from the operation ID and never resubmit creation."
          },
          "method": {
            "http": "POST",
            "path": "/v1/images/generations"
          },
          "output": {
            "all_results": "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.",
            "family": "image",
            "fields": [
              {
                "description": null,
                "name": "created",
                "type": null
              },
              {
                "description": null,
                "name": "data[].url",
                "type": null
              },
              {
                "description": null,
                "name": "data[].b64_json",
                "type": null
              },
              {
                "description": null,
                "name": "usage",
                "type": null
              }
            ]
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "basis": "この見積もりは追加料金ではなく、完了した生成処理に対する固定料金でもありません。",
            "dimensions": {
              "forecast_quantity": "one generation estimate"
            },
            "label": "生成費用の見積もり",
            "units": [
              {
                "amount": "0.24576",
                "amount_unit": "usd_per_exact_native_unit",
                "billing_input": false,
                "estimate_only": true,
                "key": "forecast_usd",
                "label": "Estimated generation cost",
                "native_amount_usd_per_unit": "0.24576",
                "native_quantity": 1,
                "public_unit_label": "estimate before generation",
                "quantity": 1,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "request_estimate"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np={'prompt': 'A cute baby sea otter', 'model': 'gpt-image-2', 'size': '1024x1024', 'n': 1, 'background': 'auto', 'moderation': 'auto', 'output_format': 'png'}\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n    if not items: raise SystemExit(\"No completed images; retain the full response\")\n    for index, item in enumerate(items):\n        encoded=item.get(\"b64_json\")\n        uri=item.get(\"url\", \"\")\n        if not encoded and uri.startswith(\"data:image/\"):\n            header, separator, encoded=uri.partition(\",\")\n            if not separator or \";base64\" not in header: raise SystemExit(\"Unsupported image data URI\")\n        if encoded:\n            raw=base64.b64decode(encoded,validate=True)\n        elif uri:\n            uri=urljoin(\"https://api.ailoot.ai\",uri)\n            parsed=urlsplit(uri)\n            if parsed.scheme!=\"https\" or not parsed.netloc or parsed.username or parsed.password:\n                raise SystemExit(\"Invalid returned image URL\")\n            owned=parsed.netloc==\"api.ailoot.ai\" and parsed.path.startswith(\"/v1/media/assets/\") and parsed.path.endswith(\"/content\")\n            args=[\"curl\",\"--fail-with-body\",\"--silent\",\"--show-error\",uri]\n            if owned: args += [\"-H\",\"Authorization: Bearer \"+os.environ[\"AILOOT_API_KEY\"]]\n            temporary=Path(f\"image-{index}.bin\")\n            subprocess.run(args+[\"-o\",str(temporary)],check=True)\n            raw=temporary.read_bytes()\n            temporary.unlink()\n        else: raise SystemExit(\"Image has neither bytes nor URL\")\n        if not raw: raise SystemExit(\"Empty image result\")\n        ext=\"png\" if raw.startswith(b\"\\x89PNG\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else \"svg\" if raw.lstrip().startswith((b\"<svg\",b\"<?xml\")) else \"bin\"\n        Path(f\"image-{index}.{ext}\").write_bytes(raw)\n    print(\"Every returned image saved; complete response metadata retained\")\nsave_images(json.loads(Path(\"result.json\").read_text())[\"data\"])\nPY_RESULT\n",
            "label": "curl · exact creation/save all outputs",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -o owned-assets.json\n# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.\n",
            "label": "Read existing owned assets",
            "language": "bash"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "images",
        "http": "POST",
        "in": null,
        "input": [
          "text"
        ],
        "label": "画像",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "out": null,
        "output": [
          "image"
        ],
        "path": "/v1/images/generations",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Not specified",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Not specified",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Not specified",
            "when": "When maximum reasoning effort uses the default adjustment"
          }
        ],
        "pricing": {
          "billing_mode": "original_invoice_usd",
          "image_input_price": null,
          "image_output_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "basis": "This estimate is not an additional charge or a fixed rate for the completed generation.",
            "dimensions": {
              "forecast_quantity": "one generation estimate"
            },
            "label": "Estimated generation cost",
            "units": [
              {
                "amount": "0.24576",
                "amount_unit": "usd_per_exact_native_unit",
                "billing_input": false,
                "estimate_only": true,
                "key": "forecast_usd",
                "label": "Estimated generation cost",
                "native_amount_usd_per_unit": "0.24576",
                "native_quantity": 1,
                "public_unit_label": "estimate before generation",
                "quantity": 1,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "request_estimate"
              }
            ]
          }
        ],
        "request_model_id": "gpt-image-2",
        "route_label": "Ultra",
        "status_reads": [
          "GET /v1/media/tasks/{task_id}"
        ],
        "tiers": [],
        "units": [
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          },
          {
            "amount": "0.24576",
            "amount_unit": "usd_per_exact_native_unit",
            "billing_input": false,
            "estimate_only": true,
            "key": "forecast_usd",
            "label": "Estimated generation cost",
            "native_amount_usd_per_unit": "0.24576",
            "native_quantity": 1,
            "public_unit_label": "estimate before generation",
            "quantity": 1,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "request_estimate"
          }
        ]
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">O</span><h2 id=\"sheet-title\">OpenAI: GPT Image 2</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"閉じる\">×</button></div><div class=\"idline\"><span>OpenAI /</span><code>openai/gpt-image-2</code><button type=\"button\" id=\"copy-id\">IDをコピー</button></div><nav class=\"card-jump-nav\" aria-label=\"モデルカードのセクション\"><button type=\"button\" data-card-jump=\"overview\">はじめに</button><button type=\"button\" data-card-jump=\"methods\">入力とメソッド</button><button type=\"button\" data-card-jump=\"pricing\">料金</button><button type=\"button\" data-card-jump=\"examples\">例</button><button type=\"button\" data-card-jump=\"results\">結果</button><button type=\"button\" data-card-jump=\"aliases\">エイリアス</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"APIメソッド\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|images|/v1/images/generations|gpt-image-2\">画像</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-1\" data-card-method=\"Ultra|images|/v1/images/generations|openai%2Fgpt-image-2\">画像 · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">モデルID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Ultra|images|/v1/images/generations|gpt-image-2\">gpt-image-2</option><option value=\"Ultra|images|/v1/images/generations|openai%2Fgpt-image-2\" selected>openai/gpt-image-2</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-1\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">はじめに</h3><p class=\"mdesc-full\">GPT Image 2は、テキストと視覚参照から画像を生成・編集します。柔軟なフレーム寸法に対応し、すべての画像入力を自動で高忠実度処理します。完成素材の品質、形式、背景は個別に制御できます。</p><dl class=\"card-io\" data-card-io><div><dt>対応する入力</dt><dd>テキスト · 画像</dd></div><div><dt>結果</dt><dd>画像</dd></div></dl><details class=\"card-about\"><summary>モデルについて</summary><p class=\"note-s\" data-model-method-boundary>この説明はモデルの機能を紹介するものです。Ailootで利用できる入力、出力、オプションは、選択したメソッドごとに以下に記載されています。</p><div class=\"mabout\" id=\"m-about\"><p>GPT Image 2は、テキストと視覚入力から画像を生成・編集するOpenAIのモデルです。文章の制作指示から新しい画像を作り、編集や参照中心の制作には原画像を使えます。イラスト、商品コンセプト、視覚的な構図、既存素材の変更などが実用例です。GPT Image 2.5 SunburstやFlareとは別のエディションで、固有の品質範囲と入力忠実度の動作を持ちます。</p><p>生成では、被写体、シーン、構図、光、意図したスタイルを記述します。編集では変えるものと外観を維持するものを指定します。商品制作なら、淡い面に置いた陶器のランプ、中央の輪郭、キャプション用の余白を依頼し、追加編集でランプの形と視点を保ちながら背景を変えられます。記載された直接の生成・編集ワークフローは最大32,000文字のプロンプトを受け付け、1～10枚の画像を返せます。</p><p>参照を使う編集は最大16枚の入力画像に対応します。被写体、背景、視覚表現が混同されないよう、各参照の目的を指定します。GPT Image 2はすべての画像入力を自動で高忠実度処理します。このエディションでは調整できないため、input_fidelityは省略します。これはGPT Image 1のhighまたはlowの選択や、GPT Image 1 Miniのlow限定の入力忠実度とは異なります。高忠実度の入力処理は原素材の細部を支えますが、すべての細部が変わらず再現される保証ではありません。</p><p>マスクで編集領域を示せます。ガイドの準備要件では、原画像とマスクは同じ形式と寸法で、50 MB未満である必要があります。マスクにはアルファチャンネルも必要です。複数の入力画像がある場合、マスクは最初の画像に適用されます。モデルはマスクを厳密な幾何学的境界ではなく、プロンプトに基づく誘導として扱います。局所的な変更と維持要件を記述し、周囲に意図しない差異がないかを確認します。</p><p>GPT Image 2はlow、medium、high、autoの品質に対応し、標準はautoです。2.5ファミリーのxhighとmaxは、このエディションの品質範囲に含まれません。サイズは正方形、横長、縦長、自動、または有効な独自の幅と高さを選べます。開発元の例は1024 × 1024、1536 × 1024、1024 × 1536、2048 × 2048、2048 × 1152、3840 × 2160、2160 × 3840ピクセルです。品質と寸法を同じ制御として扱わず、実際のレイアウトに合う向きと細部の水準を選びます。</p><p>独自寸法は16ピクセルの倍数、最大辺3840ピクセル、長辺対短辺の比率3:1以下、面積655,360～8,294,400ピクセルが条件です。これらは同時に適用されます。2560 × 1440を超える解像度は実験的とされています。一つの条件を満たすフレームでも別の条件に違反し得るため、有効な縦横寸法の組み合わせを選び、切り取りで失いたくない要素を制作指示に記述します。</p><p>出力の標準はPNGで、JPEGとWebPも利用できます。JPEGとWebPは0～100の圧縮値に対応します。背景は不透明または自動を選べます。現在の個別仕様は、GPT Image 2の透明背景をプレビュー機能として説明しています。透明背景を依頼する場合は、アルファチャンネルを保持できるPNGまたはWebPを使います。記載されたストリーミングは、完成画像の前に最大3枚の部分画像を送れます。進捗プレビューではなく最終素材を保存してください。開発元のインターフェースはバッチ処理にも対応します。</p><p>実際の結果で、文字の明瞭さ、物体の位置、原素材の細部の維持を評価します。GPT Imageは、正確な文字、レイアウトに敏感な構図、別々の生成で視覚的特徴を繰り返し保つことが難しい場合があります。編集を続ける場合は採用した結果を次の原画像に使い、目に見える問題に結びつく具体的な変更を指定します。GPT Image 2の有用な出力は、明確な生成・編集指示に結びついた画像です。その作業に合わせて高忠実度入力、寸法、品質を選びます。</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailootで利用可能 · 入力とメソッド</h3><details class=\"card-method\" open><summary><b>Ailoot Ultra · 画像</b> <code>POST /v1/images/generations</code></summary><dl class=\"method-capabilities\"><div><dt>入力の種類</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>出力の種類</dt><dd><code>image</code></dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>フィールド</th><th>種類</th><th>要件</th><th>値と制限</th><th>デフォルト</th></tr></thead><tbody><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>必須</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>openai/gpt-image-2</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">prompt</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>必須</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>最小の長さ: 1</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">aspect_ratio</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9, auto</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">quality</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>auto, low, medium, high</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">background</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>string</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>auto, opaque</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">n</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>integer</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>最小値: 1</div><div>最大値: 10</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">input_references</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>array</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>最小項目数: 0</div><div>最大項目数: 16</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">output_compression</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>integer</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span><div>最小値: 