MODEL PRICING

明確なモデル価格とポイント

モデル料金、接続状況、利用条件を1ページで確認できます。実際の利用可否はAPIキー権限とサーバー回線で決まります。

ページ内容

モデル料金、接続状況、利用条件を1ページで確認できます。実際の利用可否はAPIキー権限とサーバー回線で決まります。

本ページは海外向け概要です。技術・契約上の正式な表現は中国語版を基準とします。

公開カタログ613モデル項目（候補を含む）

HCD Codex 接続ツール91モデル収録

画像スタジオ25モデル収録

音声スタジオ17モデル収録

リアルタイム音声スタジオ7モデル収録

動画スタジオ32モデル収録

文書スタジオ6モデル収録

ナレッジスタジオ26モデル収録

3D スタジオ3モデル収録

テキスト・コードスタジオ2モデル収録

各入口の公開済みモデル一覧を基に、同一スタジオ内では各モデルを1回だけ集計します。複数のスタジオに含まれるモデルもあります。実際の利用可否と機能は、APIキー権限、サーバー回線、各モデルの説明をご確認ください。

Completed capability declarations: 44. Each covers its stated deployment scope; model notes retain limits and pending items.

Token 料金は100万 Token あたりのポイントです。他の能力は表示単位で計算します。コンテキストと処理区分は各モデルの料金に従います。アカウントは実際の消費量で計算し、Key係数はKeyポイントのみに適用されます。利用可能なサービスは実際の使用量に応じてポイントを消費します。オンラインチャージと請求書発行は未開始です。

モデルポイント消費

独立モデルを優先表示します。同一プラットフォーム・世代・機能系列で利用可能な入口が一つだけの場合に限り、スナップショットやエイリアスを含めます。全種類を選ぶと他の版も検索でき、コード・料金・利用状態を個別に保持します。資料待ちや型関係の未確定は利用不可を意味しません。音声・サービス入口は新しい基盤モデルではありません。既存API経路や認証範囲は変更しません。

モデルの種類表示 / 全件: 482 / 613

Claude Haiku 5.5claude-haiku-5-5独立モデルAnthropic · 正式2026-10-07全機能価格の最終確認
確認待ち (UTC+8)

性能—費用対効果—

未評価

入力使用量 · 100万 Token あたり200,000 ポイントキャッシュヒット使用量 · 100万 Token あたり20,000 ポイントキャッシュ書込使用量 · 5m · 100万 Token あたり250,000 ポイントキャッシュ書込使用量 · 1h · 100万 Token あたり400,000 ポイント出力使用量 · 100万 Token あたり1,000,000 ポイントウェブ検索 · 1,000検索ユニットあたり20,000,000 ポイント

Claude Haiku 5.5-100claude-haiku-5-5-100独立モデルAnthropic · 正式2026-10-07固定単価なし。実際のサービスに応じて課金

性能 · Estimated74.7費用対効果 · Estimated82.3

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

未評価 · Confidence 0%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Gemini Nano Banana 2.1-100gemini-nano-banana-2.1独立モデルGoogle · 正式2026-10-06全機能価格の最終確認
確認待ち (UTC+8)

性能92.5費用対効果 · Estimated66.5

暫定評価

未評価 · Confidence 0%

入力使用量 · 100万 Token あたり3,000,000 ポイント入力使用量 · 画像 · 100万 Token あたり3,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり300,000 ポイント出力使用量 · 100万 Token あたり15,000,000 ポイントキャッシュヒット使用量 · 画像 · 100万 Token あたり300,000 ポイント出力使用量 · 画像 · 100万 Token あたり60,000,000 ポイント

Qwen-Image-2.1-Proqwen-image-2.1-pro独立モデルQwen · 正式2026-10-02全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated66.4費用対効果 · Estimated61.5

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

出力使用量 · 画像 · 1枚あたり68,494 ポイント

Grok 4.7-100grok-4.7-100独立モデルxAI · プレビュー2026-09-30全機能価格の最終確認
確認待ち (UTC+8)

性能—費用対効果—

未評価

入力使用量 · 100万 Token あたり4,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり1,000,000 ポイント出力使用量 · 100万 Token あたり12,000,000 ポイント

GPT-6.1 Solgpt-6.1-sol独立モデルOpenAI · 正式2026-09-29全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated82.2費用対効果 · Estimated69.2

12/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 76.4 (estimated) · 5/19 observed / reasoning 85.3 (estimated) · 3/13 observed / writing 84.8 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-6-astra · 1 benchmarksReference: gpt-6-luna · 1 benchmarksReference: gpt-6-sol · 1 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

入力使用量 · 100万 Token あたり4,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり200,000 ポイントキャッシュ書込使用量 · 100万 Token あたり5,000,000 ポイント出力使用量 · 100万 Token あたり20,000,000 ポイント

Claude Sonnet 5.5claude-sonnet-5-5独立モデルAnthropic · 正式2026-09-28全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated74.4費用対効果 · Estimated63.8

12/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 84.5 (estimated) · 5/19 observed / reasoning 78.8 (estimated) · 3/13 observed / writing 59.8 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

入力使用量 · 100万 Token あたり4,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり400,000 ポイントキャッシュ書込使用量 · 5m · 100万 Token あたり5,000,000 ポイントキャッシュ書込使用量 · 1h · 100万 Token あたり8,000,000 ポイント出力使用量 · 100万 Token あたり20,000,000 ポイントウェブ検索 · 1,000検索ユニットあたり20,000,000 ポイント

Claude Sonnet 5.5-100claude-sonnet-5-5-100独立モデルAnthropic · 正式2026-09-28固定単価なし。実際のサービスに応じて課金

性能 · Estimated74.4費用対効果 · Estimated67.1

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 84.5 (estimated) · 0/19 observed / reasoning 78.8 (estimated) · 0/13 observed / writing 59.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-sonnet-5-5 · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

决策模型（预览版）decision-model-preview独立モデルQwen · 正式2026-09-24全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり0 ポイント

Gemini 3.8 Live-100gemini-3.8-live独立モデルGoogle · 正式2026-09-24全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated76.9費用対効果 · Estimated68.8

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.9 (estimated) · 0/19 observed / reasoning 76.8 (estimated) · 0/13 observed / writing 87.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gemini-3.8-flash-high · 7 benchmarksReference: gemini-4-argon-high · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり1,500,000 ポイント動画入力 · 100万 Token あたり2,000,000 ポイント入力使用量 · 音声 · 100万 Token あたり6,000,000 ポイント出力使用量 · 100万 Token あたり9,000,000 ポイント出力使用量 · 音声 · 100万 Token あたり24,000,000 ポイント出力使用量 · 動画生成 · 100万 Token あたり2,000,000 ポイント

Claude Opus 5.5claude-opus-5-5独立モデルAnthropic · 正式2026-09-22全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated86.9費用対効果 · Estimated69.6

13/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 91.4 (estimated) · 5/19 observed / reasoning 94.0 (estimated) · 4/13 observed / writing 75.4 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

入力使用量 · 100万 Token あたり8,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり400,000 ポイントキャッシュ書込使用量 · 5m · 100万 Token あたり10,000,000 ポイントキャッシュ書込使用量 · 1h · 100万 Token あたり16,000,000 ポイント出力使用量 · 100万 Token あたり40,000,000 ポイントウェブ検索 · 1,000検索ユニットあたり20,000,000 ポイント

Claude Opus 5.5-100claude-opus-5-5-100独立モデルAnthropic · 正式2026-09-22固定単価なし。実際のサービスに応じて課金

性能 · Estimated86.9費用対効果 · Estimated75.8

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 91.4 (estimated) · 0/19 observed / reasoning 94.0 (estimated) · 0/13 observed / writing 75.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-opus-5-5 · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

GPT-6 Lunagpt-6-luna独立モデルOpenAI · 正式2026-09-22全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated59.4費用対効果 · Estimated65.7

Version comparison review13/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.8 (estimated) · 5/19 observed / reasoning 64.0 (estimated) · 4/13 observed / writing 50.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReview: below gpt-5.6-luna by 4.3 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

入力使用量 · 100万 Token あたり200,000 ポイントキャッシュヒット使用量 · 100万 Token あたり20,000 ポイントキャッシュ書込使用量 · 100万 Token あたり250,000 ポイント出力使用量 · 100万 Token あたり1,000,000 ポイント

GPT-6 Solgpt-6-sol独立モデルOpenAI · 正式2026-09-22全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated74.3費用対効果 · Estimated63.7

Version comparison review13/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 74.6 (estimated) · 5/19 observed / reasoning 78.4 (estimated) · 4/13 observed / writing 69.9 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReview: below gpt-5.6-sol by 8.8 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

入力使用量 · 100万 Token あたり4,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり400,000 ポイントキャッシュ書込使用量 · 100万 Token あたり5,000,000 ポイント出力使用量 · 100万 Token あたり20,000,000 ポイント

Grok 4.7grok-4.7独立モデルxAI · 正式2026-09-21全機能価格の最終確認
確認待ち (UTC+8)

性能—費用対効果—

未評価

Qwen-Audio-3.1-Realtime-Plusqwen-audio-3.1-realtime-plus独立モデルQwen · 正式2026-09-20固定単価なし。実際のサービスに応じて課金

性能 · Estimated52.6費用対効果 · Estimated51.8

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · Official

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen3.8-Livetranslate-Flash-Realtimeqwen3.8-livetranslate-flash-realtime独立モデルQwen · 正式2026-09-18固定単価なし。実際のサービスに応じて課金

性能 · Estimated52.6費用対効果 · Estimated51.8

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-MT-Uniqwen-mt-uni独立モデルQwen · 正式2026-09-16固定単価なし。実際のサービスに応じて課金

性能 · Estimated49.4費用対効果 · Estimated49.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 45.5 (estimated) · 0/19 observed / reasoning 54.8 (estimated) · 0/13 observed / writing 47.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: qwen-14b-chat · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-kimi/kimi-k2.8-previewqwen-kimi-kimi-k2.8-preview独立モデルMoonshot AI · 正式2026-09-11価格の最終確認
確認待ち (UTC+8)

性能 · Estimated41.0費用対効果 · Estimated29.9

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり1,780,822 ポイントキャッシュヒット使用量 · 100万 Token あたり465,753 ポイント出力使用量 · 100万 Token あたり7,397,260 ポイント

DeepSeek V4.1 Flashdeepseek-flash独立モデルDeepSeek · 正式2026-09-10全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated78.1費用対効果 · Estimated77.6

12/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 81.2 (estimated) · 4/19 observed / reasoning 82.4 (estimated) · 4/13 observed / writing 70.8 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksEstimated value uses this exact model's reviewed off-peak public point rates and the shared text workload. Weekday peak rates double; public holidays use off-peak rates. It is not a measured charge.arena · Independent arena · Independent livebench · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent

入力使用量 · 100万 Token あたり300,000 ポイントキャッシュヒット使用量 · 100万 Token あたり6,000 ポイント出力使用量 · 100万 Token あたり1,200,000 ポイント

doubao-deepseek-v4-1-flashdoubao-deepseek-v4-1-flash-260910固定スナップショット／版 · 唯一の入口DeepSeek · 正式2026-09-10全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated62.9

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり273,973 ポイントキャッシュヒット使用量 · 100万 Token あたり5,479 ポイント出力使用量 · 100万 Token あたり1,095,890 ポイント

qwen-DeepSeek V4.1 Flashqwen-deepseek-v4.1-flash独立モデルDeepSeek · 正式2026-09-10価格の最終確認
確認待ち (UTC+8)

性能 · Estimated61.4費用対効果 · Estimated66.3

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり273,973 ポイントキャッシュヒット使用量 · 100万 Token あたり27,397 ポイント出力使用量 · 100万 Token あたり1,095,890 ポイント

qwen-vanchin/deepseek-v4.1-flashqwen-vanchin-deepseek-v4.1-flash独立モデルDeepSeek · 正式2026-09-10固定単価なし。実際のサービスに応じて課金

性能 · Estimated61.4費用対効果 · Estimated58.0

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

GPT Image 2.5 Flaregpt-image-2.5-flare独立モデルOpenAI · 正式2026-09-08利用可能・生成と編集価格の最終確認
確認待ち (UTC+8)

性能98.5費用対効果70.3

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent arena · Independent

入力使用量 · 100万 Token あたり10,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり2,500,000 ポイント入力使用量 · 画像 · 100万 Token あたり16,000,000 ポイントキャッシュヒット使用量 · 画像 · 100万 Token あたり4,000,000 ポイント出力使用量 · 画像 · 100万 Token あたり60,000,000 ポイント

GPT Image 2.5 Sunburstgpt-image-2.5-sunburst独立モデルOpenAI · 正式2026-09-08利用可能・生成と編集価格の最終確認
確認待ち (UTC+8)

性能100.0費用対効果71.4

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent arena · Independent

GPT-6 Astragpt-6-astra独立モデルOpenAI · 正式2026-09-03全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated85.4費用対効果 · Estimated64.8

13/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 79.9 (estimated) · 5/19 observed / reasoning 92.0 (estimated) · 4/13 observed / writing 84.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksarena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

入力使用量 · 100万 Token あたり20,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり2,000,000 ポイントキャッシュ書込使用量 · 100万 Token あたり25,000,000 ポイント出力使用量 · 100万 Token あたり100,000,000 ポイント

Gemini 3.8 Flash-100gemini-3.8-flash-100独立モデルGoogle · 正式2026-09-02全機能価格の最終確認
確認待ち (UTC+8)

性能—費用対効果—

未評価

入力使用量 · 100万 Token あたり3,000,000 ポイント入力使用量 · 画像 · 100万 Token あたり3,000,000 ポイント入力使用量 · 音声 · 100万 Token あたり3,000,000 ポイント動画入力 · 100万 Token あたり3,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり300,000 ポイント出力使用量 · 100万 Token あたり15,000,000 ポイントキャッシュ書込使用量 · 100万 Token あたり3,000,000 ポイント明示的キャッシュ保存 · 100万Token・時間あたり2,000,000 ポイント

Claude Fable 5.1claude-fable-5-1独立モデルAnthropic · 正式2026-09-01全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated89.2費用対効果 · Estimated67.4

Shared exact-model performance from claude-fable-5-1; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 90.5 (estimated) · 5/19 observed / reasoning 93.8 (estimated) · 4/13 observed / writing 83.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

入力使用量 · 100万 Token あたり20,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり500,000 ポイントキャッシュ書込使用量 · 5m · 100万 Token あたり25,000,000 ポイントキャッシュ書込使用量 · 1h · 100万 Token あたり40,000,000 ポイント出力使用量 · 100万 Token あたり100,000,000 ポイントウェブ検索 · 1,000検索ユニットあたり20,000,000 ポイント

Claude Fable 5.1-100claude-fable-5-1-100独立モデルAnthropic · 正式2026-09-01固定単価なし。実際のサービスに応じて課金

性能 · Estimated89.2費用対効果—

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 90.5 (estimated) · 5/19 observed / reasoning 93.8 (estimated) · 4/13 observed / writing 83.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Doubao-Seed-2.1-Litedoubao-seed-2-1-lite-260915固定スナップショット／版 · 唯一の入口Doubao · 正式2026-09 (公式情報は月まで)価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated63.4

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 0%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 56.6microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり219,178 ポイントキャッシュヒット使用量 · 100万 Token あたり43,836 ポイント出力使用量 · 100万 Token あたり739,726 ポイント

doubao-seedream-5-0-flashdoubao-seedream-5-0-flash-260915固定スナップショット／版 · 唯一の入口Doubao · 正式2026-09 (公式情報は月まで)固定単価なし。実際のサービスに応じて課金

性能 · Estimated65.8費用対効果 · Estimated61.1

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: seedream-5.0-lite · 50.2Reference: seedream-5.0-pro · 85.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

千问3.7-通用文本向量-flashqwen3.7-text-embedding-flash独立モデルAlibaba Cloud · 正式2026-09-01価格の最終確認
確認待ち (UTC+8)

性能 · Estimated62.3費用対効果 · Estimated73.6

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Official aliyun-embedding · Official

埋め込み入力 · 100万 Token あたり34,247 ポイント

千问3.7-通用文本重排序qwen3.7-text-rerank独立モデルAlibaba Cloud · 正式2026-09-01全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated72.5費用対効果 · Estimated80.8

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3-Reranker-4B · 73.9Reference: Qwen3-Reranker-8B · 74.2Reference: Qwen3-Reranker-0.6B · 68.8qwen-rerank-public · Official

入力使用量 · 100万 Token あたり136,987 ポイント

Qwen3.8-Omni-Flashqwen3.8-omni-flash独立モデルQwen · 正式2026-09 (公式情報は月まで)固定単価なし。実際のサービスに応じて課金

性能 · Estimated61.4費用対効果 · Estimated58.0

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen3.8-Omni-Flash-Realtimeqwen3.8-omni-flash-realtime独立モデルQwen · 正式2026-09 (公式情報は月まで)固定単価なし。実際のサービスに応じて課金