0</div><div>最大値: 100</div></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">provider</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span><code>object</code></td><td data-cell-label=\"要件\"><span class=\"card-cell-label\">要件</span>任意</td><td data-cell-label=\"値と制限\"><span class=\"card-cell-label\">値と制限</span></td><td data-cell-label=\"デフォルト\" data-default=\"unspecified\"><span class=\"card-cell-label\">デフォルト</span>—</td></tr></tbody></table></div><details class=\"note-s\" data-method-contract><summary>メソッドのパラメータとライフサイクル</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>パラメータ</th><th>仕様</th></tr></thead><tbody><tr><th data-cell-label=\"パラメータ\" scope=\"row\"><span class=\"card-cell-label\">パラメータ</span><code>content_type</code></th><td data-cell-label=\"仕様\"><span class=\"card-cell-label\">仕様</span>application/json</td></tr><tr><th data-cell-label=\"パラメータ\" scope=\"row\"><span class=\"card-cell-label\">パラメータ</span><code>required</code></th><td data-cell-label=\"仕様\"><span class=\"card-cell-label\">仕様</span>model, prompt</td></tr><tr><th data-cell-label=\"パラメータ\" scope=\"row\"><span class=\"card-cell-label\">パラメータ</span><code>material_types</code></th><td data-cell-label=\"仕様\"><span class=\"card-cell-label\">仕様</span>text, image</td></tr></tbody></table></div><p>ライフサイクル: <code>synchronous_result_then_owned_library</code></p><p class=\"note-s\"><code>GET /v1/media/tasks/{task_id}</code> · 実際に返された task_id またはメディアライブラリのレコード</p><p class=\"note-s\"><code>GET /v1/media/assets/{asset_id}/content</code></p><p class=\"note-s\"><code>GET /v1/media/assets</code></p><p class=\"note-s\"><code>GET /v1/media/assets/{asset_id}</code></p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">料金</h3><div class=\"card-result-process\" data-billing-basis><h5>最終料金の計算方法</h5><p class=\"note-s\">表示料金は生成前の費用の見積もりです。最終請求額は、元の生成処理に記録された費用から計算されます。実測された出力時間や予測数量が、そのまま最終的な課金数量になるわけではありません。</p></div><div data-native-semantic-method=\"v1\" data-tariff-reference-only><p class=\"note-s\" data-rate-support-note>料金情報はリクエストの機能を追加しません。対応するパラメーターは選択したメソッドに記載されています。</p><dl data-price-conditions><dt>高速モード</dt><dd>未指定 <span class=\"note-s\">高速モードが選択されている場合</span></dd><dt>Flex モード</dt><dd>未指定 <span class=\"note-s\">flex モードが選択されている場合</span></dd><dt>最大推論量</dt><dd>未指定 <span class=\"note-s\">推論量が最大で、調整に既定値（default）を使用する場合</span></dd></dl></div><div data-declared-tariff-pricing><h4>比較用の推定料金</h4><h4>設定別の価格</h4><p class=\"note-s\">各料金を表示された条件と照合してください。選択肢となる設定の各組には、いずれか1つの料金を適用します。</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>設定</th><th>料金表</th><th>予測数量</th><th>料金</th></tr></thead><tbody><tr><th data-cell-label=\"設定\" scope=\"row\"><span class=\"card-cell-label\">設定</span>基本トークン料金</th><td data-cell-label=\"料金表\"><span class=\"card-cell-label\">料金表</span>基本料金</td><td data-cell-label=\"予測数量\"><span class=\"card-cell-label\">予測数量</span>—</td><td data-cell-label=\"料金\"><span class=\"card-cell-label\">料金</span><div><span>入力 · 入力トークン · 比較専用の見積もり</span> <b>—</b> <span class=\"price-unit\">/ 1K トークン</span></div><div><span>出力 · 出力トークン · 比較専用の見積もり</span> <b>—</b> <span class=\"price-unit\">/ 1K トークン</span></div><div><span>入力 · キャッシュ読み取り · 比較専用の見積もり</span> <b>—</b> <span class=\"price-unit\">/ 1K トークン</span></div><div><span>入力 · キャッシュ書き込み · 比較専用の見積もり</span> <b>—</b> <span class=\"price-unit\">/ 1K トークン</span></div><div><span>入力 · キャッシュ書き込み、1時間 · 比較専用の見積もり</span> <b>—</b> <span class=\"price-unit\">/ 1K トークン</span></div></td></tr><tr><th data-cell-label=\"設定\" scope=\"row\"><span class=\"card-cell-label\">設定</span>生成費用の見積もり</th><td data-cell-label=\"料金表\"><span class=\"card-cell-label\">料金表</span>—</td><td data-cell-label=\"予測数量\"><span class=\"card-cell-label\">予測数量</span>生成1回分の概算</td><td data-cell-label=\"料金\"><span class=\"card-cell-label\">料金</span><div><span>出力 · 推定生成コスト · 比較専用の見積もり</span> <b>$0.24576</b> <span class=\"price-unit\">生成前の見積もり</span></div><p class=\"note-s\">この見積もりは追加料金ではなく、完了した生成処理に対する固定料金でもありません。</p></td></tr></tbody></table></div></div><p class=\"note-s\">Ailootはリクエスト前に見積額を確保します。結果の取得後、実測使用量に基づいて最終料金を精算します。ストリーミング時の精算には最終の使用量記録を使用します。<a href=\"/docs/ja/billing/reserve/\">金額の確保と精算の仕組み →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">リクエスト例</h3><h4>Ailoot Ultra · 画像</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"コードの種類\"><button class=\"cg-tab\" id=\"model-code-645-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-645-panel-0\" aria-selected=\"true\" tabindex=\"0\">curl</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"コードをコピー\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-645-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-645-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\nexport AILOOT_API_KEY\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np={&#39;model&#39;: &#39;openai/gpt-image-2&#39;, &#39;prompt&#39;: &#39;a red panda astronaut floating in space, studio lighting&#39;}\n\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n    if not items: raise SystemExit(&quot;No completed images; retain the full response&quot;)\n    for index, item in enumerate(items):\n        encoded=item.get(&quot;b64_json&quot;)\n        uri=item.get(&quot;url&quot;, &quot;&quot;)\n        if not encoded and uri.startswith(&quot;data:image/&quot;):\n            header, separator, encoded=uri.partition(&quot;,&quot;)\n            if not separator or &quot;;base64&quot; not in header: raise SystemExit(&quot;Unsupported image data URI&quot;)\n        if encoded:\n            raw=base64.b64decode(encoded,validate=True)\n        elif uri:\n            uri=urljoin(&quot;https://api.ailoot.ai&quot;,uri)\n            parsed=urlsplit(uri)\n            if parsed.scheme!=&quot;https&quot; or not parsed.netloc or parsed.username or parsed.password:\n                raise SystemExit(&quot;Invalid returned image URL&quot;)\n            owned=parsed.netloc==&quot;api.ailoot.ai&quot; and parsed.path.startswith(&quot;/v1/media/assets/&quot;) and parsed.path.endswith(&quot;/content&quot;)\n            args=[&quot;curl&quot;,&quot;--fail-with-body&quot;,&quot;--silent&quot;,&quot;--show-error&quot;,uri]\n            if owned: args += [&quot;-H&quot;,&quot;Authorization: Bearer &quot;+os.environ[&quot;AILOOT_API_KEY&quot;]]\n            temporary=Path(f&quot;image-{index}.bin&quot;)\n            subprocess.run(args+[&quot;-o&quot;,str(temporary)],check=True)\n            raw=temporary.read_bytes()\n            temporary.unlink()\n        else: raise SystemExit(&quot;Image has neither bytes nor URL&quot;)\n        if not raw: raise SystemExit(&quot;Empty image result&quot;)\n        ext=&quot;png&quot; if raw.startswith(b&quot;\\x89PNG&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else &quot;svg&quot; if raw.lstrip().startswith((b&quot;&lt;svg&quot;,b&quot;&lt;?xml&quot;)) else &quot;bin&quot;\n        Path(f&quot;image-{index}.{ext}&quot;).write_bytes(raw)\n    print(&quot;Every returned image saved; complete response metadata retained&quot;)\nsave_images(json.loads(Path(&quot;result.json&quot;).read_text())[&quot;data&quot;])\nPY_RESULT\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">結果を受け取って保存</h3><h4>Ailoot Ultra · 画像</h4><p class=\"note-s\">返された画像をすべてダウンロードするか、Base64の内容を保存</p><ul class=\"card-result-paths\"><li><code>GET /v1/media/tasks/{task_id}</code></li><li><code>GET /v1/media/assets/{asset_id}/content</code></li><li><code>GET /v1/media/assets</code></li><li><code>GET /v1/media/assets/{asset_id}</code></li></ul><details class=\"card-about\"><summary>その他のコンテンツ取得</summary><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"コードの種類\"><button class=\"cg-tab\" id=\"model-code-646-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-646-panel-0\" aria-selected=\"true\" tabindex=\"0\">自分が所有する既存のアセットを読み取る</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"コードをコピー\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-646-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-646-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -o owned-assets.json\n# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.\n</code></pre></div></div></div></details><div class=\"card-result-process\" data-all-results><h5>完了した結果をすべて保存</h5><p class=\"note-s\">完了した画像をすべて保存してください。返された各URLから取得するか、Base64の内容をデコードしてください。</p><p class=\"note-s\">レスポンスとヘッダーの全体、実際の出力すべて、最初に返された識別子、使用量フィールドすべてを保存してください。作成リクエストを再送せずに、元の操作を復旧してください。</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>元のレスポンスを確認する場合</h5><p class=\"note-s\">照合のため、返された X-Client-Request-ID を保存してください。実際に返された task_id/asset_id の値、または自分が所有するメディアライブラリだけを使って読み取ってください。操作 ID からタスクの URL を組み立てたり、作成リクエストを再送したりしないでください。</p></div><details class=\"card-about\" data-output-fields><summary>レスポンスのフィールド</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>フィールド</th><th>種類</th></tr></thead><tbody><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">created</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span></td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">data[].url</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span></td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">data[].b64_json</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span></td></tr><tr><th data-cell-label=\"フィールド\" scope=\"row\"><span class=\"card-cell-label\">フィールド</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"種類\" data-field-type><span class=\"card-cell-label\">種類</span></td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">エイリアス</h3><h4>モデルのエイリアス</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=openai%2Fgpt-image-2&amp;route=Core&amp;caller=gpt-image-2&amp;fmt=images\"><code>gpt-image-2</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=openai%2Fgpt-image-2&amp;route=Ultra&amp;caller=gpt-image-2&amp;fmt=images\"><code>gpt-image-2</code></a>, <a href=\"#m=openai%2Fgpt-image-2&amp;route=Ultra&amp;caller=openai%2Fgpt-image-2&amp;fmt=images\"><code>openai/gpt-image-2</code></a></span></p><h4>メソッドパスのエイリアス</h4><p class=\"note-s\"><code>/v1/images</code></p><h4>関連する呼び出し用ID</h4><p class=\"note-s\"><a href=\"#m=openai%2Fgpt-image-2&amp;route=Ultra&amp;caller=openai%2Fgpt-image-2&amp;fmt=images\"><code>openai/gpt-image-2</code></a>, <a href=\"#m=openai%2Fgpt-image-2&amp;route=Core&amp;caller=gpt-image-2&amp;fmt=images\"><code>gpt-image-2</code></a>, <a href=\"#m=openai%2Fgpt-image-2&amp;route=Ultra&amp;caller=gpt-image-2&amp;fmt=images\"><code>gpt-image-2</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "openai/gpt-image-2",
        "fmt": "images",
        "http": "POST",
        "path": "/v1/images/generations",
        "request_model_id": "openai/gpt-image-2",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|images|/v1/images/generations|openai%2Fgpt-image-2",
      "ordinal": 2,
      "rawMethod": {
        "available": null,
        "billing_basis": {
          "basis": "original_invoice_usd",
          "description": "表示料金は生成前の費用の見積もりです。最終請求額は、元の生成処理に記録された費用から計算されます。実測された出力時間や予測数量が、そのまま最終的な課金数量になるわけではありません。",
          "forecast_quantity_is_estimate": true,
          "physical_output_is_billable_quantity": false,
          "version": "original_invoice_usd_v1"
        },
        "cache_read": null,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.",
            "lifecycle": {
              "assets": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets"
                },
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}"
                }
              ],
              "content": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}/content",
                  "url_source": "exact returned signed URL; never construct token"
                }
              ],
              "mode": "synchronous_result_then_owned_library",
              "operation_id_is_not_task_id": true,
              "status": [
                {
                  "http": "GET",
                  "id_source": "actual returned task_id or media library record",
                  "path": "/v1/media/tasks/{task_id}"
                }
              ],
              "unknown": "照合のため、返された X-Client-Request-ID を保存してください。実際に返された task_id/asset_id の値、または自分が所有するメディアライブラリだけを使って読み取ってください。操作 ID からタスクの URL を組み立てたり、作成リクエストを再送したりしないでください。"
            },
            "outputs": {
              "all_results": "レスポンスとヘッダーの全体、実際の出力すべて、最初に返された識別子、使用量フィールドすべてを保存してください。作成リクエストを再送せずに、元の操作を復旧してください。",
              "family": "image",
              "fields": [
                {
                  "description": null,
                  "name": "created",
                  "type": null
                },
                {
                  "description": null,
                  "name": "data[].url",
                  "type": null
                },
                {
                  "description": null,
                  "name": "data[].b64_json",
                  "type": null
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": null
                }
              ]
            },
            "parameters": [
              {
                "enum": [
                  "openai/gpt-image-2"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "min_length": 1,
                "name": "prompt",
                "required": true,
                "type": "string"
              },
              {
                "enum": [
                  "1:1",
                  "3:2",
                  "2:3",
                  "4:3",
                  "3:4",
                  "16:9",
                  "9:16",
                  "21:9",
                  "auto"
                ],
                "enum_known": true,
                "name": "aspect_ratio",
                "required": false,
                "type": "string"
              },
              {
                "enum": [
                  "auto",
                  "low",
                  "medium",
                  "high"
                ],
                "enum_known": true,
                "name": "quality",
                "required": false,
                "type": "string"
              },
              {
                "enum": [
                  "auto",
                  "opaque"
                ],
                "enum_known": true,
                "name": "background",
                "required": false,
                "type": "string"
              },
              {
                "maximum": 10,
                "minimum": 1,
                "name": "n",
                "required": false,
                "type": "integer"
              },
              {
                "items": {
                  "properties": {
                    "image_url": {
                      "properties": {
                        "url": {
                          "type": "string"
                        }
                      },
                      "required": [
                        "url"
                      ],
                      "type": "object"
                    },
                    "type": {
                      "const": "image_url"
                    }
                  },
                  "required": [
                    "type",
                    "image_url"
                  ],
                  "type": "object"
                },
                "maximum_items": 16,
                "minimum_items": 0,
                "name": "input_references",
                "required": false,
                "type": "array"
              },
              {
                "maximum": 100,
                "minimum": 0,
                "name": "output_compression",
                "required": false,
                "type": "integer"
              },
              {
                "name": "provider",
                "required": false,
                "type": "object"
              }
            ],
            "request_schema": {
              "properties": {
                "aspect_ratio": {
                  "enum": [
                    "1:1",
                    "3:2",
                    "2:3",
                    "4:3",
                    "3:4",
                    "16:9",
                    "9:16",
                    "21:9",
                    "auto"
                  ],
                  "type": "string"
                },
                "background": {
                  "enum": [
                    "auto",
                    "opaque"
                  ],
                  "type": "string"
                },
                "input_references": {
                  "items": {
                    "properties": {
                      "image_url": {
                        "properties": {
                          "url": {
                            "type": "string"
                          }
                        },
                        "required": [
                          "url"
                        ],
                        "type": "object"
                      },
                      "type": {
                        "const": "image_url"
                      }
                    },
                    "required": [
                      "type",
                      "image_url"
                    ],
                    "type": "object"
                  },
                  "maxItems": 16,
                  "minItems": 0,
                  "type": "array"
                },
                "model": {
                  "enum": [
                    "openai/gpt-image-2"
                  ],
                  "type": "string"
                },
                "n": {
                  "maximum": 10,
                  "minimum": 1,
                  "type": "integer"
                },
                "output_compression": {
                  "maximum": 100,
                  "minimum": 0,
                  "type": "integer"
                },
                "prompt": {
                  "minLength": 1,
                  "type": "string"
                },
                "provider": {
                  "description": "Exact image provider preferences from the documented image request schema.",
                  "type": "object"
                },
                "quality": {
                  "enum": [
                    "auto",
                    "low",
                    "medium",
                    "high"
                  ],
                  "type": "string"
                }
              },
              "required": [
                "model",
                "prompt"
              ],
              "type": "object"
            },
            "schema_template": {
              "actual_file_preparation_required": false,
              "body": {
                "model": "openai/gpt-image-2",
                "prompt": "a red panda astronaut floating in space, studio lighting"
              },
              "content_type": "application/json"
            }
          },
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "required": [
              "model",
              "prompt"
            ]
          },
          "lifecycle": {
            "assets": [
              {
                "http": "GET",
                "path": "/v1/media/assets"
              },
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}"
              }
            ],
            "content": [
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}/content",
                "url_source": "exact returned signed URL; never construct token"
              }
            ],
            "mode": "synchronous_result_then_owned_library",
            "operation_id_is_not_task_id": true,
            "status": [
              {
                "http": "GET",
                "id_source": "実際に返された task_id またはメディアライブラリのレコード",
                "path": "/v1/media/tasks/{task_id}"
              }
            ],
            "unknown": "Keep the returned X-Client-Request-ID for reconciliation. Read only actual returned task_id/asset_id values or the owned media library; never build a task URL from the operation ID and never resubmit creation."
          },
          "method": {
            "http": "POST",
            "path": "/v1/images/generations"
          },
          "output": {
            "all_results": "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.",
            "family": "image",
            "fields": [
              {
                "description": null,
                "name": "created",
                "type": null
              },
              {
                "description": null,
                "name": "data[].url",
                "type": null
              },
              {
                "description": null,
                "name": "data[].b64_json",
                "type": null
              },
              {
                "description": null,
                "name": "usage",
                "type": null
              }
            ]
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "basis": "この見積もりは追加料金ではなく、完了した生成処理に対する固定料金でもありません。",
            "dimensions": {
              "forecast_quantity": "one generation estimate"
            },
            "label": "生成費用の見積もり",
            "units": [
              {
                "amount": "0.24576",
                "amount_unit": "usd_per_exact_native_unit",
                "billing_input": false,
                "estimate_only": true,
                "key": "forecast_usd",
                "label": "Estimated generation cost",
                "native_amount_usd_per_unit": "0.24576",
                "native_quantity": 1,
                "public_unit_label": "estimate before generation",
                "quantity": 1,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "request_estimate"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np={'model': 'openai/gpt-image-2', 'prompt': 'a red panda astronaut floating in space, studio lighting'}\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n    if not items: raise SystemExit(\"No completed images; retain the full response\")\n    for index, item in enumerate(items):\n        encoded=item.get(\"b64_json\")\n        uri=item.get(\"url\", \"\")\n        if not encoded and uri.startswith(\"data:image/\"):\n            header, separator, encoded=uri.partition(\",\")\n            if not separator or \";base64\" not in header: raise SystemExit(\"Unsupported image data URI\")\n        if encoded:\n            raw=base64.b64decode(encoded,validate=True)\n        elif uri:\n            uri=urljoin(\"https://api.ailoot.ai\",uri)\n            parsed=urlsplit(uri)\n            if parsed.scheme!=\"https\" or not parsed.netloc or parsed.username or parsed.password:\n                raise SystemExit(\"Invalid returned image URL\")\n            owned=parsed.netloc==\"api.ailoot.ai\" and parsed.path.startswith(\"/v1/media/assets/\") and parsed.path.endswith(\"/content\")\n            args=[\"curl\",\"--fail-with-body\",\"--silent\",\"--show-error\",uri]\n            if owned: args += [\"-H\",\"Authorization: Bearer \"+os.environ[\"AILOOT_API_KEY\"]]\n            temporary=Path(f\"image-{index}.bin\")\n            subprocess.run(args+[\"-o\",str(temporary)],check=True)\n            raw=temporary.read_bytes()\n            temporary.unlink()\n        else: raise SystemExit(\"Image has neither bytes nor URL\")\n        if not raw: raise SystemExit(\"Empty image result\")\n        ext=\"png\" if raw.startswith(b\"\\x89PNG\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else \"svg\" if raw.lstrip().startswith((b\"<svg\",b\"<?xml\")) else \"bin\"\n        Path(f\"image-{index}.{ext}\").write_bytes(raw)\n    print(\"Every returned image saved; complete response metadata retained\")\nsave_images(json.loads(Path(\"result.json\").read_text())[\"data\"])\nPY_RESULT\n",
            "label": "curl · exact creation/save all outputs",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -o owned-assets.json\n# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.\n",
            "label": "Read existing owned assets",
            "language": "bash"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "images",
        "hints": [
          "Use the exact caller model ID and documented input representation.",
          "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again."