性能 · Estimated52.6費用対効果 · Estimated51.8

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-MT-Image-2.0qwen-mt-image-2.0独立モデルQwen · 正式2026-08-28固定単価なし。実際のサービスに応じて課金

性能 · Estimated73.8費用対効果 · Estimated66.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Cohere Parse v5cohere-parse-v5独立モデルCohere · プレビュー2026-08-27全機能価格の最終確認
確認待ち (UTC+8)

性能79.2費用対効果85.4

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 18%cohere-parsebench · Official

文書処理 · 1,000ページあたり3,000,000 ポイント

Gemini Omni 1.1 Flash Preview-100gemini-omni-1.1-flash-preview独立モデルGoogle · 正式2026-08-27固定単価なし。実際のサービスに応じて課金

性能 · Estimated49.9費用対効果 · Estimated49.9

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 46.2 (estimated) · 0/19 observed / reasoning 44.4 (estimated) · 0/13 observed / writing 59.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gemini-3.5-flash-high · 7 benchmarksReference: gemini-1.5-flash-001 · 4 benchmarksReference: gemini-1.5-flash-002 · 4 benchmarksReference: gemini-1.5-flash-8b-001 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ZHIPU/GLM-5.3-Flashqwen-zhipu-glm-5.3-flash独立モデルZhipu AI · 正式2026-08-26価格の最終確認
確認待ち (UTC+8)

性能 · Estimated41.0費用対効果 · Estimated48.3

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり219,178 ポイントキャッシュヒット使用量 · 100万 Token あたり63,014 ポイント出力使用量 · 100万 Token あたり767,123 ポイント

Qwen3.8-Flashqwen3.8-flash独立モデルQwen · 正式2026-08-25価格の最終確認
確認待ち (UTC+8)

性能 · Estimated61.4費用対効果 · Estimated67.5

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

入力使用量 · 100万 Token あたり219,178 ポイントキャッシュヒット使用量 · 100万 Token あたり27,397 ポイント出力使用量 · 100万 Token あたり739,726 ポイント

qwen-Kimi-K3qwen-kimi-k3独立モデルMoonshot · 正式2026-08-19価格の最終確認
確認待ち (UTC+8)

性能 · Estimated39.7費用対効果 · Estimated38.2

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 35.6 (estimated) · 0/19 observed / reasoning 49.2 (estimated) · 0/13 observed / writing 34.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b · 4 benchmarksReference: qwen3-30b-a3b · 4 benchmarksReference: qwen3-32b · 4 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり5,479,452 ポイントキャッシュヒット使用量 · 100万 Token あたり547,945 ポイント出力使用量 · 100万 Token あたり27,397,260 ポイント

Qwen3.8-27Bqwen3.8-27b独立モデルQwen · 正式2026-08-17価格の最終確認
確認待ち (UTC+8)

性能 · Estimated65.0費用対効果 · Estimated64.2

13/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.4 (estimated) · 5/19 observed / reasoning 68.3 (estimated) · 4/13 observed / writing 62.4 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

入力使用量 · 100万 Token あたり821,918 ポイントキャッシュヒット使用量 · 100万 Token あたり164,384 ポイント出力使用量 · 100万 Token あたり3,287,671 ポイント

qwen-GLM-5.3qwen-glm-5.3独立モデルZhipu AI · 正式2026-08-14価格の最終確認
確認待ち (UTC+8)

性能 · Estimated61.1費用対効果 · Estimated57.8

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり2,191,781 ポイントキャッシュヒット使用量 · 100万 Token あたり547,945 ポイント出力使用量 · 100万 Token あたり7,671,233 ポイント

qwen-ZHIPU/GLM-5.3qwen-zhipu-glm-5.3独立モデルZhipu AI · 正式2026-08-14価格の最終確認
確認待ち (UTC+8)

性能 · Estimated41.0費用対効果 · Estimated28.7

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

DeepSeek V4 Prodeepseek-v4-pro独立モデルDeepSeek · 正式2026-08-13全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated64.4費用対効果 · Estimated62.3

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 53.8 (estimated) · 0/19 observed / reasoning 74.3 (estimated) · 0/13 observed / writing 65.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: deepseek-v4-pro · 7 benchmarksReference: deepseek-v4-pro-0813 · 7 benchmarksReference: deepseek-v4-pro · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり1,320,000 ポイントキャッシュヒット使用量 · 100万 Token あたり44,000 ポイント出力使用量 · 100万 Token あたり3,960,000 ポイント

GLM-5.3glm-5.3独立モデルZhipu · 正式2026-08-13価格の最終確認
確認待ち (UTC+8)

性能 · Estimated71.7費用対効果 · Estimated65.1

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 73.9 (estimated) · 0/19 observed / reasoning 71.1 (estimated) · 0/13 observed / writing 70.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-5.3 · 7 benchmarksReference: glm-5.2 · 6 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

GLM-5.3-Flashglm-5.3-flash独立モデルZhipu · 正式2026-08-13価格の最終確認
確認待ち (UTC+8)

性能 · Estimated65.1費用対効果 · Estimated70.0

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 69.5 (estimated) · 0/19 observed / reasoning 68.7 (estimated) · 0/13 observed / writing 57.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: glm-5.3-flash · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

Grok 4.6grok-4.6独立モデルxAI · プレビュー2026-08-12価格の最終確認
確認待ち (UTC+8)

性能 · Estimated70.4費用対効果 · Estimated61.9

Shared exact-model performance from grok-4.6; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 65.3 (estimated) · 5/19 observed / reasoning 72.6 (estimated) · 4/13 observed / writing 73.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

入力使用量 · 100万 Token あたり8,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり2,000,000 ポイント出力使用量 · 100万 Token あたり24,000,000 ポイント

Grok 4.6-100grok-4.6-100独立モデルxAI · 正式2026-08-12固定単価なし。実際のサービスに応じて課金

性能 · Estimated70.4費用対効果—

Shared exact-model performance from grok-4.6; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 65.3 (estimated) · 5/19 observed / reasoning 72.6 (estimated) · 4/13 observed / writing 73.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

MAI Thinking 1mai-thinking-1独立モデルMicrosoft AI · プレビュー2026-08-12全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated51.7

12/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 18%coding 56.8 (estimated) · 4/19 observed / reasoning 60.2 (estimated) · 5/13 observed / writing 52.8 (estimated) · 3/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksReference: smaug-flash · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり4,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり400,000 ポイント出力使用量 · 100万 Token あたり16,000,000 ポイント

Qwen3.8-2.4T-A95Bqwen3.8-2.4t-a95b独立モデルQwen · 正式2026-08-12価格の最終確認
確認待ち (UTC+8)

性能 · Estimated65.0費用対効果 · Estimated58.9

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.4 (estimated) · 0/19 observed / reasoning 68.3 (estimated) · 0/13 observed / writing 62.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen3.8-27b · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり3,287,671 ポイントキャッシュヒット使用量 · 100万 Token あたり410,959 ポイント出力使用量 · 100万 Token あたり9,863,014 ポイント

万相3.0-视频生成wan3.0-video独立モデルAlibaba Cloud · 正式2026-08-06価格の最終確認
確認待ち (UTC+8)

性能 · Estimated92.6費用対効果 · Estimated72.9

Estimate basis

動画生成 480P · 1秒あたり57,535 ポイント動画生成 720P · 1秒あたり115,069 ポイント動画生成 1080P · 1秒あたり230,137 ポイント

Qwen3.8-Maxqwen3.8-max独立モデルQwen · 正式2026-08-02価格の最終確認
確認待ち (UTC+8)

性能 · Estimated76.0費用対効果 · Estimated66.6

13/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 70.3 (estimated) · 5/19 observed / reasoning 82.3 (estimated) · 4/13 observed / writing 75.4 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

Gemini 3.5 Transcribe Live Preview-100gemini-3.5-transcribe-live-preview独立モデルGoogle · 正式2026-08 (公式情報は月まで)固定単価なし。実際のサービスに応じて課金

性能 · Estimated91.4費用対効果 · Estimated79.0

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Gemini 3.5 Transcribe Preview-100gemini-3.5-transcribe-preview独立モデルGoogle · 正式2026-08 (公式情報は月まで)固定単価なし。実際のサービスに応じて課金

性能 · Estimated91.4費用対効果 · Estimated79.0

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

doubao-DeepSeek V4 Flash GA (2026-07-31)doubao-deepseek-v4-flash-ga-260731固定スナップショット／版 · 唯一の入口DeepSeek · 正式2026-07-31全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated58.8

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり821,918 ポイントキャッシュヒット使用量 · 100万 Token あたり27,397 ポイント出力使用量 · 100万 Token あたり2,465,753 ポイント

qwen-MiniMax/MiniMax-H3qwen-minimax-minimax-h3独立モデルmini-max · 正式2026-07-31固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-Audio-3.0-ASR-Flashqwen-audio-3.0-asr-flash独立モデルAlibaba Cloud · 正式2026-07-30利用可能・音声ツール価格の最終確認
確認待ち (UTC+8)

性能 · Estimated91.4費用対効果 · Estimated94.0

Estimate basis

文字起こし · 1秒あたり61 ポイント

qwen-audio-3.0-asr-flash-filetransqwen-audio-3.0-asr-flash-filetrans独立モデルQwen · 正式2026-07-30固定単価なし。実際のサービスに応じて課金

性能 · Estimated91.4費用対効果 · Estimated79.0

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-Audio-3.0-ASR-Flash-Streamingqwen-audio-3.0-asr-flash-streaming独立モデルQwen · 正式2026-07-30固定単価なし。実際のサービスに応じて課金

性能 · Estimated91.4費用対効果 · Estimated79.0

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

GPT Live Transcribegpt-live-transcribe独立モデルOpenAI · 正式2026-07-28全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated91.4費用対効果 · Estimated64.0

Estimate basis

文字起こし · 1時間あたり2,040,000 ポイント

GPT Transcribegpt-transcribe独立モデルOpenAI · 正式2026-07-28利用可能・音声ツール価格の最終確認
確認待ち (UTC+8)

性能 · Estimated91.4費用対効果 · Estimated81.7

Estimate basis

文字起こし · 1時間あたり540,000 ポイント

qwen-PixVerse-V6-r2v-omniqwen-pixverse-pixverse-v6-r2v-omni独立モデルpixverse · 正式2026-07-26固定単価なし。実際のサービスに応じて課金

性能 · Estimated61.1費用対効果 · Estimated57.8

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Claude Opus 5claude-opus-5独立モデルAnthropic · 正式2026-07-24価格の最終確認
確認待ち (UTC+8)

性能 · Estimated81.9費用対効果 · Estimated65.2

Shared exact-model performance from claude-opus-5; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 85.2 (estimated) · 5/19 observed / reasoning 86.3 (estimated) · 4/13 observed / writing 74.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

入力使用量 · 100万 Token あたり10,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり1,000,000 ポイントキャッシュ書込使用量 · 5m · 100万 Token あたり12,500,000 ポイントキャッシュ書込使用量 · 1h · 100万 Token あたり20,000,000 ポイント出力使用量 · 100万 Token あたり50,000,000 ポイント

Claude Opus 5-100claude-opus-5-100独立モデルAnthropic · 正式2026-07-24固定単価なし。実際のサービスに応じて課金

性能 · Estimated81.9費用対効果—

Shared exact-model performance from claude-opus-5; coverage refers to public model benchmarks, not tests of every platform deployment.Version comparison review13/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 85.2 (estimated) · 5/19 observed / reasoning 86.3 (estimated) · 4/13 observed / writing 74.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below claude-opus-5-5-100 by 5.0 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Gemini 3.5 Flash-Lite-100gemini-3.5-flash-lite-100独立モデルGoogle · 正式2026-07-21価格の最終確認
確認待ち (UTC+8)

性能 · Estimated52.3費用対効果 · Estimated55.0

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 47.1 (estimated) · 0/19 observed / reasoning 52.8 (estimated) · 0/13 observed / writing 56.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gemini-3.5-flash-lite-high · 7 benchmarksReference: gemini-3.5-flash-lite · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり600,000 ポイントキャッシュヒット使用量 · 100万 Token あたり60,000 ポイント出力使用量 · 100万 Token あたり5,000,000 ポイント

Qwen3.7-Flashqwen3.7-flash独立モデルQwen · 正式2026-07-21価格の最終確認
確認待ち (UTC+8)

性能 · Estimated61.4費用対効果 · Estimated73.0

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

Input 0 – 32,000 Token入力使用量 · 100万 Token あたり54,795 ポイントキャッシュヒット使用量 · 100万 Token あたり10,959 ポイント出力使用量 · 100万 Token あたり219,178 ポイント

Input 32,001 – 256,000 Token入力使用量 · 100万 Token あたり164,384 ポイントキャッシュヒット使用量 · 100万 Token あたり32,877 ポイント出力使用量 · 100万 Token あたり657,534 ポイント

Input 256,001+ Token入力使用量 · 100万 Token あたり328,767 ポイントキャッシュヒット使用量 · 100万 Token あたり65,753 ポイント出力使用量 · 100万 Token あたり1,315,068 ポイント

Qwen-Image-3.0qwen-image-3.0独立モデルAlibaba Cloud · 正式2026-07-21利用可能・生成と編集価格の最終確認
確認待ち (UTC+8)

性能 · Estimated73.8費用対効果 · Estimated81.7

Estimate basis

画像入力使用量 1K · 1枚あたり5,480 ポイント画像入力使用量 2K · 1枚あたり5,480 ポイント画像出力使用量 1K · 1枚あたり49,316 ポイント画像出力使用量 2K · 1枚あたり49,316 ポイント

Kimi K3kimi-k3独立モデルMoonshot · 正式2026-07-16価格の最終確認
確認待ち (UTC+8)

性能 · Estimated80.1費用対効果 · Estimated66.4

13/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 81.7 (estimated) · 5/19 observed / reasoning 80.2 (estimated) · 4/13 observed / writing 78.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

qwen-kimi/kimi-k3qwen-kimi-kimi-k3独立モデルMoonshot AI · 正式2026-07-16価格の最終確認
確認待ち (UTC+8)

性能 · Estimated41.0費用対効果 · Estimated28.7

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

Qwen3.7-通用文本向量qwen3.7-text-embedding独立モデルAlibaba Cloud · 正式2026-07-15価格の最終確認
確認待ち (UTC+8)

性能 · Estimated62.3費用対効果 · Estimated53.1

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Official aliyun-embedding · Official

埋め込み入力 · 100万 Token あたり136,987 ポイント

Qwen-Audio-3.0-Realtime-Flashqwen-audio-3.0-realtime-flash独立モデルQwen · 正式2026-07-14固定単価なし。実際のサービスに応じて課金

性能 · Estimated52.6費用対効果 · Estimated51.8

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-Audio-3.0-Realtime-Plusqwen-audio-3.0-realtime-plus独立モデルQwen · 正式2026-07-14固定単価なし。実際のサービスに応じて課金

性能 · Estimated52.6費用対効果 · Estimated51.8

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

GPT-5.6 Lunagpt-5.6-luna独立モデルOpenAI · 正式2026-07-09全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated63.7費用対効果 · Estimated65.5

12/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.4 (estimated) · 4/19 observed / reasoning 72.6 (estimated) · 4/13 observed / writing 54.0 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.6-luna-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-sol-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-terra-xhigh (codex-harness) · 1 benchmarksarena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent

入力使用量 · 100万 Token あたり400,000 ポイントキャッシュヒット使用量 · 100万 Token あたり40,000 ポイントキャッシュ書込使用量 · 100万 Token あたり500,000 ポイント出力使用量 · 100万 Token あたり2,400,000 ポイント

GPT-5.6 Solgpt-5.6-sol独立モデルOpenAI · 正式2026-07-09全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated83.1費用対効果 · Estimated67.0

12/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 77.4 (estimated) · 4/19 observed / reasoning 89.4 (estimated) · 4/13 observed / writing 82.6 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.6-luna-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-sol-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-terra-xhigh (codex-harness) · 1 benchmarksarena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent

入力使用量 · 100万 Token あたり8,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり800,000 ポイントキャッシュ書込使用量 · 100万 Token あたり10,000,000 ポイント出力使用量 · 100万 Token あたり40,000,000 ポイント

GPT-5.6 Terragpt-5.6-terra独立モデルOpenAI · 正式2026-07-09全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated73.1費用対効果 · Estimated62.5

12/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 65.0 (estimated) · 4/19 observed / reasoning 85.1 (estimated) · 4/13 observed / writing 69.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.6-luna-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-sol-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-terra-xhigh (codex-harness) · 1 benchmarksarena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent

入力使用量 · 100万 Token あたり4,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり400,000 ポイントキャッシュ書込使用量 · 100万 Token あたり5,000,000 ポイント出力使用量 · 100万 Token あたり24,000,000 ポイント

gpt-live-1gpt-live-1独立モデルOpenAI · 正式2026-07-08固定単価なし。実際のサービスに応じて課金

性能 · Estimated48.3費用対効果 · Estimated48.8

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.4 (estimated) · 0/19 observed / reasoning 52.2 (estimated) · 0/13 observed / writing 41.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: gpt-4-0125-preview · 10 benchmarksReference: gpt-4-1106-preview · 10 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4o · 7 benchmarksReference: gpt-5.2 · 7 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

GPT Realtime 2.1gpt-realtime-2.1独立モデルOpenAI · プレビュー2026-07-06リアルタイム音声・テキストに対応。画像入力と通話中のツール実行は未対応です。価格の最終確認
確認待ち (UTC+8)

性能 · Estimated45.3費用対効果 · Estimated31.7

Estimate basis

入力使用量 · 100万 Token あたり8,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり800,000 ポイント出力使用量 · 100万 Token あたり48,000,000 ポイント入力使用量 · 画像 · 100万 Token あたり10,000,000 ポイントキャッシュヒット使用量 · 画像 · 100万 Token あたり1,000,000 ポイント入力使用量 · 音声 · 100万 Token あたり64,000,000 ポイントキャッシュヒット使用量 · 音声 · 100万 Token あたり800,000 ポイント出力使用量 · 音声 · 100万 Token あたり128,000,000 ポイント

GPT Realtime 2.1 Minigpt-realtime-2.1-mini独立モデルOpenAI · プレビュー2026-07-06リアルタイム音声・テキストに対応。画像入力と通話中のツール実行は未対応です。価格の最終確認
確認待ち (UTC+8)

性能 · Estimated45.3費用対効果 · Estimated61.7

Estimate basis

入力使用量 · 100万 Token あたり1,200,000 ポイントキャッシュヒット使用量 · 100万 Token あたり120,000 ポイント出力使用量 · 100万 Token あたり4,800,000 ポイント入力使用量 · 画像 · 100万 Token あたり1,600,000 ポイントキャッシュヒット使用量 · 画像 · 100万 Token あたり160,000 ポイント入力使用量 · 音声 · 100万 Token あたり20,000,000 ポイントキャッシュヒット使用量 · 音声 · 100万 Token あたり600,000 ポイント出力使用量 · 音声 · 100万 Token あたり40,000,000 ポイント

Qwen-Audio-3.0-TTS-Flashqwen-audio-3.0-tts-flash独立モデルAlibaba Cloud · 正式2026-07 (公式情報は月まで)利用可能・音声ツール価格の最終確認
確認待ち (UTC+8)

性能 · Estimated74.4費用対効果 · Estimated74.8

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4qwen-tts-public · Official

音声 · 10,000文字あたり273,973 ポイント

Qwen-Audio-3.0-TTS-Plusqwen-audio-3.0-tts-plus独立モデルAlibaba Cloud · 正式2026-07 (公式情報は月まで)利用可能・音声ツール価格の最終確認
確認待ち (UTC+8)

性能 · Estimated74.4費用対効果 · Estimated63.8

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4qwen-tts-public · Official

音声 · 10,000文字あたり383,562 ポイント

claude-sonnet-5claude-sonnet-5独立モデルAnthropic · 正式2026-06-30固定単価なし。実際のサービスに応じて課金

性能 · Estimated70.2費用対効果 · Estimated64.1

13/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 76.0 (estimated) · 5/19 observed / reasoning 76.6 (estimated) · 4/13 observed / writing 58.1 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

claude-sonnet-5-100claude-sonnet-5-100独立モデルAnthropic · 正式2026-06-30固定単価なし。実際のサービスに応じて課金

性能 · Estimated70.2費用対効果 · Estimated64.1

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 76.0 (estimated) · 0/19 observed / reasoning 76.6 (estimated) · 0/13 observed / writing 58.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-sonnet-5 · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below claude-sonnet-5-5-100 by 4.2 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Doubao Seed 2.1 Turbo (2026-06-28)doubao-seed-2-1-turbo-260628固定スナップショット／版 · 唯一の入口ByteDance · 正式2026-06-28価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated57.9

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり821,918 ポイントキャッシュヒット使用量 · 100万 Token あたり164,384 ポイント出力使用量 · 100万 Token あたり4,109,589 ポイント

Mistral OCR 4mistral-ocr-4-0独立モデルMistral AI · プレビュー2026-06-23全機能価格の最終確認
確認待ち (UTC+8)

性能81.8費用対効果57.3

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 25%mistral-ocr · Official cohere-parsebench · Official

文書処理 · 1,000ページあたり8,000,000 ポイント構造化注釈付き文書処理 · 1,000ページあたり10,000,000 ポイント

HappyHorse-1.1-I2Vhappyhorse-1.1-i2v独立モデルAlibaba Cloud · 正式2026-06-22価格の最終確認
確認待ち (UTC+8)

性能 · Estimated80.9費用対効果 · Estimated56.6

Estimate basis

動画生成 480P · 1秒あたり123,288 ポイント動画生成 720P · 1秒あたり246,576 ポイント動画生成 1080P · 1秒あたり328,768 ポイント

HappyHorse-1.1-R2Vhappyhorse-1.1-r2v独立モデルAlibaba Cloud · 正式2026-06-22価格の最終確認
確認待ち (UTC+8)

性能 · Estimated80.9費用対効果 · Estimated56.6

Estimate basis

動画生成 480P · 1秒あたり123,288 ポイント動画生成 720P · 1秒あたり246,576 ポイント動画生成 1080P · 1秒あたり328,768 ポイント

HappyHorse-1.1-T2Vhappyhorse-1.1-t2v独立モデルAlibaba Cloud · 正式2026-06-22価格の最終確認
確認待ち (UTC+8)

性能 · Estimated80.9費用対効果 · Estimated56.6

Estimate basis

動画生成 480P · 1秒あたり123,288 ポイント動画生成 720P · 1秒あたり246,576 ポイント動画生成 1080P · 1秒あたり328,768 ポイント

doubao-GLM 5.2 (2026-06-17)doubao-glm-5-2-260617固定スナップショット／版 · 唯一の入口Zhipu · 正式2026-06-17価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated54.5

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

qwen-HappyOyster-1.0-Adventureqwen-happyoyster-1.0-adventure独立モデルhappyoyster · 正式2026-06-17固定単価なし。実際のサービスに応じて課金

性能 · Estimated43.2費用対効果 · Estimated45.2

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.0 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 41.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

GLM-5.2glm-5.2独立モデルZhipu · 正式2026-06-16価格の最終確認
確認待ち (UTC+8)

性能 · Estimated66.4費用対効果 · Estimated61.3

13/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 68.8 (estimated) · 5/19 observed / reasoning 70.9 (estimated) · 4/13 observed / writing 59.6 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

Qwen3.5-OCRqwen3.5-ocr独立モデルAlibaba Cloud · 正式2026-06-16価格の最終確認
確認待ち (UTC+8)

性能 · Estimated81.8費用対効果 · Estimated72.3

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mistral-ocr-4-0 · 81.8Reference: cohere-parse-v5 · 79.2Reference: mistral-document-ai-2512 · 96.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.mistral-ocr · Official cohere-parsebench · Official mistral-ocr · Official

入力使用量 · 100万 Token あたり136,987 ポイント出力使用量 · 100万 Token あたり547,946 ポイント

qwen-GLM-5.2qwen-glm-5.2独立モデルZhipu · 正式2026-06-16価格の最終確認
確認待ち (UTC+8)

性能 · Estimated61.1費用対効果 · Estimated57.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

qwen-pixverse/pixverse-upscaleqwen-pixverse-pixverse-upscale独立モデルpixverse · 正式2026-06-16固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ZHIPU/GLM-5.2qwen-zhipu-glm-5.2独立モデルZhipu AI · 正式2026-06-16価格の最終確認
確認待ち (UTC+8)

性能 · Estimated41.0費用対効果 · Estimated28.7

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

qwen-kimi-k2.7-codeqwen-kimi-k2.7-code独立モデルMoonshot · 正式2026-06-15価格の最終確認
確認待ち (UTC+8)

性能 · Estimated34.7費用対効果 · Estimated39.7

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 41.4 (estimated) · 0/13 observed / writing 28.5 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2.5-72b-instruct · 4 benchmarksReference: qwen2.5-coder-32b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり1,780,822 ポイントキャッシュヒット使用量 · 100万 Token あたり356,164 ポイント出力使用量 · 100万 Token あたり7,397,260 ポイント

Kimi K2.7 Codekimi-k2.7-code独立モデルMoonshot · 正式2026-06-12価格の最終確認
確認待ち (UTC+8)

性能 · Estimated46.3費用対効果 · Estimated47.8

8/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 47.8 (estimated) · 3/19 observed / reasoning 48.4 (estimated) · 3/13 observed / writing 42.8 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksarena · Independent livebench · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent

qwen-kimi/kimi-k2.7-codeqwen-kimi-kimi-k2.7-code独立モデルMoonshot AI · 正式2026-06-12価格の最終確認
確認待ち (UTC+8)

性能 · Estimated41.0費用対効果 · Estimated29.9

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

claude-fable-5claude-fable-5独立モデルAnthropic · 正式2026-06-09固定単価なし。実際のサービスに応じて課金

性能 · Estimated87.7費用対効果 · Estimated76.4

13/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 85.6 (estimated) · 5/19 observed / reasoning 90.7 (estimated) · 4/13 observed / writing 86.7 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

claude-fable-5-100claude-fable-5-100独立モデルAnthropic · 正式2026-06-09固定単価なし。実際のサービスに応じて課金

性能 · Estimated87.7費用対効果 · Estimated76.4

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 85.6 (estimated) · 0/19 observed / reasoning 90.7 (estimated) · 0/13 observed / writing 86.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-fable-5 · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below claude-fable-5-1-100 by 1.5 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen3.7-Max-2026-06-08qwen3.7-max-2026-06-08固定スナップショット／版 · 唯一の入口Qwen · 正式2026-06-09価格の最終確認
確認待ち (UTC+8)

性能 · Estimated64.5費用対効果 · Estimated58.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.2 (estimated) · 0/19 observed / reasoning 69.6 (estimated) · 0/13 observed / writing 73.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.7-max · 8 benchmarksReference: qwen3.7-max-preview · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり3,287,671 ポイントキャッシュヒット使用量 · 100万 Token あたり657,534 ポイント出力使用量 · 100万 Token あたり9,863,014 ポイント

doubao-seedance-2-5-260628doubao-seedance-2-5-260628固定スナップショット／版 · 唯一の入口ByteDance · 正式2026-06 (公式情報は月まで)価格の最終確認
確認待ち (UTC+8)

性能 · Estimated90.4費用対効果 · Estimated63.3

Version comparison review

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: dreamina-seedance-2.5-720p · 90.4Review: below doubao-seedance-2-0-260128 by 1.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independent arena · Independent

出力使用量 · 動画生成 · 100万 Token あたり19,178,083 ポイント

doubao-seed-evolvingdoubao-seed-evolvingエイリアス · 唯一の入口Doubao · 正式2026-06 (公式情報は月まで)固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

doubao-seedream-5-0-pro-260628doubao-seedream-5-0-pro-260628固定スナップショット／版 · 唯一の入口ByteDance · 正式2026-06 (公式情報は月まで)利用可能・生成と編集価格の最終確認
確認待ち (UTC+8)

性能 · Estimated85.2費用対効果 · Estimated69.2

Estimate basis

出力使用量 · 画像 · 1枚あたり82,192 ポイント入力使用量 · 画像 · 1枚あたり5,480 ポイント

Fun-ASR-Flash-2026-06-15fun-asr-flash-2026-06-15固定スナップショット／版 · 唯一の入口Alibaba Cloud · 正式2026-06 (公式情報は月まで)利用可能・音声ツール価格の最終確認
確認待ち (UTC+8)

性能 · Estimated91.4費用対効果 · Estimated94.0

Estimate basis

文字起こし · 1秒あたり61 ポイント

Qwen3.7-Plusqwen3.7-plus独立モデルQwen · 正式2026-06-01価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.0費用対効果 · Estimated60.5

5/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.7 (estimated) · 2/19 observed / reasoning 62.0 (estimated) · 1/13 observed / writing 55.4 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-plus · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent livebench · Independent

Input 0 – 256,000 Token入力使用量 · 100万 Token あたり438,356 ポイントキャッシュヒット使用量 · 100万 Token あたり87,671 ポイント出力使用量 · 100万 Token あたり1,753,425 ポイント

Input 256,001+ Token入力使用量 · 100万 Token あたり1,315,068 ポイントキャッシュヒット使用量 · 100万 Token あたり263,014 ポイント出力使用量 · 100万 Token あたり5,260,274 ポイント

qwen-MiniMax/MiniMax-M3qwen-minimax-minimax-m3独立モデルmini-max · 正式2026-06-01価格の最終確認
確認待ち (UTC+8)

性能 · Estimated41.0費用対効果 · Estimated46.0

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b-thinking-2507 · 4 benchmarksReference: qwen3-30b-a3b · 4 benchmarksReference: qwen3-32b · 4 benchmarksReview: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり1,150,685 ポイントキャッシュヒット使用量 · 100万 Token あたり230,137 ポイント出力使用量 · 100万 Token あたり4,602,740 ポイント

qwen-stepfun/step-3.7-flashqwen-stepfun-step-3.7-flash独立モデルstepfun · 正式2026-05-29価格の最終確認
確認待ち (UTC+8)

性能 · Estimated61.4費用対効果 · Estimated64.2

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

入力使用量 · 100万 Token あたり369,863 ポイントキャッシュヒット使用量 · 100万 Token あたり73,973 ポイント出力使用量 · 100万 Token あたり2,219,178 ポイント

claude-opus-4-8claude-opus-4-8独立モデルAnthropic · 正式2026-05-28固定単価なし。実際のサービスに応じて課金

性能 · Estimated74.3費用対効果 · Estimated67.0

13/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 72.3 (estimated) · 5/19 observed / reasoning 77.9 (estimated) · 4/13 observed / writing 72.6 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

claude-opus-4-8-100claude-opus-4-8-100独立モデルAnthropic · 正式2026-05-28固定単価なし。実際のサービスに応じて課金

性能 · Estimated74.3費用対効果 · Estimated67.0

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 72.3 (estimated) · 0/19 observed / reasoning 77.9 (estimated) · 0/13 observed / writing 72.6 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-opus-4-8 · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen3.7-Maxqwen3.7-max独立モデルQwen · 正式2026-05-21価格の最終確認
確認待ち (UTC+8)

性能 · Estimated64.5費用対効果 · Estimated58.6

8/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.2 (estimated) · 3/19 observed / reasoning 69.6 (estimated) · 3/13 observed / writing 73.8 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.7-max-preview · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarkslivebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent

Cohere Command A Pluscohere-command-a-plus-05-2026独立モデルCohere · プレビュー2026-05-20価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated55.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり1,600,000 ポイント出力使用量 · 100万 Token あたり6,400,000 ポイント

Qwen3.7-Max-Previewqwen3.7-max-preview独立モデルQwen · プレビュー2026-05-20価格の最終確認
確認待ち (UTC+8)

性能 · Estimated64.5費用対効果 · Estimated58.6

4/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.2 (estimated) · 1/19 observed / reasoning 69.6 (estimated) · 1/13 observed / writing 73.8 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.7-max · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり3,287,671 ポイントキャッシュヒット使用量 · 100万 Token あたり0 ポイント出力使用量 · 100万 Token あたり9,863,014 ポイント

Qwen3.5-LiveTranslate-Flash-Realtimeqwen3.5-livetranslate-flash-realtime独立モデルQwen · 正式2026-05-19固定単価なし。実際のサービスに応じて課金

性能 · Estimated52.6費用対効果 · Estimated51.8

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Grok 4.3grok-4.3独立モデルxAI · プレビュー2026-05-12価格の最終確認
確認待ち (UTC+8)

性能 · Estimated44.8費用対効果 · Estimated46.5

Shared exact-model performance from grok-4.3; coverage refers to public model benchmarks, not tests of every platform deployment.12/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.8 (estimated) · 4/19 observed / reasoning 48.3 (estimated) · 4/13 observed / writing 47.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independent arena · Independent livebench · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent

入力使用量 · 100万 Token あたり2,500,000 ポイントキャッシュヒット使用量 · 100万 Token あたり400,000 ポイント出力使用量 · 100万 Token あたり5,000,000 ポイント

Mistral Medium 3.5mistral-medium-3-5独立モデルMistral AI · プレビュー2026-04-28全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated60.6費用対効果 · Estimated55.3

6/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.4 (estimated) · 3/19 observed / reasoning 70.3 (estimated) · 1/13 observed / writing 61.1 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksarena · Independent arena · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official livebench · Independent