        ],
        "http": "POST",
        "in": null,
        "input": [
          "text",
          "image"
        ],
        "label": "画像",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [
          "/v1/images"
        ],
        "native_endpoint": "images",
        "out": null,
        "output": [
          "image"
        ],
        "path": "/v1/images/generations",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Not specified",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Not specified",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Not specified",
            "when": "When maximum reasoning effort uses the default adjustment"
          }
        ],
        "pricing": {
          "billing_mode": "original_invoice_usd",
          "image_input_price": null,
          "image_output_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "basis": "This estimate is not an additional charge or a fixed rate for the completed generation.",
            "dimensions": {
              "forecast_quantity": "one generation estimate"
            },
            "label": "Estimated generation cost",
            "units": [
              {
                "amount": "0.24576",
                "amount_unit": "usd_per_exact_native_unit",
                "billing_input": false,
                "estimate_only": true,
                "key": "forecast_usd",
                "label": "Estimated generation cost",
                "native_amount_usd_per_unit": "0.24576",
                "native_quantity": 1,
                "public_unit_label": "estimate before generation",
                "quantity": 1,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "request_estimate"
              }
            ]
          }
        ],
        "request_model_id": "openai/gpt-image-2",
        "route_label": "Ultra",
        "status_reads": [
          "GET /v1/media/tasks/{task_id}"
        ],
        "tiers": [],
        "units": [
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          },
          {
            "amount": "0.24576",
            "amount_unit": "usd_per_exact_native_unit",
            "billing_input": false,
            "estimate_only": true,
            "key": "forecast_usd",
            "label": "Estimated generation cost",
            "native_amount_usd_per_unit": "0.24576",
            "native_quantity": 1,
            "public_unit_label": "estimate before generation",
            "quantity": 1,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "request_estimate"
          }
        ]
      }
    }
  ],
  "model_id": "openai/gpt-image-2",
  "nativeProvenance": {
    "input_facts_canonical_sha256": "6d088aad7a9cfd61556903f5349341e62b6fcc04a8269e4e7f7ce16b6e3368c5",
    "input_html_sha256": "b6112dad6c58d6d9d1afc30cbb068bd1b090f9af6f4346ba0905d13e85d60286",
    "private_audit_sha256": "535905df24165536cfbe2cefa32c905b4c6a92b7f23f17dc966c321292b225a5",
    "role": "historical-normalized-input-audit-hashes",
    "schema": "ailoot-native-model-provenance-v2"
  },
  "page": {
    "canonical": "https://ailoot.ai/models/ja/gpt-image-2/",
    "description": "GPT Image 2は、テキストと視覚参照から画像を生成・編集します。柔軟なフレーム寸法に対応し、すべての画像入力を自動で高忠実度処理します。完成素材の品質、形式、背景は個別に制御できます。",
    "locale": "ja",
    "md_url": "https://ailoot.ai/models/ja/gpt-image-2/index.md",
    "title": "OpenAI: GPT Image 2 — Ailoot",
    "url": "https://ailoot.ai/models/ja/gpt-image-2/"
  },
  "rawModel": {
    "about": "GPT Image 2は、テキストと視覚入力から画像を生成・編集するOpenAIのモデルです。文章の制作指示から新しい画像を作り、編集や参照中心の制作には原画像を使えます。イラスト、商品コンセプト、視覚的な構図、既存素材の変更などが実用例です。GPT Image 2.5 SunburstやFlareとは別のエディションで、固有の品質範囲と入力忠実度の動作を持ちます。\n\n生成では、被写体、シーン、構図、光、意図したスタイルを記述します。編集では変えるものと外観を維持するものを指定します。商品制作なら、淡い面に置いた陶器のランプ、中央の輪郭、キャプション用の余白を依頼し、追加編集でランプの形と視点を保ちながら背景を変えられます。記載された直接の生成・編集ワークフローは最大32,000文字のプロンプトを受け付け、1～10枚の画像を返せます。\n\n参照を使う編集は最大16枚の入力画像に対応します。被写体、背景、視覚表現が混同されないよう、各参照の目的を指定します。GPT Image 2はすべての画像入力を自動で高忠実度処理します。このエディションでは調整できないため、input_fidelityは省略します。これはGPT Image 1のhighまたはlowの選択や、GPT Image 1 Miniのlow限定の入力忠実度とは異なります。高忠実度の入力処理は原素材の細部を支えますが、すべての細部が変わらず再現される保証ではありません。\n\nマスクで編集領域を示せます。ガイドの準備要件では、原画像とマスクは同じ形式と寸法で、50 MB未満である必要があります。マスクにはアルファチャンネルも必要です。複数の入力画像がある場合、マスクは最初の画像に適用されます。モデルはマスクを厳密な幾何学的境界ではなく、プロンプトに基づく誘導として扱います。局所的な変更と維持要件を記述し、周囲に意図しない差異がないかを確認します。\n\nGPT Image 2はlow、medium、high、autoの品質に対応し、標準はautoです。2.5ファミリーのxhighとmaxは、このエディションの品質範囲に含まれません。サイズは正方形、横長、縦長、自動、または有効な独自の幅と高さを選べます。開発元の例は1024 × 1024、1536 × 1024、1024 × 1536、2048 × 2048、2048 × 1152、3840 × 2160、2160 × 3840ピクセルです。品質と寸法を同じ制御として扱わず、実際のレイアウトに合う向きと細部の水準を選びます。\n\n独自寸法は16ピクセルの倍数、最大辺3840ピクセル、長辺対短辺の比率3:1以下、面積655,360～8,294,400ピクセルが条件です。これらは同時に適用されます。2560 × 1440を超える解像度は実験的とされています。一つの条件を満たすフレームでも別の条件に違反し得るため、有効な縦横寸法の組み合わせを選び、切り取りで失いたくない要素を制作指示に記述します。\n\n出力の標準はPNGで、JPEGとWebPも利用できます。JPEGとWebPは0～100の圧縮値に対応します。背景は不透明または自動を選べます。現在の個別仕様は、GPT Image 2の透明背景をプレビュー機能として説明しています。透明背景を依頼する場合は、アルファチャンネルを保持できるPNGまたはWebPを使います。記載されたストリーミングは、完成画像の前に最大3枚の部分画像を送れます。進捗プレビューではなく最終素材を保存してください。開発元のインターフェースはバッチ処理にも対応します。\n\n実際の結果で、文字の明瞭さ、物体の位置、原素材の細部の維持を評価します。GPT Imageは、正確な文字、レイアウトに敏感な構図、別々の生成で視覚的特徴を繰り返し保つことが難しい場合があります。編集を続ける場合は採用した結果を次の原画像に使い、目に見える問題に結びつく具体的な変更を指定します。GPT Image 2の有用な出力は、明確な生成・編集指示に結びついた画像です。その作業に合わせて高忠実度入力、寸法、品質を選びます。",
    "alias_of": null,
    "aliases": [
      "gpt-image-2"
    ],
    "author": "OpenAI",
    "capabilities": {
      "context_length": 400000,
      "manufacturer_input": [
        "text",
        "image"
      ],
      "manufacturer_output": [
        "image"
      ]
    },
    "card_routes": [
      {
        "label": "Core",
        "rates": [
          {
            "amount": 2.5,
            "amount_unit": "usd_per_million_tokens",
            "key": "in",
            "label": "Input",
            "side": "in"
          },
          {
            "amount": 0,
            "amount_unit": "usd_per_million_tokens",
            "key": "out",
            "label": "Output",
            "side": "out"
          }
        ],
        "summary": "構成の料金情報はすべて詳細で確認できます。"
      },
      {
        "label": "Ultra",
        "rates": [
          {
            "amount": "0.24576",
            "amount_unit": "usd_per_exact_native_unit",
            "billing_input": false,
            "estimate_only": true,
            "key": "forecast_usd",
            "label": "Estimated generation cost",
            "native_amount_usd_per_unit": "0.24576",
            "native_quantity": 1,
            "public_unit_label": "estimate before generation",
            "quantity": 1,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "request_estimate"
          }
        ],
        "summary": "構成の料金情報はすべて詳細で確認できます。"
      },
      {
        "label": "Ultra",
        "rates": [
          {
            "amount": "0.24576",
            "amount_unit": "usd_per_exact_native_unit",
            "billing_input": false,
            "estimate_only": true,
            "key": "forecast_usd",
            "label": "Estimated generation cost",
            "native_amount_usd_per_unit": "0.24576",
            "native_quantity": 1,
            "public_unit_label": "estimate before generation",
            "quantity": 1,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "request_estimate"
          }
        ],
        "summary": "構成の料金情報はすべて詳細で確認できます。"
      }
    ],
    "ctx": null,
    "formats": [
      "images"
    ],
    "id": "openai/gpt-image-2",
    "input": [
      "text",
      "image"
    ],
    "kind": "image",
    "max_out": null,
    "methods": [
      {
        "cache_read": null,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Save every data item. Decode each b64_json or fetch every returned signed URL. Select a filename extension from the actual MIME/bytes.",
            "errors": [
              {
                "code": null,
                "condition": "必須フィールド、素材の表現形式、またはパラメーター値が不正です",
                "http_status": 400,
                "recovery": "新しい生成リクエストを送る前に、指定されたフィールドを修正してください。",
                "type": "invalid_request_error"
              },
              {
                "code": null,
                "condition": "返されたレスポンスは、操作または結果の確認が必要であることを示しています",
                "http_status": null,
                "recovery": "最初に返された操作／タスク ID、リクエストヘッダー、レスポンスを保存し、その元の操作に対してサポートされている読み取りを継続してください。作成リクエストを再送しないでください。",
                "type": "server_error"
              }
            ],
            "hints": [],
            "ignored_fields": [],
            "lifecycle": {
              "all_results": "Follow everyactualreturnedoutputandownedasset; no result is discardedbecauseindex0orcontent_urlalreadyexists.",
              "assets": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets"
                },
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}"
                }
              ],
              "content": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}/content",
                  "url_source": "exact returned signed URL; never construct token"
                }
              ],
              "mode": "synchronous_result_then_owned_library",
              "operation_id_is_not_task_id": true,
              "status": [
                {
                  "http": "GET",
                  "id_source": "actual returned task_id or media library record",
                  "path": "/v1/media/tasks/{task_id}"
                }
              ],
              "unknown": "画像の生成または編集の結果に確認が必要な場合は、元の operation_id/X-Client-Request-ID と、返された結果情報を保存してください。実際の task_id または asset_id の値を使い、メディアライブラリから自分が所有する既存の結果を取得してください。生成／編集リクエストを再送したり、operation_id からポーリング URL を組み立てたりしないでください。"
            },
            "material_combinations": [
              {
                "content_types": [
                  "application/json",
                  "multipart/form-data"
                ],
                "file_id_supported": false,
                "mode": "text_to_image",
                "multipart_part_read_limit_bytes": 20971520,
                "optional_mask": {
                  "json": "mask.image_url",
                  "multipart": "mask"
                },
                "reference_representations": {
                  "json": "images[].image_url",
                  "multipart": [
                    "image",
                    "image[]",
                    "image[index]"
                  ]
                },
                "required": [
                  "prompt"
                ]
              }
            ],
            "media_library": {
              "asset": {
                "fields": [
                  {
                    "description": null,
                    "name": "asset_id",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "task_id",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "output_key",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "family",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "model",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "method",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "status",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "content_type",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "sha256",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "size_bytes",
                    "type": "integer"
                  },
                  {
                    "description": null,
                    "name": "content_url",
                    "type": "string"
                  }
                ],
                "http": "GET",
                "id_source": "actual returned asset_id",
                "path": "/v1/media/assets/{asset_id}"
              },
              "content": {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}/content",
                "range_header_supported": true,
                "url_source": "Use exact returned signed content_url including its token; do not construct a token."