入力使用量 · 100万 Token あたり3,000,000 ポイント出力使用量 · 100万 Token あたり15,000,000 ポイント

HappyHorse-1.0-I2Vhappyhorse-1.0-i2v独立モデルAlibaba Cloud · 正式2026-04-27価格の最終確認
確認待ち (UTC+8)

性能 · Estimated80.9費用対効果 · Estimated56.6

Estimate basis

動画生成 720P · 1秒あたり246,576 ポイント動画生成 1080P · 1秒あたり438,357 ポイント

HappyHorse-1.0-R2Vhappyhorse-1.0-r2v独立モデルAlibaba Cloud · 正式2026-04-27価格の最終確認
確認待ち (UTC+8)

性能 · Estimated80.9費用対効果 · Estimated56.6

Estimate basis

動画生成 720P · 1秒あたり246,576 ポイント動画生成 1080P · 1秒あたり438,357 ポイント

HappyHorse-1.0-T2Vhappyhorse-1.0-t2v独立モデルAlibaba Cloud · 正式2026-04-27価格の最終確認
確認待ち (UTC+8)

性能 · Estimated80.9費用対効果 · Estimated56.6

Estimate basis

動画生成 720P · 1秒あたり246,576 ポイント動画生成 1080P · 1秒あたり438,357 ポイント

qwen-DeepSeek-V4-Proqwen-deepseek-v4-pro独立モデルDeepSeek · 正式2026-04-24全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated70.1費用対効果 · Estimated63.1

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.8 (estimated) · 0/19 observed / reasoning 74.5 (estimated) · 0/13 observed / writing 69.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen3.8-27b · 13 benchmarksReference: qwen3.8-max · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり3,287,671 ポイントキャッシュヒット使用量 · 100万 Token あたり273,973 ポイント出力使用量 · 100万 Token あたり6,575,342 ポイント

GPT-5.5gpt-5.5独立モデルOpenAI · 正式2026-04-23価格の最終確認
確認待ち (UTC+8)

性能 · Estimated80.5費用対効果 · Estimated63.8

12/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 71.8 (estimated) · 4/19 observed / reasoning 88.6 (estimated) · 4/13 observed / writing 81.1 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.5 (codex-harness) · 1 benchmarksReference: gpt-5.5-high (codex-harness) · 1 benchmarksReference: gpt-5.5-xhigh (codex-harness) · 1 benchmarksarena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent

入力使用量 · 100万 Token あたり10,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり1,000,000 ポイント出力使用量 · 100万 Token あたり60,000,000 ポイント

qwen-xiaomi/mimo-v2.5-proqwen-xiaomi-mimo-v2.5-pro独立モデルXiaomi · 正式2026-04-23価格の最終確認
確認待ち (UTC+8)

性能 · Estimated41.0費用対効果 · Estimated30.5

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり1,917,808 ポイントキャッシュヒット使用量 · 100万 Token あたり383,562 ポイント出力使用量 · 100万 Token あたり5,753,425 ポイント

Qwen3.6-27Bqwen3.6-27b独立モデルQwen · 正式2026-04-22価格の最終確認
確認待ち (UTC+8)

性能 · Estimated46.6費用対効果 · Estimated50.5

7/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 40.1 (estimated) · 2/19 observed / reasoning 56.9 (estimated) · 3/13 observed / writing 42.8 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.5-122b-a10b · 5 benchmarksReference: qwen3.5-27b · 5 benchmarksReference: qwen3.5-397b-a17b · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarkslivebench · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent

入力使用量 · 100万 Token あたり821,918 ポイントキャッシュヒット使用量 · 100万 Token あたり0 ポイント出力使用量 · 100万 Token あたり4,931,507 ポイント

GPT Image 2gpt-image-2独立モデルOpenAI · 正式2026-04-21利用可能・生成と編集価格の最終確認
確認待ち (UTC+8)

性能97.0費用対効果69.3

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent arena · Independent

qwen-Kimi-K2.6qwen-kimi-k2.6独立モデルMoonshot · 正式2026-04-21価格の最終確認
確認待ち (UTC+8)

性能 · Estimated34.9費用対効果 · Estimated39.9

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 41.8 (estimated) · 0/13 observed / writing 28.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2.5-72b-instruct · 4 benchmarksReference: qwen2.5-coder-32b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

Kimi K2.6kimi-k2.6独立モデルMoonshot · 正式2026-04-20価格の最終確認
確認待ち (UTC+8)

性能 · Estimated77.4費用対効果 · Estimated69.6

5/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 77.8 (estimated) · 2/19 observed / reasoning 78.7 (estimated) · 1/13 observed / writing 75.7 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: kimi-k3 · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり1,780,822 ポイントキャッシュヒット使用量 · 100万 Token あたり301,370 ポイント出力使用量 · 100万 Token あたり7,397,260 ポイント

qwen-Kimi/Kimi K2.6qwen-kimi-kimi-k2.6独立モデルMoonshot AI · 正式2026-04-20価格の最終確認
確認待ち (UTC+8)

性能 · Estimated41.0費用対効果 · Estimated29.9

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

claude-opus-4-7claude-opus-4-7独立モデルAnthropic · 正式2026-04-16固定単価なし。実際のサービスに応じて課金

性能 · Estimated74.1費用対効果 · Estimated66.9

12/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 73.6 (estimated) · 4/19 observed / reasoning 81.7 (estimated) · 4/13 observed / writing 67.0 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent livebench · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

claude-opus-4-7-100claude-opus-4-7-100独立モデルAnthropic · 正式2026-04-16固定単価なし。実際のサービスに応じて課金

性能 · Estimated74.1費用対効果 · Estimated66.9

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 73.6 (estimated) · 0/19 observed / reasoning 81.7 (estimated) · 0/13 observed / writing 67.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-opus-4-7 · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen3.6-35B-A3Bqwen3.6-35b-a3b独立モデルQwen · 正式2026-04-16価格の最終確認
確認待ち (UTC+8)

性能 · Estimated45.4費用対効果 · Estimated51.8

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.0 (estimated) · 0/19 observed / reasoning 54.8 (estimated) · 0/13 observed / writing 42.3 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3.5-122b-a10b · 5 benchmarksReference: qwen3.5-35b-a3b · 5 benchmarksReference: qwen3.5-397b-a17b · 5 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり493,151 ポイントキャッシュヒット使用量 · 100万 Token あたり0 ポイント出力使用量 · 100万 Token あたり2,958,904 ポイント

Qwen3.6-Flashqwen3.6-flash独立モデルQwen · 正式2026-04-16価格の最終確認
確認待ち (UTC+8)

性能 · Estimated58.2費用対効果 · Estimated62.4

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

Input 0 – 256,000 Token入力使用量 · 100万 Token あたり328,767 ポイントキャッシュヒット使用量 · 100万 Token あたり65,753 ポイント出力使用量 · 100万 Token あたり1,972,603 ポイント

Input 256,001+ Token入力使用量 · 100万 Token あたり1,315,068 ポイントキャッシュヒット使用量 · 100万 Token あたり263,014 ポイント出力使用量 · 100万 Token あたり7,890,411 ポイント

qwen-GLM-5.1qwen-glm-5.1独立モデルZhipu · 正式2026-04-14価格の最終確認
確認待ち (UTC+8)

性能 · Estimated61.1費用対効果 · Estimated58.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

Input 0 – 32,000 Token入力使用量 · 100万 Token あたり1,643,836 ポイントキャッシュヒット使用量 · 100万 Token あたり328,767 ポイント出力使用量 · 100万 Token あたり6,575,342 ポイント

Input 32,001+ Token入力使用量 · 100万 Token あたり2,191,781 ポイントキャッシュヒット使用量 · 100万 Token あたり438,356 ポイント出力使用量 · 100万 Token あたり7,671,233 ポイント

qwen-ViduQ3-mix_reference2videoqwen-vidu-viduq3-mix_reference2video独立モデルvidu · 正式2026-04-13固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ3_reference2videoqwen-vidu-viduq3_reference2video独立モデルvidu · 正式2026-04-13固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ3-Turbo_reference2videoqwen-vidu-viduq3-turbo_reference2video独立モデルvidu · 正式2026-04-13固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-PixVerse-C1-it2vqwen-pixverse-pixverse-c1-it2v独立モデルpixverse · 正式2026-04-07固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-PixVerse-C1-kf2vqwen-pixverse-pixverse-c1-kf2v独立モデルpixverse · 正式2026-04-07固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-PixVerse-C1-r2vqwen-pixverse-pixverse-c1-r2v独立モデルpixverse · 正式2026-04-07固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-PixVerse-C1-t2vqwen-pixverse-pixverse-c1-t2v独立モデルpixverse · 正式2026-04-07固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ZHIPU/GLM-5.1qwen-zhipu-glm-5.1独立モデルZhipu AI · 正式2026-04-07価格の最終確認
確認待ち (UTC+8)

性能 · Estimated41.0費用対効果 · Estimated28.7

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

Wan2.7-I2Vwan2.7-i2v独立モデルAlibaba Cloud · 正式2026-04-07価格の最終確認
確認待ち (UTC+8)

性能78.7費用対効果63.2

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent

動画生成 720P · 1秒あたり164,384 ポイント動画生成 1080P · 1秒あたり273,973 ポイント

Wan2.7-R2Vwan2.7-r2v独立モデルAlibaba Cloud · 正式2026-04-07価格の最終確認
確認待ち (UTC+8)

性能 · Estimated69.2費用対効果 · Estimated56.5

Estimate basis

動画生成 720P · 1秒あたり164,384 ポイント動画生成 1080P · 1秒あたり273,973 ポイント

Wan2.7-T2Vwan2.7-t2v独立モデルAlibaba Cloud · 正式2026-04-07価格の最終確認
確認待ち (UTC+8)

性能59.6費用対効果49.8

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent

動画生成 720P · 1秒あたり164,384 ポイント動画生成 1080P · 1秒あたり273,973 ポイント

qwen-Wan2.7-VideoEditwan2.7-videoedit独立モデルWan · 正式2026-04-07固定単価なし。実際のサービスに応じて課金

性能 · Estimated69.2費用対効果 · Estimated63.4

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-i2v · 78.7Reference: wan2.7-t2v · 59.6Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Grok 4.20 Non-Reasoninggrok-4-20-non-reasoning独立モデルxAI · プレビュー2026-04-06価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated54.7

Shared exact-model performance from grok-4-20-non-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

Grok 4.20 Reasoninggrok-4-20-reasoning独立モデルxAI · プレビュー2026-04-06価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated54.7

Shared exact-model performance from grok-4-20-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

Gemma 4 26B A4B It-100gemma-4-26b-a4b-it-maas-001独立モデルGoogle · プレビュー2026-04-02価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated62.5

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり300,000 ポイントキャッシュヒット使用量 · 100万 Token あたり30,000 ポイント出力使用量 · 100万 Token あたり1,200,000 ポイント

Veo 3.1 Lite Generate 001-100veo-3.1-lite-generate-001独立モデルGoogle · 正式2026-04-02固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

doubao-seed3d-2-0-260328doubao-seed3d-2-0-260328固定スナップショット／版 · 唯一の入口ByteDance · 正式2026-04 (公式情報は月まで)価格の最終確認
確認待ち (UTC+8)

性能82.2費用対効果57.5

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 18%seed3d-public · Official

出力使用量 · 3D · 100万 Token あたり21,917,809 ポイント

Qwen3.6-Plusqwen3.6-plus独立モデルQwen · 正式2026-04-01価格の最終確認
確認待ち (UTC+8)

性能 · Estimated54.5費用対効果 · Estimated57.7

12/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.4 (estimated) · 4/19 observed / reasoning 60.4 (estimated) · 4/13 observed / writing 52.8 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independent arena · Independent livebench · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent

Input 0 – 256,000 Token入力使用量 · 100万 Token あたり547,945 ポイントキャッシュヒット使用量 · 100万 Token あたり109,589 ポイント出力使用量 · 100万 Token あたり3,287,671 ポイント

Input 256,001+ Token入力使用量 · 100万 Token あたり2,191,781 ポイントキャッシュヒット使用量 · 100万 Token あたり438,356 ポイント出力使用量 · 100万 Token あたり13,150,685 ポイント

Wan2.7-Imagewan2.7-image独立モデルAlibaba Cloud · 正式2026-04-01利用可能・生成と編集価格の最終確認
確認待ち (UTC+8)

性能41.7費用対効果46.3

Version comparison review

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%Review: below wan2.6-t2i by 8.3 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independent arena · Independent

出力使用量 · 画像 · 1枚あたり54,795 ポイント

Wan2.7-Image-Prowan2.7-image-pro独立モデルAlibaba Cloud · 正式2026-04-01利用可能・生成と編集価格の最終確認
確認待ち (UTC+8)

性能44.1費用対効果30.9

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent arena · Independent

出力使用量 · 画像 · 1枚あたり136,987 ポイント

qwen-PixVerse-V6-it2vqwen-pixverse-pixverse-v6-it2v独立モデルpixverse · 正式2026-03-29固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-PixVerse-V6-kf2vqwen-pixverse-pixverse-v6-kf2v独立モデルpixverse · 正式2026-03-29固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-PixVerse-V6-t2vqwen-pixverse-pixverse-v6-t2v独立モデルpixverse · 正式2026-03-29固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

GLM-5.1glm-5.1独立モデルZhipu · 正式2026-03-27価格の最終確認
確認待ち (UTC+8)

性能 · Estimated65.1費用対効果 · Estimated61.4

5/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.7 (estimated) · 2/19 observed / reasoning 69.9 (estimated) · 1/13 observed / writing 58.6 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-5.2 · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent livebench · Independent

Input 0 – 31,999 Token入力使用量 · 100万 Token あたり1,643,836 ポイントキャッシュヒット使用量 · 100万 Token あたり356,164 ポイント出力使用量 · 100万 Token あたり6,575,342 ポイント

Input 32,000+ Token入力使用量 · 100万 Token あたり2,191,781 ポイントキャッシュヒット使用量 · 100万 Token あたり547,945 ポイント出力使用量 · 100万 Token あたり7,671,233 ポイント

Lyria 3 Clip Preview-100lyria-3-clip-preview独立モデルGoogle · 正式2026-03-25固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Lyria 3 Pro Preview-100lyria-3-pro-preview独立モデルGoogle · 正式2026-03-25固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-MiniMax/MiniMax-M2.7qwen-minimax-minimax-m2.7独立モデルMiniMax · 正式2026-03-18価格の最終確認
確認待ち (UTC+8)

性能 · Estimated41.0費用対効果 · Estimated36.6

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

入力使用量 · 100万 Token あたり575,342 ポイントキャッシュヒット使用量 · 100万 Token あたり115,068 ポイント出力使用量 · 100万 Token あたり2,301,370 ポイント

GPT-5.4 Minigpt-5.4-mini独立モデルOpenAI · 正式2026-03-17価格の最終確認
確認待ち (UTC+8)

性能 · Estimated47.9費用対効果 · Estimated48.9

12/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 44.3 (estimated) · 4/19 observed / reasoning 53.8 (estimated) · 4/13 observed / writing 45.6 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 7 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independent arena · Independent livebench · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent

入力使用量 · 100万 Token あたり1,500,000 ポイントキャッシュヒット使用量 · 100万 Token あたり150,000 ポイント出力使用量 · 100万 Token あたり9,000,000 ポイント

GPT-5.4 Nanogpt-5.4-nano独立モデルOpenAI · 正式2026-03-17価格の最終確認
確認待ち (UTC+8)

性能 · Estimated48.6費用対効果 · Estimated54.8

11/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 44.5 (estimated) · 3/19 observed / reasoning 57.0 (estimated) · 4/13 observed / writing 44.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-nano-2025-04-14 · 7 benchmarksReference: gpt-5.4 · 2 benchmarksReference: gpt-5.4-high (codex-harness) · 1 benchmarksReference: gpt-5.4-mini · 1 benchmarksarena · Independent livebench · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent

入力使用量 · 100万 Token あたり400,000 ポイントキャッシュヒット使用量 · 100万 Token あたり40,000 ポイント出力使用量 · 100万 Token あたり2,500,000 ポイント

GLM-5-Turboglm-5-turbo独立モデルZhipu · 正式2026-03-14価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated56.0

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

Input 0 – 31,999 Token入力使用量 · 100万 Token あたり1,369,863 ポイントキャッシュヒット使用量 · 100万 Token あたり328,767 ポイント出力使用量 · 100万 Token あたり6,027,397 ポイント

Input 32,000+ Token入力使用量 · 100万 Token あたり1,917,808 ポイントキャッシュヒット使用量 · 100万 Token あたり493,151 ポイント出力使用量 · 100万 Token あたり7,123,288 ポイント

qwen-Tripo-P1.0qwen-tripo-tripo-p1.0独立モデルtripo · 正式2026-03-11固定単価なし。実際のサービスに応じて課金