              },
              "expired_link": {
                "code": "link_expired",
                "http_status": 404,
                "recovery": "Read the asset again to obtain its refreshed signed content_url, then fetch that URL. Do not regenerate."
              },
              "list": {
                "all_pages": "Follow every returned next_cursor, then select records by their actual task_id/output_key.",
                "http": "GET",
                "output_fields": [
                  {
                    "description": null,
                    "name": "object",
                    "type": "string"
                  },
                  {
                    "description": null,
                    "name": "data",
                    "type": "asset[]"
                  },
                  {
                    "description": null,
                    "name": "next_cursor",
                    "type": "string|null"
                  }
                ],
                "parameters": [
                  {
                    "availability": "source_interface",
                    "default": null,
                    "default_known": false,
                    "enum": null,
                    "enum_known": false,
                    "name": "family",
                    "required": false,
                    "type": "string"
                  },
                  {
                    "availability": "source_interface",
                    "default": null,
                    "default_known": false,
                    "enum": null,
                    "enum_known": false,
                    "name": "cursor",
                    "required": false,
                    "type": "string"
                  },
                  {
                    "availability": "source_interface",
                    "default": 20,
                    "default_known": true,
                    "enum": null,
                    "enum_known": false,
                    "maximum": 100,
                    "minimum": 1,
                    "name": "limit",
                    "required": false,
                    "type": "integer"
                  }
                ],
                "path": "/v1/media/assets"
              },
              "revoke": {
                "http": "DELETE",
                "meaning": "Revokes/deletes the existing owned file; this is not generation cancellation.",
                "path": "/v1/media/assets/{asset_id}",
                "pending_status": "revoking",
                "success_statuses": [
                  202,
                  204
                ]
              },
              "task": {
                "http": "GET",
                "id_source": "actual returned task_id or media library record; operation_id is not task_id",
                "path": "/v1/media/tasks/{task_id}"
              }
            },
            "operation_modes": [
              "text_to_image"
            ],
            "outputs": {
              "all_results": "すべてのデータ項目を保存してください。各 b64_json をデコードするか、返された署名付き URL すべてから取得してください。実際の MIME タイプ／バイト列に応じてファイル名の拡張子を選んでください。",
              "family": "image",
              "fields": [
                {
                  "description": null,
                  "name": "created",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "data[].url",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "data[].b64_json",
                  "type": "base64 string"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "actual validated raster MIME"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "gpt-image-2"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_length": 1,
                "name": "prompt",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": 1,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "n",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "url",
                  "b64_json"
                ],
                "enum_known": true,
                "name": "response_format",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "size",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "quality",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "background",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_format",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_compression",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "moderation",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input_fidelity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "style",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "partial_images",
                "required": false,
                "type": "integer"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": [
              "images[].file_id",
              "mask.file_id"
            ]
          },
          "hints": [
            "メソッドの形式とIDは正確に記載しています。供給元の対応能力とリクエストの受け入れは別です。"
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "prompt"
            ]
          },
          "lifecycle": {
            "assets": [
              {
                "http": "GET",
                "path": "/v1/media/assets"
              },
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}"
              }
            ],
            "content": [
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}/content",
                "url_source": "exact returned signed URL; never construct token"
              }
            ],
            "mode": "synchronous_result_then_owned_library",
            "operation_id_is_not_task_id": true,
            "status": [
              {
                "http": "GET",
                "id_source": "実際に返された task_id またはメディアライブラリのレコード",
                "path": "/v1/media/tasks/{task_id}"
              }
            ],
            "unknown": "If an image generation or edit result requires a check, keep the original operation_id/X-Client-Request-ID and returned result information. Recover existing owned results through the media library using actual task_id or asset_id values. Do not resubmit the generation/edit request or construct a polling URL from operation_id."
          },
          "method": {
            "http": "POST",
            "path": "/v1/images/generations"
          },
          "operation_modes": [
            "images"
          ],
          "output": {
            "family": [
              "image"
            ],
            "format": null,
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": null,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\nexport AILOOT_API_KEY\n: \"${AILOOT_PROMPT_FILE:?Set your actual UTF-8 image brief}\"\nexport AILOOT_PROMPT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"gpt-image-2\", \"prompt\": \"\"}')\nf=Path(os.environ[\"AILOOT_PROMPT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 brief\")\np['prompt']=f.read_text(encoding=\"utf-8\")\nif not p['prompt'].strip():raise SystemExit(\"Brief must contain text\")\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n    if not items: raise SystemExit(\"No completed images; retain the full response\")\n    for index, item in enumerate(items):\n        encoded=item.get(\"b64_json\")\n        uri=item.get(\"url\", \"\")\n        if not encoded and uri.startswith(\"data:image/\"):\n            header, separator, encoded=uri.partition(\",\")\n            if not separator or \";base64\" not in header: raise SystemExit(\"Unsupported image data URI\")\n        if encoded:\n            raw=base64.b64decode(encoded,validate=True)\n        elif uri:\n            uri=urljoin(\"https://api.ailoot.ai\",uri)\n            parsed=urlsplit(uri)\n            if parsed.scheme!=\"https\" or not parsed.netloc or parsed.username or parsed.password:\n                raise SystemExit(\"Invalid returned image URL\")\n            owned=parsed.netloc==\"api.ailoot.ai\" and parsed.path.startswith(\"/v1/media/assets/\") and parsed.path.endswith(\"/content\")\n            args=[\"curl\",\"--fail-with-body\",\"--silent\",\"--show-error\",uri]\n            if owned: args += [\"-H\",\"Authorization: Bearer \"+os.environ[\"AILOOT_API_KEY\"]]\n            temporary=Path(f\"image-{index}.bin\")\n            subprocess.run(args+[\"-o\",str(temporary)],check=True)\n            raw=temporary.read_bytes()\n            temporary.unlink()\n        else: raise SystemExit(\"Image has neither bytes nor URL\")\n        if not raw: raise SystemExit(\"Empty image result\")\n        ext=\"png\" if raw.startswith(b\"\\x89PNG\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else \"svg\" if raw.lstrip().startswith((b\"<svg\",b\"<?xml\")) else \"bin\"\n        Path(f\"image-{index}.{ext}\").write_bytes(raw)\n    print(\"Every returned image saved; complete response metadata retained\")\nsave_images(json.loads(Path(\"result.json\").read_text())[\"data\"])\nPY_RESULT\n",
            "label": "Create and save every image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n    if not items: raise SystemExit(\"No completed images; retain the full response\")\n    for index, item in enumerate(items):\n        encoded=item.get(\"b64_json\")\n        uri=item.get(\"url\", \"\")\n        if not encoded and uri.startswith(\"data:image/\"):\n            header, separator, encoded=uri.partition(\",\")\n            if not separator or \";base64\" not in header: raise SystemExit(\"Unsupported image data URI\")\n        if encoded:\n            raw=base64.b64decode(encoded,validate=True)\n        elif uri:\n            uri=urljoin(\"https://api.ailoot.ai\",uri)\n            parsed=urlsplit(uri)\n            if parsed.scheme!=\"https\" or not parsed.netloc or parsed.username or parsed.password:\n                raise SystemExit(\"Invalid returned image URL\")\n            owned=parsed.netloc==\"api.ailoot.ai\" and parsed.path.startswith(\"/v1/media/assets/\") and parsed.path.endswith(\"/content\")\n            args=[\"curl\",\"--fail-with-body\",\"--silent\",\"--show-error\",uri]\n            if owned: args += [\"-H\",\"Authorization: Bearer \"+os.environ[\"AILOOT_API_KEY\"]]\n            temporary=Path(f\"image-{index}.bin\")\n            subprocess.run(args+[\"-o\",str(temporary)],check=True)\n            raw=temporary.read_bytes()\n            temporary.unlink()\n        else: raise SystemExit(\"Image has neither bytes nor URL\")\n        if not raw: raise SystemExit(\"Empty image result\")\n        ext=\"png\" if raw.startswith(b\"\\x89PNG\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else \"svg\" if raw.lstrip().startswith((b\"<svg\",b\"<?xml\")) else \"bin\"\n        Path(f\"image-{index}.{ext}\").write_bytes(raw)\n    print(\"Every returned image saved; complete response metadata retained\")\n\nf=Path(os.environ[\"AILOOT_PROMPT_FILE\"])\nif not f.is_file():raise SystemExit(\"Set your actual UTF-8 image brief file\")\nrequest={'model': 'gpt-image-2', 'prompt': ''}\nrequest[\"prompt\"]=f.read_text(encoding=\"utf-8\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.images.generate(**request)\nPath(\"sdk-result.txt\").write_text(str(result),encoding=\"utf-8\")\nsave_images([{\"b64_json\":getattr(item,\"b64_json\",None),\"url\":getattr(item,\"url\",None)} for item in result.data])\n",
            "label": "Python SDK · save all image outputs",
            "language": "python"
          },
          {
            "code": "import OpenAI from \"openai\";\nimport { readFileSync, writeFileSync } from \"node:fs\";\nconst key=process.env.AILOOT_API_KEY;\nif(!key) throw new Error(\"Set your actual Ailoot API key\");\nconst client=new OpenAI({baseURL:\"https://api.ailoot.ai/v1\",apiKey:key,maxRetries:0});\nconst request={\"model\": \"gpt-image-2\", \"prompt\": \"\"};\nif(!process.env.AILOOT_PROMPT_FILE)throw new Error(\"Set your actual UTF-8 image brief file\");\nrequest.prompt=readFileSync(process.env.AILOOT_PROMPT_FILE,\"utf8\");\nconst result=await client.images.generate(request);\nwriteFileSync(\"sdk-result.json\",JSON.stringify(result,null,2));\nif(!result.data?.length) throw new Error(\"No completed images\");\nfor(let index=0;index<result.data.length;index++) {\n  const item=result.data[index];let encoded=item.b64_json,uri=item.url||\"\",raw;\n  if(!encoded && uri.startsWith(\"data:image/\")) {\n    const comma=uri.indexOf(\",\");if(comma<0 || !uri.slice(0,comma).includes(\";base64\")) throw new Error(\"Unsupported image data URI\");\n    encoded=uri.slice(comma+1);\n  }\n  if(encoded) {\n    if(encoded.length%4!==0 || !/^[A-Za-z0-9+/]*={0,2}$/.test(encoded)) throw new Error(\"Invalid Base64\");\n    raw=Buffer.from(encoded,\"base64\");\n  } else if(uri) {\n    const u=new URL(uri,\"https://api.ailoot.ai\");\n    if(u.protocol!==\"https:\" || u.username || u.password) throw new Error(\"Invalid returned URL\");\n    const owned=u.origin===\"https://api.ailoot.ai\" && u.pathname.startsWith(\"/v1/media/assets/\") && u.pathname.endsWith(\"/content\");\n    const response=await fetch(u,{headers:owned?{Authorization:\"Bearer \"+key}:{},redirect:\"manual\"});\n    if(!response.ok) throw new Error(\"Image content download failed: \"+response.status);\n    raw=Buffer.from(await response.arrayBuffer());\n  } else throw new Error(\"Image has neither bytes nor URL\");\n  if(!raw.length) throw new Error(\"Empty image result\");\n  const ext=raw.subarray(0,4).equals(Buffer.from([137,80,78,71]))?\"png\":raw[0]===255&&raw[1]===216?\"jpg\":raw.toString(\"ascii\",0,4)===\"RIFF\"&&raw.toString(\"ascii\",8,12)===\"WEBP\"?\"webp\":raw.toString(\"utf8\").trimStart().startsWith(\"<svg\")||raw.toString(\"utf8\").trimStart().startsWith(\"<?xml\")?\"svg\":\"bin\";\n  writeFileSync(`image-${index}.${ext}`,raw);\n}\nconsole.log(\"Every returned image saved; sdk-result.json retains complete metadata\");\n",