性能 · Estimated43.2費用対効果 · Estimated45.2

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Tripo-H3.1qwen-tripo-tripo-h3.1独立モデルtripo · 正式2026-03-06固定単価なし。実際のサービスに応じて課金

性能 · Estimated44.9費用対効果 · Estimated46.4

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.4 (estimated) · 0/19 observed / reasoning 54.4 (estimated) · 0/13 observed / writing 42.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-v3.1 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

GPT-5.4gpt-5.4独立モデルOpenAI · 正式2026-03-05価格の最終確認
確認待ち (UTC+8)

性能 · Estimated73.0費用対効果 · Estimated61.5

13/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 58.7 (estimated) · 5/19 observed / reasoning 84.9 (estimated) · 4/13 observed / writing 75.5 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksarena · Independent arena · Independent livebench · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official

入力使用量 · 100万 Token あたり5,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり500,000 ポイント出力使用量 · 100万 Token あたり30,000,000 ポイント

GPT-5.4 Progpt-5.4-pro独立モデルOpenAI · 正式2026-03-05価格の最終確認
確認待ち (UTC+8)

性能 · Estimated58.8費用対効果 · Estimated41.2

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 49.8 (estimated) · 0/19 observed / reasoning 67.8 (estimated) · 0/13 observed / writing 58.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-5.4 · 13 benchmarksReference: gpt-5.4-mini · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: gpt-5.4-nano · 11 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり60,000,000 ポイント出力使用量 · 100万 Token あたり360,000,000 ポイント

Qwen3.5-Omni-Flashqwen3.5-omni-flash独立モデルQwen · 正式2026-03 (公式情報は月まで)固定単価なし。実際のサービスに応じて課金

性能 · Estimated58.2費用対効果 · Estimated55.7

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen3.5-Omni-Flash-Realtimeqwen3.5-omni-flash-realtime独立モデルQwen · 正式2026-03 (公式情報は月まで)固定単価なし。実際のサービスに応じて課金

性能 · Estimated52.6費用対効果 · Estimated51.8

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen3.5-Omni-Plusqwen3.5-omni-plus独立モデルQwen · 正式2026-03 (公式情報は月まで)固定単価なし。実際のサービスに応じて課金

性能 · Estimated54.5費用対効果 · Estimated53.1

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.4 (estimated) · 0/19 observed / reasoning 60.4 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: qwen3.6-plus · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen3.5-Omni-Plus-Realtimeqwen3.5-omni-plus-realtime独立モデルQwen · 正式2026-03 (公式情報は月まで)固定単価なし。実際のサービスに応じて課金

性能 · Estimated52.6費用対効果 · Estimated51.8

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-pixverse/pixverse-motioncontrolqwen-pixverse-pixverse-motioncontrol独立モデルpixverse · 正式2026-02-28固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

GPT-5.3 Codexgpt-5.3-codex独立モデルOpenAI · 正式2026-02-24価格の最終確認
確認待ち (UTC+8)

性能 · Estimated58.5費用対効果 · Estimated52.1

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.4 (estimated) · 0/19 observed / reasoning 63.1 (estimated) · 0/13 observed / writing 56.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-5.4 · 9 benchmarksReference: gpt-5.2 · 8 benchmarksReference: gpt-5.2-codex · 8 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReview: below gpt-5.2-codex by 3.5 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり3,500,000 ポイントキャッシュヒット使用量 · 100万 Token あたり350,000 ポイント出力使用量 · 100万 Token あたり28,000,000 ポイント

qwen-MiniMax-M2.5qwen-minimax-m2.5独立モデルMiniMax · 正式2026-02-24価格の最終確認
確認待ち (UTC+8)

性能 · Estimated34.9費用対効果 · Estimated44.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

GPT Audio 1.5gpt-audio-1.5独立モデルOpenAI · 正式2026-02-23全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated52.6費用対効果 · Estimated41.6

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9openai-realtime-public · Official

入力使用量 · 100万 Token あたり5,000,000 ポイント出力使用量 · 100万 Token あたり20,000,000 ポイント入力使用量 · 音声 · 100万 Token あたり64,000,000 ポイント出力使用量 · 音声 · 100万 Token あたり128,000,000 ポイント

GPT Realtime 1.5gpt-realtime-1.5独立モデルOpenAI · 正式2026-02-23全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated45.3費用対効果 · Estimated31.7

Estimate basis

入力使用量 · 100万 Token あたり8,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり800,000 ポイント出力使用量 · 100万 Token あたり32,000,000 ポイント入力使用量 · 画像 · 100万 Token あたり10,000,000 ポイントキャッシュヒット使用量 · 画像 · 100万 Token あたり1,000,000 ポイント入力使用量 · 音声 · 100万 Token あたり64,000,000 ポイントキャッシュヒット使用量 · 音声 · 100万 Token あたり800,000 ポイント出力使用量 · 音声 · 100万 Token あたり128,000,000 ポイント

Qwen3.5-122B-A10Bqwen3.5-122b-a10b独立モデルQwen · 正式2026-02-23価格の最終確認
確認待ち (UTC+8)

性能 · Estimated46.4費用対効果 · Estimated55.2

5/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.9 (estimated) · 2/19 observed / reasoning 56.8 (estimated) · 1/13 observed / writing 42.4 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent livebench · Independent

Input 0 – 128,000 Token入力使用量 · 100万 Token あたり219,178 ポイントキャッシュヒット使用量 · 100万 Token あたり0 ポイント出力使用量 · 100万 Token あたり1,753,425 ポイント

Input 128,001+ Token入力使用量 · 100万 Token あたり547,945 ポイントキャッシュヒット使用量 · 100万 Token あたり0 ポイント出力使用量 · 100万 Token あたり4,383,562 ポイント

Qwen3.5-27Bqwen3.5-27b独立モデルQwen · 正式2026-02-23価格の最終確認
確認待ち (UTC+8)

性能 · Estimated45.7費用対効果 · Estimated55.9

5/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.4 (estimated) · 2/19 observed / reasoning 56.1 (estimated) · 1/13 observed / writing 41.7 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent livebench · Independent

Input 0 – 128,000 Token入力使用量 · 100万 Token あたり164,384 ポイントキャッシュヒット使用量 · 100万 Token あたり0 ポイント出力使用量 · 100万 Token あたり1,315,068 ポイント

Input 128,001+ Token入力使用量 · 100万 Token あたり493,151 ポイントキャッシュヒット使用量 · 100万 Token あたり0 ポイント出力使用量 · 100万 Token あたり3,945,205 ポイント

Qwen3.5-35B-A3Bqwen3.5-35b-a3b独立モデルQwen · 正式2026-02-23価格の最終確認
確認待ち (UTC+8)

性能 · Estimated42.9費用対効果 · Estimated55.6

5/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 36.8 (estimated) · 2/19 observed / reasoning 51.7 (estimated) · 1/13 observed / writing 40.2 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent livebench · Independent

Input 0 – 128,000 Token入力使用量 · 100万 Token あたり109,589 ポイントキャッシュヒット使用量 · 100万 Token あたり0 ポイント出力使用量 · 100万 Token あたり876,712 ポイント

Input 128,001+ Token入力使用量 · 100万 Token あたり438,356 ポイントキャッシュヒット使用量 · 100万 Token あたり0 ポイント出力使用量 · 100万 Token あたり3,506,849 ポイント

Qwen3.5-Flashqwen3.5-flash独立モデルQwen · 正式2026-02-23価格の最終確認
確認待ち (UTC+8)

性能 · Estimated58.2費用対効果 · Estimated68.6

5/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 2/19 observed / reasoning 62.8 (estimated) · 1/13 observed / writing 59.9 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent livebench · Independent

Input 0 – 128,000 Token入力使用量 · 100万 Token あたり54,795 ポイントキャッシュヒット使用量 · 100万 Token あたり10,959 ポイント出力使用量 · 100万 Token あたり547,945 ポイント

Input 128,001 – 256,000 Token入力使用量 · 100万 Token あたり219,178 ポイントキャッシュヒット使用量 · 100万 Token あたり43,836 ポイント出力使用量 · 100万 Token あたり2,191,781 ポイント

Input 256,001+ Token入力使用量 · 100万 Token あたり328,767 ポイントキャッシュヒット使用量 · 100万 Token あたり65,753 ポイント出力使用量 · 100万 Token あたり3,287,671 ポイント

qwen-GLM-5qwen-glm-5独立モデルZhipu · 正式2026-02-18価格の最終確認
確認待ち (UTC+8)

性能 · Estimated61.1費用対効果 · Estimated60.1

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

Input 0 – 32,000 Token入力使用量 · 100万 Token あたり1,095,890 ポイントキャッシュヒット使用量 · 100万 Token あたり219,178 ポイント出力使用量 · 100万 Token あたり4,931,507 ポイント

Input 32,001+ Token入力使用量 · 100万 Token あたり1,643,836 ポイントキャッシュヒット使用量 · 100万 Token あたり328,767 ポイント出力使用量 · 100万 Token あたり6,027,397 ポイント

claude-sonnet-4-6claude-sonnet-4-6独立モデルAnthropic · 正式2026-02-17固定単価なし。実際のサービスに応じて課金

性能 · Estimated65.2費用対効果 · Estimated60.6

12/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.0 (estimated) · 4/19 observed / reasoning 71.9 (estimated) · 4/13 observed / writing 59.7 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent livebench · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

claude-sonnet-4-6-100claude-sonnet-4-6-100独立モデルAnthropic · 正式2026-02-17固定単価なし。実際のサービスに応じて課金

性能 · Estimated65.2費用対効果 · Estimated60.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.0 (estimated) · 0/19 observed / reasoning 71.9 (estimated) · 0/13 observed / writing 59.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-sonnet-4-6 · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen3.5-397B-A17Bqwen3.5-397b-a17b独立モデルQwen · 正式2026-02-15価格の最終確認
確認待ち (UTC+8)

性能 · Estimated49.6費用対効果 · Estimated56.4

5/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 42.6 (estimated) · 2/19 observed / reasoning 59.5 (estimated) · 1/13 observed / writing 46.6 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent livebench · Independent

Input 0 – 128,000 Token入力使用量 · 100万 Token あたり328,767 ポイントキャッシュヒット使用量 · 100万 Token あたり0 ポイント出力使用量 · 100万 Token あたり1,972,603 ポイント

Input 128,001+ Token入力使用量 · 100万 Token あたり821,918 ポイントキャッシュヒット使用量 · 100万 Token あたり0 ポイント出力使用量 · 100万 Token あたり4,931,507 ポイント

Qwen3.5-Plusqwen3.5-plus独立モデルQwen · 正式2026-02-15価格の最終確認
確認待ち (UTC+8)

性能 · Estimated54.5費用対効果 · Estimated61.5

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.4 (estimated) · 0/19 observed / reasoning 60.4 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: qwen3.6-plus · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

Input 0 – 128,000 Token入力使用量 · 100万 Token あたり219,178 ポイントキャッシュヒット使用量 · 100万 Token あたり43,836 ポイント出力使用量 · 100万 Token あたり1,315,068 ポイント

Input 128,001 – 256,000 Token入力使用量 · 100万 Token あたり547,945 ポイントキャッシュヒット使用量 · 100万 Token あたり109,589 ポイント出力使用量 · 100万 Token あたり3,287,671 ポイント

Input 256,001+ Token入力使用量 · 100万 Token あたり1,095,890 ポイントキャッシュヒット使用量 · 100万 Token あたり219,178 ポイント出力使用量 · 100万 Token あたり6,575,342 ポイント

qwen-MiniMax/MiniMax-M2.5qwen-minimax-minimax-m2.5独立モデルMiniMax · 正式2026-02-12価格の最終確認
確認待ち (UTC+8)

性能 · Estimated41.0費用対効果 · Estimated36.6

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

入力使用量 · 100万 Token あたり575,342 ポイントキャッシュヒット使用量 · 100万 Token あたり57,534 ポイント出力使用量 · 100万 Token あたり2,301,370 ポイント

qwen-PixVerse-V5.6-r2vqwen-pixverse-pixverse-v5.6-r2v独立モデルpixverse · 正式2026-02-12固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ZHIPU/GLM-5qwen-zhipu-glm-5独立モデルZhipu AI · 正式2026-02-12価格の最終確認
確認待ち (UTC+8)

性能 · Estimated41.0費用対効果 · Estimated31.2

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

入力使用量 · 100万 Token あたり1,643,836 ポイントキャッシュヒット使用量 · 100万 Token あたり410,959 ポイント出力使用量 · 100万 Token あたり6,027,397 ポイント

qwen-ViduQ3-Pro_start-end2videoqwen-vidu-viduq3-pro_start-end2video独立モデルvidu · 正式2026-02-11固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ3-Turbo_img2videoqwen-vidu-viduq3-turbo_img2video独立モデルvidu · 正式2026-02-11固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ3-Turbo_start-end2videoqwen-vidu-viduq3-turbo_start-end2video独立モデルvidu · 正式2026-02-11固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ3-Turbo_text2videoqwen-vidu-viduq3-turbo_text2video独立モデルvidu · 正式2026-02-11固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

GLM-5glm-5独立モデルZhipu · 正式2026-02-10価格の最終確認
確認待ち (UTC+8)

性能 · Estimated62.3費用対効果 · Estimated60.9

5/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.4 (estimated) · 2/19 observed / reasoning 66.5 (estimated) · 1/13 observed / writing 56.9 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-5.2 · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent livebench · Independent

Input 0 – 31,999 Token入力使用量 · 100万 Token あたり1,095,890 ポイントキャッシュヒット使用量 · 100万 Token あたり273,973 ポイント出力使用量 · 100万 Token あたり4,931,507 ポイント

Input 32,000+ Token入力使用量 · 100万 Token あたり1,643,836 ポイントキャッシュヒット使用量 · 100万 Token あたり410,959 ポイント出力使用量 · 100万 Token あたり6,027,397 ポイント

Qwen-Image-2.0qwen-image-2.0独立モデルAlibaba Cloud · 正式2026-02-10利用可能・生成と編集価格の最終確認
確認待ち (UTC+8)

性能 · Estimated73.8費用対効果 · Estimated68.7

Estimate basis

出力使用量 · 画像 · 1枚あたり54,795 ポイント

claude-opus-4-6claude-opus-4-6独立モデルAnthropic · 正式2026-02-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated70.8費用対効果 · Estimated64.6

12/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.4 (estimated) · 4/19 observed / reasoning 75.9 (estimated) · 4/13 observed / writing 70.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent livebench · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

claude-opus-4-6-100claude-opus-4-6-100独立モデルAnthropic · 正式2026-02-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated70.8費用対効果 · Estimated64.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.4 (estimated) · 0/19 observed / reasoning 75.9 (estimated) · 0/13 observed / writing 70.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-opus-4-6 · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Kling Image 3.0qwen-kling-kling-v3-image-generation独立モデルkling · 正式2026-02-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated73.8費用対効果 · Estimated66.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Kling Image 3.0 Omniqwen-kling-kling-v3-omni-image-generation独立モデルkling · 正式2026-02-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Kling Video 3.0 Omniqwen-kling-kling-v3-omni-video-generation独立モデルkling · 正式2026-02-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated41.7費用対効果 · Estimated44.2

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 36.7 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 37.6 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b · 4 benchmarksReference: qwen3-30b-a3b · 4 benchmarksReference: qwen3-vl-235b-a22b-instruct · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Kling Video 3.0qwen-kling-kling-v3-video-generation独立モデルkling · 正式2026-02-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Kimi-K2.5qwen-kimi-k2.5独立モデルMoonshot · 正式2026-01-30価格の最終確認
確認待ち (UTC+8)

性能 · Estimated34.9費用対効果 · Estimated41.4

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

入力使用量 · 100万 Token あたり1,095,890 ポイントキャッシュヒット使用量 · 100万 Token あたり219,178 ポイント出力使用量 · 100万 Token あたり5,753,425 ポイント

Fun-ASR-Flash-8k实时语音识别fun-asr-flash-8k-realtime独立モデルQwen · 正式2026-01-28固定単価なし。実際のサービスに応じて課金

性能 · Estimated52.6費用対効果 · Estimated51.8

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ2-Pro_reference2videoqwen-vidu-viduq2-pro_reference2video独立モデルvidu · 正式2026-01-27固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ3-Pro_img2videoqwen-vidu-viduq3-pro_img2video独立モデルvidu · 正式2026-01-27固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ3-Pro_text2videoqwen-vidu-viduq3-pro_text2video独立モデルvidu · 正式2026-01-27固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen3-VL-Plusqwen3-vl-plus独立モデルQwen · 正式2026-01-26価格の最終確認
確認待ち (UTC+8)

性能 · Estimated42.7費用対効果 · Estimated51.1

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 45.3 (estimated) · 0/19 observed / reasoning 44.7 (estimated) · 0/13 observed / writing 38.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-plus · 8 benchmarksReference: qwen2.5-plus-1127 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

Input 0 – 32,000 Token入力使用量 · 100万 Token あたり273,973 ポイントキャッシュヒット使用量 · 100万 Token あたり54,795 ポイント出力使用量 · 100万 Token あたり2,739,726 ポイント

Input 32,001 – 128,000 Token入力使用量 · 100万 Token あたり410,959 ポイントキャッシュヒット使用量 · 100万 Token あたり82,192 ポイント出力使用量 · 100万 Token あたり4,109,589 ポイント

Input 128,001+ Token入力使用量 · 100万 Token あたり821,918 ポイントキャッシュヒット使用量 · 100万 Token あたり164,384 ポイント出力使用量 · 100万 Token あたり8,219,178 ポイント

qwen-PixVerse-V5.6-it2vqwen-pixverse-pixverse-v5.6-it2v独立モデルpixverse · 正式2026-01-26固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-PixVerse-V5.6-kf2vqwen-pixverse-pixverse-v5.6-kf2v独立モデルpixverse · 正式2026-01-26固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-PixVerse-V5.6-t2vqwen-pixverse-pixverse-v5.6-t2v独立モデルpixverse · 正式2026-01-26固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Virtual Try On 001-100virtual-try-on-001独立モデルGoogle · 正式2026-01-23固定単価なし。実際のサービスに応じて課金

性能 · Estimated44.5費用対効果 · Estimated46.1

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

GPT-5.2 Codexgpt-5.2-codex独立モデルOpenAI · 正式2026-01-14価格の最終確認
確認待ち (UTC+8)

性能 · Estimated62.0費用対効果 · Estimated54.5

Version comparison review8/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 59.8 (estimated) · 3/19 observed / reasoning 68.2 (estimated) · 3/13 observed / writing 58.0 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 4 benchmarksReference: gpt-5.2-chat-latest-20260210 · 4 benchmarksReference: gpt-5.4 · 1 benchmarksReview: below gpt-5.1-codex by 1.6 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independent livebench · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent

qwen-MiniMax/MiniMax-M2.1qwen-minimax-minimax-m2.1独立モデルMiniMax · 正式2025-12-23価格の最終確認
確認待ち (UTC+8)

性能 · Estimated41.0費用対効果 · Estimated36.6

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

GLM-4.7glm-4.7独立モデルZhipu · 正式2025-12-22価格の最終確認
確認待ち (UTC+8)

性能 · Estimated60.2費用対効果 · Estimated60.6

5/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.3 (estimated) · 2/19 observed / reasoning 63.5 (estimated) · 1/13 observed / writing 53.7 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-5.2 · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent livebench · Independent

Input 0 – 31,999 Token · Output 0 – 199 Token入力使用量 · 100万 Token あたり547,945 ポイントキャッシュヒット使用量 · 100万 Token あたり109,589 ポイント出力使用量 · 100万 Token あたり2,191,781 ポイント

Input 0 – 31,999 Token · Output 200+ Token入力使用量 · 100万 Token あたり821,918 ポイントキャッシュヒット使用量 · 100万 Token あたり164,384 ポイント出力使用量 · 100万 Token あたり3,835,616 ポイント

Input 32,000+ Token入力使用量 · 100万 Token あたり1,095,890 ポイントキャッシュヒット使用量 · 100万 Token あたり219,178 ポイント出力使用量 · 100万 Token あたり4,383,562 ポイント

GPT Image 1.5gpt-image-1.5独立モデルOpenAI · 正式2025-12-16利用可能・生成と編集価格の最終確認
確認待ち (UTC+8)

性能76.0費用対効果53.2

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent arena · Independent

入力使用量 · 100万 Token あたり10,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり2,500,000 ポイント入力使用量 · 画像 · 100万 Token あたり16,000,000 ポイントキャッシュヒット使用量 · 画像 · 100万 Token あたり4,000,000 ポイント出力使用量 · 100万 Token あたり20,000,000 ポイント出力使用量 · 画像 · 100万 Token あたり64,000,000 ポイント

Wan2.6-I2Vwan2.6-i2v独立モデルAlibaba Cloud · 正式2025-12-16価格の最終確認
確認待ち (UTC+8)

性能53.2費用対効果45.3

Version comparison review

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%Review: below wan2.5-i2v-preview by 2.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independent

動画生成 720P · 1秒あたり164,384 ポイント動画生成 1080P · 1秒あたり273,973 ポイント

Wan2.6-Imagewan2.6-image独立モデルAlibaba Cloud · 正式2025-12-16利用可能・生成と編集価格の最終確認
確認待ち (UTC+8)

性能31.6費用対効果39.2

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent

出力使用量 · 画像 · 1枚あたり54,795 ポイント

qwen-Wan2.6-R2Vwan2.6-r2v独立モデルWan · 正式2025-12-16固定単価なし。実際のサービスに応じて課金

性能 · Estimated55.3費用対効果 · Estimated53.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.6-i2v · 53.2Reference: wan2.6-t2v · 57.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Wan2.6-T2Iwan2.6-t2i独立モデルAlibaba Cloud · 正式2025-12-16利用可能・生成と編集価格の最終確認
確認待ち (UTC+8)

性能50.0費用対効果52.1

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent

出力使用量 · 画像 · 1枚あたり54,795 ポイント

Wan2.6-T2Vwan2.6-t2v独立モデルAlibaba Cloud · 正式2025-12-16価格の最終確認
確認待ち (UTC+8)

性能57.4費用対効果48.3

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent

動画生成 720P · 1秒あたり164,384 ポイント動画生成 1080P · 1秒あたり273,973 ポイント

Cohere Rerank v4.0 Procohere-rerank-v4.0-pro独立モデルCohere · 正式2025-12-11全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated65.8費用対効果 · Estimated61.1

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3-Reranker-0.6B · 68.8Reference: gte-multilingual-reranker-base · 62.7Reference: BGE-reranker-v2-m3 · 57.7qwen-rerank-public · Official

再ランキング · 1,000検索ユニットあたり5,000,000 ポイント

GPT-5.2gpt-5.2独立モデルOpenAI · 正式2025-12-11価格の最終確認
確認待ち (UTC+8)

性能 · Estimated61.7費用対効果 · Estimated54.3

Version comparison review12/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 52.5 (estimated) · 4/19 observed / reasoning 73.8 (estimated) · 4/13 observed / writing 58.7 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.4 · 1 benchmarksReview: below gpt-5.1 by 2.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independent arena · Independent livebench · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent

GPT-5.1 Codex Maxgpt-5.1-codex-max独立モデルOpenAI · 正式2025-12-04価格の最終確認
確認待ち (UTC+8)

性能 · Estimated72.5費用対効果 · Estimated63.3

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 69.3 (estimated) · 0/19 observed / reasoning 78.4 (estimated) · 0/13 observed / writing 69.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-6-sol-max · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.4 · 1 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり2,500,000 ポイントキャッシュヒット使用量 · 100万 Token あたり250,000 ポイント出力使用量 · 100万 Token あたり20,000,000 ポイント

Mistral Large 3mistral-large-3独立モデルMistral AI · 正式2025-12-02価格の最終確認
確認待ち (UTC+8)

性能 · Estimated60.6費用対効果 · Estimated60.8

5/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 54.7 (estimated) · 2/19 observed / reasoning 66.7 (estimated) · 1/13 observed / writing 60.5 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksarena · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり1,000,000 ポイント出力使用量 · 100万 Token あたり3,000,000 ポイント

qwen-ViduQ2-Pro-fast_img2videoqwen-vidu-viduq2-pro-fast_img2video独立モデルvidu · 正式2025-12-02固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen3-LiveTranslate-Flashqwen3-livetranslate-flash独立モデルQwen · 正式2025-12-01固定単価なし。実際のサービスに応じて課金

性能 · Estimated58.2費用対効果 · Estimated55.7

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen3-Omni-Flashqwen3-omni-flash独立モデルQwen · 正式2025-12-01固定単価なし。実際のサービスに応じて課金

性能 · Estimated58.2費用対効果 · Estimated55.7

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-SiliconFlow DeepSeek-V3.2qwen-siliconflow-deepseek-v3.2独立モデルDeepSeek · 正式2025-12-01固定単価なし。実際のサービスに応じて課金

性能 · Estimated45.8費用対効果 · Estimated47.1

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.1 (estimated) · 0/19 observed / reasoning 54.2 (estimated) · 0/13 observed / writing 45.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-v3.2-exp · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Vanchin/DeepSeek-V3.2-thinkqwen-vanchin-deepseek-v3.2-think独立モデルDeepSeek · 正式2025-12-01固定単価なし。実際のサービスに応じて課金

性能 · Estimated45.8費用対効果 · Estimated47.1

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen3-TTS-Flash-Realtimeqwen3-tts-flash-realtime独立モデルQwen · 正式2025-11-27固定単価なし。実際のサービスに応じて課金

性能 · Estimated52.6費用対効果 · Estimated51.8

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Z-Image-Turboz-image-turbo独立モデルAlibaba Cloud · 正式2025-11-26利用可能・生成と編集価格の最終確認
確認待ち (UTC+8)

性能28.8費用対効果50.2

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent

出力使用量 · 画像 · 1枚あたり27,398 ポイント

FLUX.2 [flex]flux.2-flex独立モデルBlack Forest Labs · 正式2025-11-25利用可能・生成と編集価格の最終確認
確認待ち (UTC+8)

性能46.8費用対効果32.8

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent arena · Independent

入力使用量 · 画像 · 1メガピクセルあたり100,000 ポイント出力使用量 · 画像 · 1メガピクセルあたり100,000 ポイント

FLUX.2 Proflux.2-pro独立モデルBlack Forest Labs · 正式2025-11-25全機能価格の最終確認
確認待ち (UTC+8)

性能49.9費用対効果64.9

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent arena · Independent

最初のメガピクセル · 1メガピクセルあたり60,000 ポイント追加メガピクセル · 1メガピクセルあたり30,000 ポイント

claude-opus-4-5claude-opus-4-5独立モデルAnthropic · 正式2025-11-24固定単価なし。実際のサービスに応じて課金

性能 · Estimated67.9費用対効果—

Shared exact-model performance from claude-opus-4-5; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.9 (estimated) · 0/19 observed / reasoning 71.8 (estimated) · 0/13 observed / writing 67.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-opus-4-6 · 7 benchmarksReference: claude-opus-4-5-20251101 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

claude-opus-4-5-100claude-opus-4-5-100独立モデルAnthropic · 正式2025-11-24固定単価なし。実際のサービスに応じて課金

性能 · Estimated67.9費用対効果—

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Grok 4.1 Fast Non-Reasoninggrok-4-1-fast-non-reasoning独立モデルxAI · 正式2025-11-19価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated62.1

Shared exact-model performance from grok-4-1-fast-non-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり400,000 ポイントキャッシュヒット使用量 · 100万 Token あたり100,000 ポイント出力使用量 · 100万 Token あたり1,000,000 ポイント

Grok 4.1 Fast Reasoninggrok-4-1-fast-reasoning独立モデルxAI · 正式2025-11-19価格の最終確認
確認待ち (UTC+8)

性能 · Estimated59.5費用対効果 · Estimated64.1

Shared exact-model performance from grok-4-1-fast-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.5/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 53.3 (estimated) · 2/19 observed / reasoning 65.8 (estimated) · 1/13 observed / writing 59.5 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksarena · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent livebench · Independent

Gemini 3 Pro Preview-100gemini-3-pro-preview独立モデルGoogle · 正式2025-11-18固定単価なし。実際のサービスに応じて課金

性能 · Estimated69.4費用対効果 · Estimated63.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 48.1 (estimated) · 0/19 observed / reasoning 77.5 (estimated) · 0/13 observed / writing 82.6 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gemini-3.1-pro-preview-high · 7 benchmarksReference: gemini-3-pro · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Veo 3.1 Fast Generate 001-100veo-3.1-fast-generate-001独立モデルGoogle · 正式2025-11-17固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Veo 3.1 Generate 001-100veo-3.1-generate-001独立モデルGoogle · 正式2025-11-17固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

GPT-5.1gpt-5.1独立モデルOpenAI · 正式2025-11-13価格の最終確認
確認待ち (UTC+8)

性能 · Estimated63.8費用対効果 · Estimated57.2

5/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 54.9 (estimated) · 2/19 observed / reasoning 73.2 (estimated) · 1/13 observed / writing 63.4 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent livebench · Independent

GPT-5.1 Codexgpt-5.1-codex独立モデルOpenAI · 正式2025-11-13価格の最終確認
確認待ち (UTC+8)

性能 · Estimated63.6費用対効果 · Estimated57.1

1/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 58.2 (estimated) · 1/19 observed / reasoning 70.3 (estimated) · 0/13 observed / writing 62.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5.1 · 4 benchmarksarena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent livebench · Independent

GPT-5.1 Codex Minigpt-5.1-codex-mini独立モデルOpenAI · 正式2025-11-13価格の最終確認
確認待ち (UTC+8)

性能 · Estimated43.1費用対効果 · Estimated49.4

1/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.6 (estimated) · 1/19 observed / reasoning 48.9 (estimated) · 0/13 observed / writing 40.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 7 benchmarksReference: gpt-5.4-mini · 7 benchmarksReference: gpt-5-mini · 4 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり500,000 ポイントキャッシュヒット使用量 · 100万 Token あたり50,000 ポイント出力使用量 · 100万 Token あたり4,000,000 ポイント

Lyria 002-100lyria-002独立モデルGoogle · 正式2025-10-27固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ2_reference2videoqwen-vidu-viduq2_reference2video独立モデルvidu · 正式2025-10-21固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ2_text2videoqwen-vidu-viduq2_text2video独立モデルvidu · 正式2025-10-21固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Vanchin/DeepSeek-OCRqwen-vanchin-deepseek-ocr独立モデルDeepSeek · 正式2025-10-20固定単価なし。実際のサービスに応じて課金

性能 · Estimated81.8費用対効果 · Estimated72.3

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mistral-ocr-4-0 · 81.8Reference: cohere-parse-v5 · 79.2Reference: mistral-document-ai-2512 · 96.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.mistral-ocr · Official cohere-parsebench · Official mistral-ocr · Official

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

claude-haiku-4-5claude-haiku-4-5独立モデルAnthropic · 正式2025-10-15固定単価なし。実際のサービスに応じて課金

性能 · Estimated60.4費用対効果 · Estimated57.3

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.5 (estimated) · 0/19 observed / reasoning 63.8 (estimated) · 0/13 observed / writing 60.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-haiku-4-5-20251001 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

claude-haiku-4-5-100claude-haiku-4-5-100独立モデルAnthropic · 正式2025-10-15固定単価なし。実際のサービスに応じて課金

性能 · Estimated60.4費用対効果 · Estimated57.3

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

GPT-5 Progpt-5-pro独立モデルOpenAI · 正式2025-10-06価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.5費用対効果 · Estimated41.7

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.9 (estimated) · 0/19 observed / reasoning 61.9 (estimated) · 0/13 observed / writing 51.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5 · 5 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり20,000,000 ポイント出力使用量 · 100万 Token あたり240,000,000 ポイント

GPT Audio Minigpt-audio-mini独立モデルOpenAI · 正式2025-10-06全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated52.6費用対効果 · Estimated66.8

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9openai-realtime-public · Official

入力使用量 · 100万 Token あたり1,200,000 ポイント出力使用量 · 100万 Token あたり4,800,000 ポイント入力使用量 · 音声 · 100万 Token あたり20,000,000 ポイント出力使用量 · 音声 · 100万 Token あたり40,000,000 ポイント

GPT Image 1 Minigpt-image-1-mini独立モデルOpenAI · 正式2025-10-06利用可能・生成と編集価格の最終確認
確認待ち (UTC+8)

性能20.1費用対効果44.1

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent arena · Independent

入力使用量 · 100万 Token あたり4,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり400,000 ポイント入力使用量 · 画像 · 100万 Token あたり5,000,000 ポイントキャッシュヒット使用量 · 画像 · 100万 Token あたり500,000 ポイント出力使用量 · 画像 · 100万 Token あたり16,000,000 ポイント

GPT Realtime Minigpt-realtime-mini独立モデルOpenAI · 正式2025-10-06全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated54.0費用対効果 · Estimated67.8

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-realtime-2025-08-28 · 59.9Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3openai-realtime-public · Official

Gemini 2.5 Flash TTS-100gemini-2.5-flash-tts独立モデルGoogle · 正式2025-09-30固定単価なし。実際のサービスに応じて課金

性能 · Estimated87.1費用対効果 · Estimated76.0

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Gemini-flash · 87.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · Official

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Gemini 2.5 Pro TTS-100gemini-2.5-pro-tts独立モデルGoogle · 正式2025-09-30固定単価なし。実際のサービスに応じて課金

性能 · Estimated82.6費用対効果 · Estimated72.8

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Gemini-pro · 82.6Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · Official