            "label": "Node SDK · save all image outputs",
            "language": "js"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "images",
        "http": "POST",
        "img_in": 4,
        "img_out": 15,
        "in": 2.5,
        "input": [
          "text"
        ],
        "label": "画像",
        "max_out": null,
        "max_tool_calls": null,
        "out": 0,
        "output": [
          "image"
        ],
        "path": "/v1/images/generations",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 2.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 4,
                "amount_unit": "usd_per_million_tokens",
                "key": "img_in",
                "label": "Image input",
                "side": "in"
              },
              {
                "amount": 15,
                "amount_unit": "usd_per_million_tokens",
                "key": "img_out",
                "label": "Image output",
                "side": "out"
              }
            ]
          }
        ],
        "request_model_id": "gpt-image-2",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "billing_basis": {
          "basis": "original_invoice_usd",
          "description": "表示料金は生成前の費用の見積もりです。最終請求額は、元の生成処理に記録された費用から計算されます。実測された出力時間や予測数量が、そのまま最終的な課金数量になるわけではありません。",
          "forecast_quantity_is_estimate": true,
          "physical_output_is_billable_quantity": false,
          "version": "original_invoice_usd_v1"
        },
        "cache_read": null,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.",
            "lifecycle": {
              "assets": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets"
                },
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}"
                }
              ],
              "content": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}/content",
                  "url_source": "exact returned signed URL; never construct token"
                }
              ],
              "mode": "synchronous_result_then_owned_library",
              "operation_id_is_not_task_id": true,
              "status": [
                {
                  "http": "GET",
                  "id_source": "actual returned task_id or media library record",
                  "path": "/v1/media/tasks/{task_id}"
                }
              ],
              "unknown": "照合のため、返された X-Client-Request-ID を保存してください。実際に返された task_id/asset_id の値、または自分が所有するメディアライブラリだけを使って読み取ってください。操作 ID からタスクの URL を組み立てたり、作成リクエストを再送したりしないでください。"
            },
            "outputs": {
              "all_results": "レスポンスとヘッダーの全体、実際の出力すべて、最初に返された識別子、使用量フィールドすべてを保存してください。作成リクエストを再送せずに、元の操作を復旧してください。",
              "family": "image",
              "fields": [
                {
                  "description": null,
                  "name": "created",
                  "type": null
                },
                {
                  "description": null,
                  "name": "data[].url",
                  "type": null
                },
                {
                  "description": null,
                  "name": "data[].b64_json",
                  "type": null
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": null
                }
              ]
            },
            "parameters": [
              {
                "enum": [
                  "gpt-image-2"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "maxLength": 32000,
                "maximum_length": 32000,
                "name": "prompt",
                "required": true,
                "type": "string"
              },
              {
                "conditions": "autoまたはWIDTHxHEIGHTを使用し、幅と高さの両方を16で割り切れる値にしてください。長辺は最大3,840ピクセル、総画素数は最大8,300,000ピクセルです。",
                "default": "auto",
                "default_known": true,
                "description": "Use auto or WIDTHxHEIGHT with both dimensions divisible by 16. The longest side is at most 3,840 pixels and total size at most 8,300,000 pixels.",
                "name": "size",
                "required": false,
                "type": "string"
              },
              {
                "default": "auto",
                "default_known": true,
                "enum": [
                  "transparent",
                  "opaque",
                  "auto"
                ],
                "enum_known": true,
                "name": "background",
                "required": false,
                "type": "string"
              },
              {
                "conditions": "標準のコンテンツモデレーションにはautoを使用してください。",
                "description": "Use auto for standard content moderation.",
                "enum": [
                  "low",
                  "auto"
                ],
                "enum_known": true,
                "name": "moderation",
                "required": false,
                "type": "string"
              },
              {
                "default": 1,
                "default_known": true,
                "maximum": 10,
                "minimum": 1,
                "name": "n",
                "required": false,
                "type": "integer"
              },
              {
                "default": "auto",
                "default_known": true,
                "enum": [
                  "auto",
                  "high",
                  "medium",
                  "low"
                ],
                "enum_known": true,
                "name": "quality",
                "required": false,
                "type": "string"
              },
              {
                "conditions": "JPEGとWebPの出力に適用されます。文書に記載された整数値を送信してください。",
                "default": 100,
                "default_known": true,
                "description": "Applies to JPEG and WebP output; send the documented integer value.",
                "maximum": 100,
                "minimum": 0,
                "name": "output_compression",
                "required": false,
                "type": "integer"
              },
              {
                "default": "png",
                "default_known": true,
                "enum": [
                  "webp",
                  "png",
                  "jpeg"
                ],
                "enum_known": true,
                "name": "output_format",
                "required": false,
                "type": "string"
              },
              {
                "conditions": "このルートは、完了したJSONレスポンスを一件返します。",
                "default": false,
                "default_known": true,
                "description": "This route returns one completed JSON response.",
                "enum": [
                  false
                ],
                "enum_known": true,
                "name": "stream",
                "required": false,
                "type": "boolean"
              }
            ],
            "request_schema": {
              "properties": {
                "background": {
                  "default": "auto",
                  "enum": [
                    "transparent",
                    "opaque",
                    "auto"
                  ],
                  "type": "string"
                },
                "model": {
                  "enum": [
                    "gpt-image-2"
                  ],
                  "type": "string"
                },
                "moderation": {
                  "description": "Use auto for standard content moderation.",
                  "enum": [
                    "low",
                    "auto"
                  ],
                  "type": "string"
                },
                "n": {
                  "default": 1,
                  "maximum": 10,
                  "minimum": 1,
                  "type": "integer"
                },
                "output_compression": {
                  "default": 100,
                  "description": "Applies to JPEG and WebP output; send the documented integer value.",
                  "maximum": 100,
                  "minimum": 0,
                  "type": "integer"
                },
                "output_format": {
                  "default": "png",
                  "enum": [
                    "webp",
                    "png",
                    "jpeg"
                  ],
                  "type": "string"
                },
                "prompt": {
                  "maxLength": 32000,
                  "type": "string"
                },
                "quality": {
                  "default": "auto",
                  "enum": [
                    "auto",
                    "high",
                    "medium",
                    "low"
                  ],
                  "type": "string"
                },
                "size": {
                  "default": "auto",
                  "description": "Use auto or WIDTHxHEIGHT with both dimensions divisible by 16. The longest side is at most 3,840 pixels and total size at most 8,300,000 pixels.",
                  "type": "string"
                },
                "stream": {
                  "default": false,
                  "description": "This route returns one completed JSON response.",
                  "enum": [
                    false
                  ],
                  "type": "boolean"
                }
              },
              "required": [
                "prompt",
                "model"
              ],
              "type": "object"
            },
            "schema_template": {
              "actual_file_preparation_required": false,
              "body": {
                "background": "auto",
                "model": "gpt-image-2",
                "moderation": "auto",
                "n": 1,
                "output_format": "png",
                "prompt": "A cute baby sea otter",
                "size": "1024x1024"
              },
              "content_type": "application/json"
            }
          },
          "input": {
            "conditions": [
              "透過背景にはPNGまたはWebPが必要です。",
              "出力圧縮はJPEGまたはWebPに適用されます。",
              "選択したメソッドはテキストから生成します。メーカーの説明に記載されている編集およびストリーミングの制御は、別の機能です。"
            ],
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional": [
              "size",
              "background",
              "moderation",
              "n",
              "quality",
              "output_compression",
              "output_format",
              "stream"
            ],
            "required": [
              "prompt",
              "model"
            ]
          },
          "lifecycle": {
            "assets": [
              {
                "http": "GET",
                "path": "/v1/media/assets"
              },
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}"
              }
            ],
            "content": [
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}/content",
                "url_source": "exact returned signed URL; never construct token"
              }
            ],
            "mode": "synchronous_result_then_owned_library",
            "operation_id_is_not_task_id": true,
            "status": [
              {
                "http": "GET",
                "id_source": "実際に返された task_id またはメディアライブラリのレコード",
                "path": "/v1/media/tasks/{task_id}"
              }
            ],
            "unknown": "Keep the returned X-Client-Request-ID for reconciliation. Read only actual returned task_id/asset_id values or the owned media library; never build a task URL from the operation ID and never resubmit creation."