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sora 2sora-2独立モデルOpenAI · プレビュー2025-09-30価格の最終確認
確認待ち (UTC+8)

性能66.0費用対効果50.4

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent

動画生成 · 1秒あたり200,000 ポイント

claude-sonnet-4-5claude-sonnet-4-5独立モデルAnthropic · 正式2025-09-29固定単価なし。実際のサービスに応じて課金

性能 · Estimated61.6費用対効果 · Estimated58.1

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 58.8 (estimated) · 0/19 observed / reasoning 66.2 (estimated) · 0/13 observed / writing 59.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-sonnet-4-6 · 7 benchmarksReference: claude-sonnet-4-5-20250929 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ2-Pro_img2videoqwen-vidu-viduq2-pro_img2video独立モデルvidu · 正式2025-09-24固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ2-Pro_start-end2videoqwen-vidu-viduq2-pro_start-end2video独立モデルvidu · 正式2025-09-24固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ2-Turbo_img2videoqwen-vidu-viduq2-turbo_img2video独立モデルvidu · 正式2025-09-24固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ2-Turbo_start-end2videoqwen-vidu-viduq2-turbo_start-end2video独立モデルvidu · 正式2025-09-24固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

GPT-5 Codexgpt-5-codex独立モデルOpenAI · 正式2025-09-23価格の最終確認
確認待ち (UTC+8)

性能 · Estimated59.1費用対効果 · Estimated53.9

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 59.5 (estimated) · 0/19 observed / reasoning 63.0 (estimated) · 0/13 observed / writing 54.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5 · 5 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

qwen-SiliconFlow DeepSeek-V3.1-Terminusqwen-siliconflow-deepseek-v3.1-terminus独立モデルDeepSeek · 正式2025-09-22固定単価なし。実際のサービスに応じて課金

性能 · Estimated44.9費用対効果 · Estimated46.4

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Vanchin/DeepSeek-V3.1-Terminusqwen-vanchin-deepseek-v3.1-terminus独立モデルDeepSeek · 正式2025-09-22固定単価なし。実際のサービスに応じて課金

性能 · Estimated44.9費用対効果 · Estimated46.4

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen3-TTS-Flashqwen3-tts-flash独立モデルAlibaba Cloud · 正式2025-09 (公式情報は月まで)利用可能・音声ツール価格の最終確認
確認待ち (UTC+8)

性能 · Estimated74.4費用対効果 · Estimated82.1

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4qwen-tts-public · Official

音声 · 10,000文字あたり219,179 ポイント

Chirp 3-100chirp-3独立モデルGoogle · 正式2025-08-29固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

GPT Realtimegpt-realtime独立モデルOpenAI · 正式2025-08-28全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated59.9費用対効果 · Estimated41.9

Estimate basis

GPT-5gpt-5独立モデルOpenAI · 正式2025-08-07価格の最終確認
確認待ち (UTC+8)

性能 · Estimated58.7費用対効果 · Estimated53.6

5/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 54.6 (estimated) · 2/19 observed / reasoning 65.6 (estimated) · 1/13 observed / writing 56.0 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independent arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent livebench · Independent

GPT-5 Minigpt-5-mini独立モデルOpenAI · 正式2025-08-07価格の最終確認
確認待ち (UTC+8)

性能 · Estimated43.1費用対効果 · Estimated49.4

4/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.6 (estimated) · 1/19 observed / reasoning 48.9 (estimated) · 1/13 observed / writing 40.7 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 7 benchmarksReference: gpt-5.4-mini · 7 benchmarksReference: gpt-5.1-codex-mini · 1 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent livebench · Independent

GPT-5 Nanogpt-5-nano独立モデルOpenAI · 正式2025-08-07価格の最終確認
確認待ち (UTC+8)

性能 · Estimated44.4費用対効果 · Estimated57.0

4/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 43.4 (estimated) · 1/19 observed / reasoning 50.3 (estimated) · 1/13 observed / writing 39.5 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-nano-2025-04-14 · 7 benchmarksReference: gpt-5.4-nano · 7 benchmarksReference: gpt-5 · 1 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり100,000 ポイントキャッシュヒット使用量 · 100万 Token あたり10,000 ポイント出力使用量 · 100万 Token あたり800,000 ポイント

GPT-OSS 120B-100openai-gpt-oss-120b-maas-001独立モデルOpenAI · 正式2025-08-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated57.3費用対効果 · Estimated55.1

4/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 57.4 (estimated) · 1/19 observed / reasoning 63.0 (estimated) · 1/13 observed / writing 51.5 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen3-Coder-Flashqwen3-coder-flash独立モデルQwen · 正式2025-08-05価格の最終確認
確認待ち (UTC+8)

性能 · Estimated58.2費用対効果 · Estimated64.0

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

Input 0 – 32,000 Token入力使用量 · 100万 Token あたり273,973 ポイントキャッシュヒット使用量 · 100万 Token あたり54,795 ポイント出力使用量 · 100万 Token あたり1,095,890 ポイント

Input 32,001 – 128,000 Token入力使用量 · 100万 Token あたり410,959 ポイントキャッシュヒット使用量 · 100万 Token あたり82,192 ポイント出力使用量 · 100万 Token あたり1,643,836 ポイント

Input 128,001 – 256,000 Token入力使用量 · 100万 Token あたり684,932 ポイントキャッシュヒット使用量 · 100万 Token あたり136,986 ポイント出力使用量 · 100万 Token あたり2,739,726 ポイント

Input 256,001+ Token入力使用量 · 100万 Token あたり1,369,863 ポイントキャッシュヒット使用量 · 100万 Token あたり273,973 ポイント出力使用量 · 100万 Token あたり6,849,315 ポイント

Qwen-Flashqwen-flash独立モデルQwen · 正式2025-08-05価格の最終確認
確認待ち (UTC+8)

性能 · Estimated59.4費用対効果 · Estimated70.7

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.4 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

Input 0 – 128,000 Token入力使用量 · 100万 Token あたり41,096 ポイントキャッシュヒット使用量 · 100万 Token あたり8,219 ポイント出力使用量 · 100万 Token あたり410,959 ポイント

Input 128,001 – 256,000 Token入力使用量 · 100万 Token あたり164,384 ポイントキャッシュヒット使用量 · 100万 Token あたり32,877 ポイント出力使用量 · 100万 Token あたり1,643,836 ポイント

doubao-glm-4-5-airdoubao-glm-4-5-air-20250728固定スナップショット／版 · 唯一の入口Zhipu AI · 正式2025-07-28固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

GLM-4.5-Airglm-4.5-air独立モデルZhipu · 正式2025-07-27価格の最終確認
確認待ち (UTC+8)

性能 · Estimated59.3費用対効果 · Estimated64.4

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 57.9 (estimated) · 0/19 observed / reasoning 64.2 (estimated) · 0/13 observed / writing 55.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-4.5-air · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

Input 0 – 31,999 Token · Output 0 – 199 Token入力使用量 · 100万 Token あたり219,178 ポイントキャッシュヒット使用量 · 100万 Token あたり43,836 ポイント出力使用量 · 100万 Token あたり547,945 ポイント

Input 0 – 31,999 Token · Output 200+ Token入力使用量 · 100万 Token あたり219,178 ポイントキャッシュヒット使用量 · 100万 Token あたり43,836 ポイント出力使用量 · 100万 Token あたり1,643,836 ポイント

Input 32,000+ Token入力使用量 · 100万 Token あたり328,767 ポイントキャッシュヒット使用量 · 100万 Token あたり65,753 ポイント出力使用量 · 100万 Token あたり2,191,781 ポイント

qwen-pixverse/pixverse-lipsyncqwen-pixverse-pixverse-lipsync独立モデルpixverse · 正式2025-07-14固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-Plusqwen-plus独立モデルQwen · 正式2025-06-24価格の最終確認
確認待ち (UTC+8)

性能 · Estimated44.2費用対効果 · Estimated55.9

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 45.6 (estimated) · 0/19 observed / reasoning 46.7 (estimated) · 0/13 observed / writing 40.3 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-plus · 8 benchmarksReference: qwen-plus-0125 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

Input 0 – 128,000 Token入力使用量 · 100万 Token あたり219,178 ポイントキャッシュヒット使用量 · 100万 Token あたり43,836 ポイント出力使用量 · 100万 Token あたり547,945 ポイント

Input 128,001 – 256,000 Token入力使用量 · 100万 Token あたり657,534 ポイントキャッシュヒット使用量 · 100万 Token あたり131,507 ポイント出力使用量 · 100万 Token あたり5,479,452 ポイント

Input 256,001+ Token入力使用量 · 100万 Token あたり1,315,068 ポイントキャッシュヒット使用量 · 100万 Token あたり263,014 ポイント出力使用量 · 100万 Token あたり13,150,685 ポイント

qwen-SiliconFlow DeepSeek-R1-0528qwen-siliconflow-deepseek-r1-0528独立モデルDeepSeek · 正式2025-05-28固定単価なし。実際のサービスに応じて課金

性能 · Estimated43.2費用対効果 · Estimated45.2

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Mistral OCR 2505-100mistralai-mistral-ocr-2505-001独立モデルMistral AI · 正式2025-05-22固定単価なし。実際のサービスに応じて課金

性能 · Estimated81.8費用対効果 · Estimated72.3

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mistral-ocr-4-0 · 81.8Reference: cohere-parse-v5 · 79.2Reference: mistral-document-ai-2512 · 96.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.mistral-ocr · Official cohere-parsebench · Official mistral-ocr · Official

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

mistral-medium-2505mistral-medium-2505独立モデルMistral AI · 正式2025-05-07固定単価なし。実際のサービスに応じて課金

性能 · Estimated54.1費用対効果 · Estimated52.9

Version comparison review4/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 47.4 (estimated) · 1/19 observed / reasoning 59.7 (estimated) · 1/13 observed / writing 55.3 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below mistral-medium-3-5 by 6.5 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Phi-4 Reasoningphi-4-reasoning独立モデルMicrosoft · 正式2025-04-30価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated63.3

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり250,000 ポイント出力使用量 · 100万 Token あたり1,000,000 ポイント

o3o3独立モデルOpenAI · 正式2025-04-16価格の最終確認
確認待ち (UTC+8)

性能 · Estimated62.8費用対効果 · Estimated56.1

7/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 18%coding 57.9 (estimated) · 1/19 observed / reasoning 70.4 (estimated) · 4/13 observed / writing 60.0 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: o3-2025-04-16 · 4 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksReference: DeepSeek V4 Pro (High) (0813) · 1 benchmarksopenai-simple-evals · Official microsoft-mai-report · Official mistral-codestral · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり4,000,000 ポイントキャッシュヒット使用量 · 100万 Token あたり1,000,000 ポイント出力使用量 · 100万 Token あたり16,000,000 ポイント

Veo 2.0 Generate 001-100veo-2.0-generate-001独立モデルGoogle · 正式2025-04-09固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Llama 4 Maverick 17B 128Ellama-4-maverick-17b-128e-instruct-fp8独立モデルMeta · 正式2025-04-05価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated60.4

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり500,000 ポイント出力使用量 · 100万 Token あたり2,000,000 ポイント

Llama 4 Maverick 17B 128E-100llama-4-maverick-17b-128e-instruct-maas-100独立モデルMeta · 正式2025-04-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Llama 4 Scout 17B 16E Instruct-100meta-llama-4-scout-17b-16e-instruct-maas-001独立モデルMeta · 正式2025-04-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated53.1費用対効果 · Estimated52.2

4/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.1 (estimated) · 1/19 observed / reasoning 56.7 (estimated) · 1/13 observed / writing 47.4 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-SiliconFlow DeepSeek-V3-0324qwen-siliconflow-deepseek-v3-0324独立モデルDeepSeek · 正式2025-03-24固定単価なし。実際のサービスに応じて課金

性能 · Estimated39.9費用対効果 · Estimated42.9

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 36.0 (estimated) · 0/19 observed / reasoning 48.3 (estimated) · 0/13 observed / writing 35.5 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-coder-480b-a35b-instruct · 5 benchmarksReference: qwen3-30b-a3b · 4 benchmarksReference: qwen3-32b · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below qwen-deepseek-r1-0528 by 4.6 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

GPT-4o Mini Transcribegpt-4o-mini-transcribe独立モデルOpenAI · 正式2025-03-20利用可能・音声ツール価格の最終確認
確認待ち (UTC+8)

性能 · Estimated91.4費用対効果 · Estimated94.0

Estimate basis

入力使用量 · 音声 · 100万 Token あたり6,000,000 ポイント入力使用量 · 100万 Token あたり2,500,000 ポイント出力使用量 · 100万 Token あたり10,000,000 ポイント

GPT-4o Mini TTSgpt-4o-mini-tts独立モデルOpenAI · 正式2025-03-20利用可能・音声ツール価格の最終確認
確認待ち (UTC+8)

性能 · Estimated59.8費用対効果 · Estimated56.9

Estimate basis

入力使用量 · 100万 Token あたり1,200,000 ポイント出力使用量 · 音声 · 100万 Token あたり24,000,000 ポイント

GPT-4o Transcribegpt-4o-transcribe独立モデルOpenAI · 正式2025-03-20利用可能・音声ツール価格の最終確認
確認待ち (UTC+8)

性能91.4費用対効果64.0

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 18%qwen-asr-report · Independent

入力使用量 · 音声 · 100万 Token あたり12,000,000 ポイント入力使用量 · 100万 Token あたり5,000,000 ポイント出力使用量 · 100万 Token あたり20,000,000 ポイント

mistral-small-2503mistral-small-2503独立モデルMistral AI · 正式2025-03-17固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.0費用対効果—

Shared exact-model performance from mistral-small-2503; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.7 (estimated) · 0/19 observed / reasoning 59.2 (estimated) · 0/13 observed / writing 52.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: mistral-small-2506 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Mistral Small 3.1-100mistral-small-2503-100独立モデルGoogle · プレビュー2025-03-17価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.0費用対効果 · Estimated64.3

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.7 (estimated) · 0/19 observed / reasoning 59.2 (estimated) · 0/13 observed / writing 52.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: mistral-small-2506 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり200,000 ポイント出力使用量 · 100万 Token あたり600,000 ポイント

Text Embedding Large Exp 03 07-100text-embedding-large-exp-03-07独立モデルGoogle · 正式2025-03-07固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-DeepSeek-R1-Distill-Qwen-1.5Bqwen-deepseek-r1-distill-qwen-1.5b独立モデルDeepSeek · 正式2025-01-20固定単価なし。実際のサービスに応じて課金

性能 · Estimated43.2費用対効果 · Estimated45.2

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Codestral 2501codestral-2501独立モデルMistral AI · 正式2025-01-13全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated60.1

9/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 18%coding 56.8 (estimated) · 9/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksReference: smaug-flash · 3 benchmarksmistral-codestral · Official microsoft-mai-report · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり600,000 ポイント出力使用量 · 100万 Token あたり1,800,000 ポイント

Ministral-3Bministral-3b独立モデルMistral AI · 正式2024-10-16固定単価なし。実際のサービスに応じて課金

性能 · Estimated49.2費用対効果 · Estimated49.4

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 53.8 (estimated) · 0/19 observed / reasoning 50.7 (estimated) · 0/13 observed / writing 43.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: ministral-8b-2410 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-Longqwen-long独立モデルQwen · 正式2024-05-20価格の最終確認
確認待ち (UTC+8)

性能 · Estimated52.5費用対効果 · Estimated62.9

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 48.7 (estimated) · 0/19 observed / reasoning 58.7 (estimated) · 0/13 observed / writing 50.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: qwen-glm-4.5 · 4 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり136,986 ポイントキャッシュヒット使用量 · 100万 Token あたり0 ポイント出力使用量 · 100万 Token あたり547,945 ポイント

Text Embedding 3 Largetext-embedding-3-large独立モデルOpenAI · 正式2024-01-25価格の最終確認
確認待ち (UTC+8)

性能64.6費用対効果45.2

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · Official

埋め込み入力 · 100万 Token あたり260,000 ポイント

Text Embedding 3 Smalltext-embedding-3-small独立モデルOpenAI · 正式2024-01-25価格の最終確認
確認待ち (UTC+8)

性能62.3費用対効果71.3

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · Official

埋め込み入力 · 100万 Token あたり40,000 ポイント

Cohere-embed-v3-englishcohere-embed-v3-english独立モデルCohere · 正式2023-11-02固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Cohere-embed-v3-multilingualcohere-embed-v3-multilingual独立モデルCohere · 正式2023-11-02固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Text Embedding Ada 002text-embedding-ada-002独立モデルOpenAI · 正式2022-12-15価格の最終確認
確認待ち (UTC+8)

性能61.0費用対効果46.6

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · Official

埋め込み入力 · 100万 Token あたり200,000 ポイント

Qwen-Image-2.1-Turboqwen-image-2.1-turbo独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-14固定単価なし。実際のサービスに応じて課金