          },
          "method": {
            "http": "POST",
            "path": "/v1/images/generations"
          },
          "output": {
            "all_results": "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.",
            "family": "image",
            "fields": [
              {
                "description": null,
                "name": "created",
                "type": null
              },
              {
                "description": null,
                "name": "data[].url",
                "type": null
              },
              {
                "description": null,
                "name": "data[].b64_json",
                "type": null
              },
              {
                "description": null,
                "name": "usage",
                "type": null
              }
            ]
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "basis": "この見積もりは追加料金ではなく、完了した生成処理に対する固定料金でもありません。",
            "dimensions": {
              "forecast_quantity": "one generation estimate"
            },
            "label": "生成費用の見積もり",
            "units": [
              {
                "amount": "0.24576",
                "amount_unit": "usd_per_exact_native_unit",
                "billing_input": false,
                "estimate_only": true,
                "key": "forecast_usd",
                "label": "Estimated generation cost",
                "native_amount_usd_per_unit": "0.24576",
                "native_quantity": 1,
                "public_unit_label": "estimate before generation",
                "quantity": 1,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "request_estimate"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np={'prompt': 'A cute baby sea otter', 'model': 'gpt-image-2', 'size': '1024x1024', 'n': 1, 'background': 'auto', 'moderation': 'auto', 'output_format': 'png'}\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n    if not items: raise SystemExit(\"No completed images; retain the full response\")\n    for index, item in enumerate(items):\n        encoded=item.get(\"b64_json\")\n        uri=item.get(\"url\", \"\")\n        if not encoded and uri.startswith(\"data:image/\"):\n            header, separator, encoded=uri.partition(\",\")\n            if not separator or \";base64\" not in header: raise SystemExit(\"Unsupported image data URI\")\n        if encoded:\n            raw=base64.b64decode(encoded,validate=True)\n        elif uri:\n            uri=urljoin(\"https://api.ailoot.ai\",uri)\n            parsed=urlsplit(uri)\n            if parsed.scheme!=\"https\" or not parsed.netloc or parsed.username or parsed.password:\n                raise SystemExit(\"Invalid returned image URL\")\n            owned=parsed.netloc==\"api.ailoot.ai\" and parsed.path.startswith(\"/v1/media/assets/\") and parsed.path.endswith(\"/content\")\n            args=[\"curl\",\"--fail-with-body\",\"--silent\",\"--show-error\",uri]\n            if owned: args += [\"-H\",\"Authorization: Bearer \"+os.environ[\"AILOOT_API_KEY\"]]\n            temporary=Path(f\"image-{index}.bin\")\n            subprocess.run(args+[\"-o\",str(temporary)],check=True)\n            raw=temporary.read_bytes()\n            temporary.unlink()\n        else: raise SystemExit(\"Image has neither bytes nor URL\")\n        if not raw: raise SystemExit(\"Empty image result\")\n        ext=\"png\" if raw.startswith(b\"\\x89PNG\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else \"svg\" if raw.lstrip().startswith((b\"<svg\",b\"<?xml\")) else \"bin\"\n        Path(f\"image-{index}.{ext}\").write_bytes(raw)\n    print(\"Every returned image saved; complete response metadata retained\")\nsave_images(json.loads(Path(\"result.json\").read_text())[\"data\"])\nPY_RESULT\n",
            "label": "curl · exact creation/save all outputs",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -o owned-assets.json\n# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.\n",
            "label": "Read existing owned assets",
            "language": "bash"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "images",
        "http": "POST",
        "in": null,
        "input": [
          "text"
        ],
        "label": "画像",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "out": null,
        "output": [
          "image"
        ],
        "path": "/v1/images/generations",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Not specified",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Not specified",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Not specified",
            "when": "When maximum reasoning effort uses the default adjustment"
          }
        ],
        "pricing": {
          "billing_mode": "original_invoice_usd",
          "image_input_price": null,
          "image_output_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "basis": "This estimate is not an additional charge or a fixed rate for the completed generation.",
            "dimensions": {
              "forecast_quantity": "one generation estimate"
            },
            "label": "Estimated generation cost",
            "units": [
              {
                "amount": "0.24576",
                "amount_unit": "usd_per_exact_native_unit",
                "billing_input": false,
                "estimate_only": true,
                "key": "forecast_usd",
                "label": "Estimated generation cost",
                "native_amount_usd_per_unit": "0.24576",
                "native_quantity": 1,
                "public_unit_label": "estimate before generation",
                "quantity": 1,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "request_estimate"
              }
            ]
          }
        ],
        "request_model_id": "gpt-image-2",
        "route_label": "Ultra",
        "status_reads": [
          "GET /v1/media/tasks/{task_id}"
        ],
        "tiers": [],
        "units": [
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          },
          {
            "amount": "0.24576",
            "amount_unit": "usd_per_exact_native_unit",
            "billing_input": false,
            "estimate_only": true,
            "key": "forecast_usd",
            "label": "Estimated generation cost",
            "native_amount_usd_per_unit": "0.24576",
            "native_quantity": 1,
            "public_unit_label": "estimate before generation",
            "quantity": 1,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "request_estimate"
          }
        ]
      },
      {
        "available": null,
        "billing_basis": {
          "basis": "original_invoice_usd",
          "description": "表示料金は生成前の費用の見積もりです。最終請求額は、元の生成処理に記録された費用から計算されます。実測された出力時間や予測数量が、そのまま最終的な課金数量になるわけではありません。",
          "forecast_quantity_is_estimate": true,
          "physical_output_is_billable_quantity": false,
          "version": "original_invoice_usd_v1"
        },
        "cache_read": null,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.",
            "lifecycle": {
              "assets": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets"
                },
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}"
                }
              ],
              "content": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}/content",
                  "url_source": "exact returned signed URL; never construct token"
                }
              ],
              "mode": "synchronous_result_then_owned_library",
              "operation_id_is_not_task_id": true,
              "status": [
                {
                  "http": "GET",
                  "id_source": "actual returned task_id or media library record",
                  "path": "/v1/media/tasks/{task_id}"
                }
              ],
              "unknown": "照合のため、返された X-Client-Request-ID を保存してください。実際に返された task_id/asset_id の値、または自分が所有するメディアライブラリだけを使って読み取ってください。操作 ID からタスクの URL を組み立てたり、作成リクエストを再送したりしないでください。"
            },
            "outputs": {
              "all_results": "レスポンスとヘッダーの全体、実際の出力すべて、最初に返された識別子、使用量フィールドすべてを保存してください。作成リクエストを再送せずに、元の操作を復旧してください。",
              "family": "image",
              "fields": [
                {
                  "description": null,
                  "name": "created",
                  "type": null
                },
                {
                  "description": null,
                  "name": "data[].url",
                  "type": null
                },
                {
                  "description": null,
                  "name": "data[].b64_json",
                  "type": null
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": null
                }
              ]
            },
            "parameters": [
              {
                "enum": [
                  "openai/gpt-image-2"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "min_length": 1,
                "name": "prompt",
                "required": true,
                "type": "string"
              },
              {
                "enum": [
                  "1:1",
                  "3:2",
                  "2:3",
                  "4:3",
                  "3:4",
                  "16:9",
                  "9:16",
                  "21:9",
                  "auto"
                ],
                "enum_known": true,
                "name": "aspect_ratio",
                "required": false,
                "type": "string"
              },
              {
                "enum": [
                  "auto",
                  "low",
                  "medium",
                  "high"
                ],
                "enum_known": true,
                "name": "quality",
                "required": false,
                "type": "string"
              },
              {
                "enum": [
                  "auto",
                  "opaque"
                ],
                "enum_known": true,
                "name": "background",
                "required": false,
                "type": "string"
              },
              {
                "maximum": 10,
                "minimum": 1,
                "name": "n",
                "required": false,
                "type": "integer"
              },
              {
                "items": {
                  "properties": {
                    "image_url": {
                      "properties": {
                        "url": {
                          "type": "string"
                        }
                      },
                      "required": [
                        "url"
                      ],
                      "type": "object"
                    },
                    "type": {
                      "const": "image_url"
                    }
                  },
                  "required": [
                    "type",
                    "image_url"
                  ],
                  "type": "object"
                },
                "maximum_items": 16,
                "minimum_items": 0,
                "name": "input_references",
                "required": false,
                "type": "array"
              },
              {
                "maximum": 100,
                "minimum": 0,
                "name": "output_compression",
                "required": false,
                "type": "integer"
              },
              {
                "name": "provider",
                "required": false,
                "type": "object"
              }
            ],
            "request_schema": {
              "properties": {
                "aspect_ratio": {
                  "enum": [
                    "1:1",
                    "3:2",
                    "2:3",
                    "4:3",
                    "3:4",
                    "16:9",
                    "9:16",
                    "21:9",
                    "auto"
                  ],
                  "type": "string"
                },
                "background": {
                  "enum": [
                    "auto",
                    "opaque"
                  ],
                  "type": "string"
                },
                "input_references": {
                  "items": {
                    "properties": {
                      "image_url": {
                        "properties": {
                          "url": {
                            "type": "string"
                          }
                        },
                        "required": [
                          "url"
                        ],
                        "type": "object"
                      },
                      "type": {
                        "const": "image_url"
                      }
                    },
                    "required": [
                      "type",
                      "image_url"
                    ],
                    "type": "object"
                  },
                  "maxItems": 16,
                  "minItems": 0,
                  "type": "array"
                },
                "model": {
                  "enum": [
                    "openai/gpt-image-2"
                  ],
                  "type": "string"
                },
                "n": {
                  "maximum": 10,
                  "minimum": 1,
                  "type": "integer"
                },
                "output_compression": {
                  "maximum": 100,
                  "minimum": 0,
                  "type": "integer"
                },
                "prompt": {
                  "minLength": 1,
                  "type": "string"
                },
                "provider": {
                  "description": "Exact image provider preferences from the documented image request schema.",
                  "type": "object"
                },
                "quality": {
                  "enum": [
                    "auto",
                    "low",
                    "medium",
                    "high"
                  ],
                  "type": "string"
                }
              },
              "required": [
                "model",
                "prompt"
              ],
              "type": "object"
            },
            "schema_template": {
              "actual_file_preparation_required": false,
              "body": {
                "model": "openai/gpt-image-2",
                "prompt": "a red panda astronaut floating in space, studio lighting"
              },
              "content_type": "application/json"
            }
          },
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "required": [
              "model",
              "prompt"
            ]
          },
          "lifecycle": {
            "assets": [
              {
                "http": "GET",
                "path": "/v1/media/assets"
              },
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}"
              }
            ],
            "content": [
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}/content",
                "url_source": "exact returned signed URL; never construct token"
              }
            ],
            "mode": "synchronous_result_then_owned_library",
            "operation_id_is_not_task_id": true,
            "status": [
              {
                "http": "GET",
                "id_source": "実際に返された task_id またはメディアライブラリのレコード",
                "path": "/v1/media/tasks/{task_id}"
              }
            ],
            "unknown": "Keep the returned X-Client-Request-ID for reconciliation. Read only actual returned task_id/asset_id values or the owned media library; never build a task URL from the operation ID and never resubmit creation."
          },
          "method": {
            "http": "POST",
            "path": "/v1/images/generations"
          },
          "output": {
            "all_results": "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.",
            "family": "image",
            "fields": [
              {
                "description": null,
                "name": "created",
                "type": null
              },
              {
                "description": null,
                "name": "data[].url",
                "type": null
              },
              {
                "description": null,
                "name": "data[].b64_json",
                "type": null
              },
              {
                "description": null,
                "name": "usage",
                "type": null
              }
            ]
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "basis": "この見積もりは追加料金ではなく、完了した生成処理に対する固定料金でもありません。",
            "dimensions": {
              "forecast_quantity": "one generation estimate"
            },
            "label": "生成費用の見積もり",
            "units": [
              {
                "amount": "0.24576",
                "amount_unit": "usd_per_exact_native_unit",
                "billing_input": false,
                "estimate_only": true,
                "key": "forecast_usd",
                "label": "Estimated generation cost",
                "native_amount_usd_per_unit": "0.24576",
                "native_quantity": 1,
                "public_unit_label": "estimate before generation",
                "quantity": 1,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "request_estimate"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np={'model': 'openai/gpt-image-2', 'prompt': 'a red panda astronaut floating in space, studio lighting'}\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n    if not items: raise SystemExit(\"No completed images; retain the full response\")\n    for index, item in enumerate(items):\n        encoded=item.get(\"b64_json\")\n        uri=item.get(\"url\", \"\")\n        if not encoded and uri.startswith(\"data:image/\"):\n            header, separator, encoded=uri.partition(\",\")\n            if not separator or \";base64\" not in header: raise SystemExit(\"Unsupported image data URI\")\n        if encoded:\n            raw=base64.b64decode(encoded,validate=True)\n        elif uri:\n            uri=urljoin(\"https://api.ailoot.ai\",uri)\n            parsed=urlsplit(uri)\n            if parsed.scheme!=\"https\" or not parsed.netloc or parsed.username or parsed.password:\n                raise SystemExit(\"Invalid returned image URL\")\n            owned=parsed.netloc==\"api.ailoot.ai\" and parsed.path.startswith(\"/v1/media/assets/\") and parsed.path.endswith(\"/content\")\n            args=[\"curl\",\"--fail-with-body\",\"--silent\",\"--show-error\",uri]\n            if owned: args += [\"-H\",\"Authorization: Bearer \"+os.environ[\"AILOOT_API_KEY\"]]\n            temporary=Path(f\"image-{index}.bin\")\n            subprocess.run(args+[\"-o\",str(temporary)],check=True)\n            raw=temporary.read_bytes()\n            temporary.unlink()\n        else: raise SystemExit(\"Image has neither bytes nor URL\")\n        if not raw: raise SystemExit(\"Empty image result\")\n        ext=\"png\" if raw.startswith(b\"\\x89PNG\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else \"svg\" if raw.lstrip().startswith((b\"<svg\",b\"<?xml\")) else \"bin\"\n        Path(f\"image-{index}.{ext}\").write_bytes(raw)\n    print(\"Every returned image saved; complete response metadata retained\")\nsave_images(json.loads(Path(\"result.json\").read_text())[\"data\"])\nPY_RESULT\n",
            "label": "curl · exact creation/save all outputs",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -o owned-assets.json\n# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.\n",
            "label": "Read existing owned assets",
            "language": "bash"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "images",
        "hints": [
          "Use the exact caller model ID and documented input representation.",
          "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again."
        ],
        "http": "POST",
        "in": null,
        "input": [
          "text",
          "image"
        ],
        "label": "画像",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [
          "/v1/images"
        ],
        "native_endpoint": "images",
        "out": null,
        "output": [
          "image"
        ],
        "path": "/v1/images/generations",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Not specified",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Not specified",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Not specified",
            "when": "When maximum reasoning effort uses the default adjustment"
          }
        ],
        "pricing": {
          "billing_mode": "original_invoice_usd",
          "image_input_price": null,
          "image_output_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": false,
                "estimate_only": true,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "basis": "This estimate is not an additional charge or a fixed rate for the completed generation.",
            "dimensions": {
              "forecast_quantity": "one generation estimate"
            },
            "label": "Estimated generation cost",
            "units": [
              {
                "amount": "0.24576",
                "amount_unit": "usd_per_exact_native_unit",
                "billing_input": false,
                "estimate_only": true,
                "key": "forecast_usd",
                "label": "Estimated generation cost",
                "native_amount_usd_per_unit": "0.24576",
                "native_quantity": 1,
                "public_unit_label": "estimate before generation",
                "quantity": 1,
                "quantity_is_estimate": true,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "request_estimate"
              }
            ]
          }
        ],
        "request_model_id": "openai/gpt-image-2",
        "route_label": "Ultra",
        "status_reads": [
          "GET /v1/media/tasks/{task_id}"
        ],
        "tiers": [],
        "units": [
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": false,
            "estimate_only": true,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          },
          {
            "amount": "0.24576",
            "amount_unit": "usd_per_exact_native_unit",
            "billing_input": false,
            "estimate_only": true,
            "key": "forecast_usd",
            "label": "Estimated generation cost",
            "native_amount_usd_per_unit": "0.24576",
            "native_quantity": 1,
            "public_unit_label": "estimate before generation",
            "quantity": 1,
            "quantity_is_estimate": true,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "request_estimate"
          }
        ]
      }
    ],
    "model_aliases": [
      {
        "canonical_model_id": "openai/gpt-image-2",
        "request_model_id": "gpt-image-2",
        "route_label": "Core"
      },
      {
        "canonical_model_id": "openai/gpt-image-2",
        "request_model_id": "gpt-image-2",
        "route_label": "Ultra"
      },
      {
        "canonical_model_id": "openai/gpt-image-2",
        "request_model_id": "openai/gpt-image-2",
        "route_label": "Ultra"
      }
    ],
    "name": "OpenAI: GPT Image 2",
    "price": {
      "estimate_only": true,
      "in": null,
      "in_label": null,
      "out": 0.24576,
      "out_label": "estimate before generation",
      "scope_label": "Estimated generation cost",
      "sort_in": null,
      "sort_out": 0.24576,
      "varies": false
    },
    "short": "GPT Image 2は、テキストと視覚参照から画像を生成・編集します。柔軟なフレーム寸法に対応し、すべての画像入力を自動で高忠実度処理します。完成素材の品質、形式、背景は個別に制御できます。"
  },
  "renderer_schema": {
    "method_order": "Original DTO methods order; every exact route/format/path/caller survives.",
    "prices": "Original public DTO fields and original native display HTML; no flattened or normalized offers."
  },
  "representation": "exact-public-dto-and-native-renderer-html",
  "representationNotes": {
    "current_reference": {
      "about_json_pointer": "/aboutHtml",
      "methods": [
        {
          "contract_json_pointer": "/methods/0/rawMethod/contract",
          "html_json_pointer": "/methods/0/html",
          "method_ordinal": 0
        },
        {
          "contract_json_pointer": "/methods/1/rawMethod/contract",
          "html_json_pointer": "/methods/1/html",
          "method_ordinal": 1
        },
        {
          "contract_json_pointer": "/methods/2/rawMethod/contract",
          "html_json_pointer": "/methods/2/html",
          "method_ordinal": 2
        }
      ],
      "role": "current-semantic-reference"
    },
    "raw_input": {
      "examples_role": "historical-input-not-current-ready-examples",
      "json_pointers": [
        "/rawModel",
        "/methods/0/rawMethod",
        "/methods/1/rawMethod",
        "/methods/2/rawMethod"
      ],
      "role": "historical-owner-input"
    },
    "schema": "ailoot-native-model-representations-v1"
  },
  "schema": "ailoot-static-model-facts-v1",
  "schema_version": 1,
  "shortText": "GPT Image 2は、テキストと視覚参照から画像を生成・編集します。柔軟なフレーム寸法に対応し、すべての画像入力を自動で高忠実度処理します。完成素材の品質、形式、背景は個別に制御できます。",
  "source": {
    "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1",
    "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036",
    "raw_model_json_sha256": "42909b3237e0173763d9847d90a36a35237208f45cf398e16b1b380a72763eaf",
    "renderer_sha256": "b06e5309d3e585ab5fe0535c1a8bd6320bdc357ea8509c2389320e8fa40c36e5"
  },
  "sourceRevision": "095a970ee9651bf31edabcc7a61a825b5d7efb464f344fe1dcfc69e893aa1abc"
}