性能—費用対効果—

未評価

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Chirp 2-100chirp-2-001独立モデルGoogle · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

语音生成CosyVoice-v3.5-flash大模型cosyvoice-v3.5-flash独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated75.4費用対効果 · Estimated67.8

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · Official

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

语音生成CosyVoice-v3.5-plus大模型cosyvoice-v3.5-plus独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated75.4費用対効果 · Estimated67.8

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · Official

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

doubao-GLM-5.3-Flashdoubao-glm-5-3-flash-260828固定スナップショット／版 · 唯一の入口Zhipu · 正式カタログ追加（公開日未確認）: 2026-10-05価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated63.3

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

qwen2-5-72bdoubao-qwen2-5-72b-20240919固定スナップショット／版 · 唯一の入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen3-0-6bdoubao-qwen3-0-6b-20250429固定スナップショット／版 · 唯一の入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen3-14bdoubao-qwen3-14b-20250429固定スナップショット／版 · 唯一の入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen3-32bdoubao-qwen3-32b-20250429固定スナップショット／版 · 唯一の入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen3-8bdoubao-qwen3-8b-20250429固定スナップショット／版 · 唯一の入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

doubao-seed-translationdoubao-seed-translation-250915固定スナップショット／版 · 唯一の入口Doubao · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

doubao-smart-routerdoubao-smart-router-250928固定スナップショット／版 · 唯一の入口Doubao · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated50.0費用対効果 · Estimated50.0

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: o1-mini · 50.0Reference: qwen3.6-plus · 50.2Reference: gemini-2.0-flash-001 · 50.3Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-simple-evals · Official arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

FaceChain人物图像检测facechain-facedetect独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated44.5費用対効果 · Estimated46.1

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Fun-ASR语音识别fun-asr独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated91.4費用対効果 · Estimated79.0

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Fun-ASR实时语音识别fun-asr-realtime独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated52.6費用対効果 · Estimated51.8

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

音乐生成 Previewfun-music-preview独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

音乐生成fun-music-v1独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Grok 4.20 Non-Reasoning-100grok-4-20-non-reasoning-100独立モデルxAI · 正式カタログ追加（公開日未確認）: 2026-10-05価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果—

Estimate basis

Grok 4.20 Reasoning-100grok-4-20-reasoning-100独立モデルxAI · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果—

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Grok 4.3-100grok-4.3-100独立モデルxAI · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated44.8費用対効果—

Shared exact-model performance from grok-4.3; coverage refers to public model benchmarks, not tests of every platform deployment.12/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.8 (estimated) · 4/19 observed / reasoning 48.3 (estimated) · 4/13 observed / writing 47.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent livebench · Independent microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-HappyHorse-1.0-Video-Edithappyhorse-1.0-video-edit独立モデルHappyHorse · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated80.9費用対効果 · Estimated71.6

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

图像擦除补全image-erase-completion独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated44.5費用対効果 · Estimated46.1

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

人物实例分割image-instance-segmentation独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated44.5費用対効果 · Estimated46.1

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Codestral 2-100mistralai-codestral-2-001独立モデルMistral AI · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Mistral Medium 3-100mistralai-mistral-medium-3-001独立モデルMistral AI · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Paraformer语音识别-8k-v2paraformer-8k-v2独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Paraformer实时语音识别-8k-v2paraformer-realtime-8k-v2独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated52.6費用対効果 · Estimated51.8

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Paraformer实时语音识别-v2paraformer-realtime-v2独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated52.6費用対効果 · Estimated51.8

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Paraformer语音识别-v2paraformer-v2独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen3-ASR-Flash-Filetransqwen3-asr-flash-filetrans独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated91.4費用対効果 · Estimated79.0

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen3-ASR-Flash-Realtimeqwen3-asr-flash-realtime独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated52.6費用対効果 · Estimated51.8

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-Audio-3.1-ASR-Flashqwen-audio-3.1-asr-flash独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated91.4費用対効果 · Estimated79.0

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-Audio-3.1-ASR-Flash-Filetransqwen-audio-3.1-asr-flash-filetrans独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated91.4費用対効果 · Estimated79.0

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-Audio-3.1-ASR-Flash-Messageqwen-audio-3.1-asr-flash-message独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated91.4費用対効果 · Estimated79.0

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-Audio-3.1-ASR-Flash-Streamingqwen-audio-3.1-asr-flash-streaming独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated91.4費用対効果 · Estimated79.0

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-Audio-3.1-TTS-Flashqwen-audio-3.1-tts-flash独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated74.4費用対効果 · Estimated67.1

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · Official

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-Audio-3.1-TTS-Nextqwen-audio-3.1-tts-next独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated74.4費用対効果 · Estimated67.1

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · Official

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-Doc-Turboqwen-doc-turbo独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05価格の最終確認
確認待ち (UTC+8)

性能 · Estimated48.7費用対効果 · Estimated49.1

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 46.8 (estimated) · 0/19 observed / reasoning 52.3 (estimated) · 0/13 observed / writing 47.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3.6-plus · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり164,384 ポイントキャッシュヒット使用量 · 100万 Token あたり32,877 ポイント出力使用量 · 100万 Token あたり273,973 ポイント

Qwen-Flash-Characterqwen-flash-character独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05価格の最終確認
確認待ち (UTC+8)

性能 · Estimated59.9費用対効果 · Estimated70.2

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 57.1 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり68,493 ポイントキャッシュヒット使用量 · 100万 Token あたり13,699 ポイント出力使用量 · 100万 Token あたり410,959 ポイント

qwen-Kling Video 3.0 Turboqwen-kling-kling-v3-turbo-video-generation独立モデルkling · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-speech-02-hdqwen-minimax-speech-02-hd独立モデルmini-max · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated32.9費用対効果 · Estimated38.0

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 32.7 (estimated) · 0/19 observed / reasoning 39.5 (estimated) · 0/13 observed / writing 26.5 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2-72b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-speech-02-turboqwen-minimax-speech-02-turbo独立モデルmini-max · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated34.1費用対効果 · Estimated38.9

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 39.8 (estimated) · 0/13 observed / writing 28.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3.6-plus · 7 benchmarksReference: qwen2-72b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-speech-2.8-hdqwen-minimax-speech-2.8-hd独立モデルmini-max · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated44.1費用対効果 · Estimated45.9

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.0 (estimated) · 0/19 observed / reasoning 53.2 (estimated) · 0/13 observed / writing 41.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b-instruct-2507 · 4 benchmarksReference: qwen3-235b-a22b-thinking-2507 · 4 benchmarksReference: qwen3-30b-a3b-instruct-2507 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-speech-2.8-turboqwen-minimax-speech-2.8-turbo独立モデルmini-max · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated46.9費用対効果 · Estimated47.8

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 40.0 (estimated) · 0/19 observed / reasoning 56.2 (estimated) · 0/13 observed / writing 44.6 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3.6-plus · 7 benchmarksReference: qwen3-30b-a3b-instruct-2507 · 4 benchmarksReference: qwen3-max-2025-09-23 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-MT-Flashqwen-mt-flash独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated59.4費用対効果 · Estimated56.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-MT-Imageqwen-mt-image独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated34.1費用対効果 · Estimated38.9

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image · 20.0Reference: qwen-image-prompt-extend · 23.8Reference: qwen-image-2.1 · 73.8Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-MT-Liteqwen-mt-lite独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.3費用対効果 · Estimated54.4

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.2 (estimated) · 0/19 observed / reasoning 60.6 (estimated) · 0/13 observed / writing 58.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.7-max · 8 benchmarksReference: qwen3.8-max · 8 benchmarksReference: qwen3.6-plus · 7 benchmarksReference: qwen-glm-4.6 · 5 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-MT-Plusqwen-mt-plus独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated46.7費用対効果 · Estimated47.7

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 46.9 (estimated) · 0/19 observed / reasoning 50.1 (estimated) · 0/13 observed / writing 43.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: qwen3.6-plus · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen-plus-0125 · 4 benchmarksReference: qwen2.5-plus-1127 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-PixVerse-V6-r2vqwen-pixverse-pixverse-v6-r2v独立モデルpixverse · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-Plus-Characterqwen-plus-character独立モデルqwen-domain-model · 正式カタログ追加（公開日未確認）: 2026-10-05価格の最終確認
確認待ち (UTC+8)

性能 · Estimated46.9費用対効果 · Estimated57.8

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 47.0 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 43.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: qwen3.6-plus · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen-plus-0125 · 4 benchmarksReference: qwen2.5-plus-1127 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり219,178 ポイントキャッシュヒット使用量 · 100万 Token あたり43,836 ポイント出力使用量 · 100万 Token あたり547,945 ポイント

qwen-stepfun/step-5-previewqwen-stepfun-step-5-preview独立モデルStepFun · 正式カタログ追加（公開日未確認）: 2026-10-05価格の最終確認
確認待ち (UTC+8)

性能 · Estimated41.0費用対効果 · Estimated30.7

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

入力使用量 · 100万 Token あたり1,917,808 ポイントキャッシュヒット使用量 · 100万 Token あたり95,890 ポイント出力使用量 · 100万 Token あたり5,479,452 ポイント

qwen-unisound/unisound-u2qwen-unisound-unisound-u2独立モデルunisound · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated32.9費用対効果 · Estimated38.0

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Vanchin/DeepSeek-R1qwen-vanchin-deepseek-r1独立モデルDeepSeek · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated43.2費用対効果 · Estimated45.2

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Vanchin/DeepSeek-V3qwen-vanchin-deepseek-v3独立モデルDeepSeek · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated42.6費用対効果 · Estimated44.8

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.2 (estimated) · 0/19 observed / reasoning 51.7 (estimated) · 0/13 observed / writing 39.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b-no-thinking · 4 benchmarksReference: qwen3-next-80b-a3b-thinking · 4 benchmarksReference: qwen3-vl-235b-a22b-thinking · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below qwen-deepseek-r1-0528 by 1.9 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-vanchin/deepseek-v4-proqwen-vanchin-deepseek-v4-pro独立モデルDeepSeek · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated71.1費用対効果 · Estimated64.8

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 67.0 (estimated) · 0/19 observed / reasoning 75.3 (estimated) · 0/13 observed / writing 70.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen3.8-max · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: qwen3.8-27b · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Vidu-image-lite_reference2imageqwen-vidu-vidu-image-lite_reference2image独立モデルvidu · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated66.4費用対効果 · Estimated61.5

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Vidu-image-pro_reference2imageqwen-vidu-vidu-image-pro_reference2image独立モデルvidu · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated66.4費用対効果 · Estimated61.5

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Vidu-image_reference2imageqwen-vidu-vidu-image_reference2image独立モデルvidu · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated73.8費用対効果 · Estimated66.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ2-fast_reference2imageqwen-vidu-viduq2-fast_reference2image独立モデルvidu · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated66.4費用対効果 · Estimated61.5

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ2-Pro_reference2imageqwen-vidu-viduq2-pro_reference2image独立モデルvidu · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated66.4費用対効果 · Estimated61.5

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ3-Ad_reference2videoqwen-vidu-viduq3-ad_reference2video独立モデルvidu · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ3-Drama_reference2videoqwen-vidu-viduq3-drama_reference2video独立モデルvidu · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ3-fast_reference2imageqwen-vidu-viduq3-fast_reference2image独立モデルvidu · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated85.0費用対効果 · Estimated74.5

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-3.0-pro · 85.0Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ViduQ3-Pro-fast_img2videoqwen-vidu-viduq3-pro-fast_img2video独立モデルvidu · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Qwen-Voice-Enrollmentqwen-voice-enrollment独立サービス入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 45.7 (estimated) · 0/19 observed / reasoning 56.4 (estimated) · 0/13 observed / writing 50.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-ZHIPU/GLM-5.3-FlashXqwen-zhipu-glm-5.3-flashx独立モデルZhipu AI · 正式カタログ追加（公開日未確認）: 2026-10-05価格の最終確認
確認待ち (UTC+8)

性能 · Estimated41.0費用対効果 · Estimated37.8

Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

入力使用量 · 100万 Token あたり547,945 ポイントキャッシュヒット使用量 · 100万 Token あたり156,164 ポイント出力使用量 · 100万 Token あたり1,917,808 ポイント

Sambert语音合成-Bethsambert-beth-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-Bettysambert-betty-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-Briansambert-brian-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-Callysambert-cally-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-Camilasambert-camila-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-Cindysambert-cindy-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-Clarasambert-clara-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-Donnasambert-donna-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-Evasambert-eva-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-Hannasambert-hanna-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-Indahsambert-indah-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-Perlasambert-perla-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-Waansambert-waan-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知厨sambert-zhichu-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知达sambert-zhida-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知德sambert-zhide-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知飞sambert-zhifei-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知柜sambert-zhigui-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated44.5費用対効果 · Estimated46.1

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知浩sambert-zhihao-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知佳sambert-zhijia-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知婧sambert-zhijing-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知伦sambert-zhilun-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知猫sambert-zhimao-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知妙（多情感）sambert-zhimiao-emo-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知茗sambert-zhiming-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知墨sambert-zhimo-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知楠sambert-zhinan-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知娜sambert-zhina-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知倩sambert-zhiqian-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知琪sambert-zhiqi-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知茹sambert-zhiru-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知硕sambert-zhishuo-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知树sambert-zhishu-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知莎sambert-zhistella-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知婷sambert-zhiting-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知薇sambert-zhiwei-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知祥sambert-zhixiang-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知笑sambert-zhixiao-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知雅sambert-zhiya-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知晔sambert-zhiye-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知颖sambert-zhiying-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知媛sambert-zhiyuan-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

Sambert语音合成-知悦sambert-zhiyue-v1独立音声入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

鞋靴模特shoemodel-v1独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated44.5費用対効果 · Estimated46.1

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

语音识别热词speech-biasing独立サービス入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

通用文本向量-async-v1text-embedding-async-v1独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

通用文本向量-async-v2text-embedding-async-v2独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

意图分类模型tongyi-intent-detect-v3独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

伶鹊-对话分析-flashtongyi-xiaomi-analysis-flash独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

入力使用量 · 100万 Token あたり54,795 ポイントキャッシュヒット使用量 · 100万 Token あたり10,959 ポイント出力使用量 · 100万 Token あたり109,589 ポイント

伶鹊-对话分析-protongyi-xiaomi-analysis-pro独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

入力使用量 · 100万 Token あたり273,973 ポイントキャッシュヒット使用量 · 100万 Token あたり54,795 ポイント出力使用量 · 100万 Token あたり739,726 ポイント

Translate LLM-100translate-llm独立モデルGoogle · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

声动人像VideoRetalkvideoretalk独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

视频风格重绘video-style-transform独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.0費用対効果 · Estimated50.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

虚拟模特V2virtualmodel-v2独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated44.5費用対効果 · Estimated46.1

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

大模型声音复刻及声音设计voice-enrollment独立サービス入口Qwen · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated56.6費用対効果 · Estimated54.6

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Wan2.2-Animate-Mixwan2.2-animate-mix独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Wan2.2-Animate-Movewan2.2-animate-move独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Wan2.2-KF2V-Flashwan2.2-kf2v-flash独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-通义万相2.2-数字人-S2Vwan2.2-s2v独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Wan2.2-S2V-Detectwan2.2-s2v-detect独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Wan2.2-T2I-Flashwan2.2-t2i-flash独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Wan2.2-T2I-Pluswan2.2-t2i-plus独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Wan2.5-I2I-Previewwan2.5-i2i-preview独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated52.7費用対効果 · Estimated51.9

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-i2v-preview · 55.3Reference: wan2.5-t2v-preview · 48.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Wan2.5-T2I-Previewwan2.5-t2i-preview独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated51.5費用対効果 · Estimated51.0

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: wan2.5-i2v-preview · 55.3Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Wan2.6-R2V-Flashwan2.6-r2v-flash独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated55.3費用対効果 · Estimated53.7

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.6-i2v · 53.2Reference: wan2.6-t2v · 57.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Wan2.0-T2I-Turbowanx2.0-t2i-turbo独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Wan2.1-ImageEditwanx2.1-imageedit独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Wan2.1-KF2V-Pluswanx2.1-kf2v-plus独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Wan2.1-T2I-Pluswanx2.1-t2i-plus独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Wan2.1-T2I-Turbowanx2.1-t2i-turbo独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-Wan2.1-VACE-Pluswanx2.1-vace-plus独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-创意海报生成wanx-poster-generation-v1独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-万相-涂鸦作画wanx-sketch-to-image-lite独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated34.8費用対効果 · Estimated39.4

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Reference: wan2.5-i2v-preview · 55.3Reference: wan2.5-t2v-preview · 48.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-人像风格重绘wanx-style-repaint-v1独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-wanx-t2iwanx-v1独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-虚拟模特wanx-virtualmodel独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated36.9費用対効果 · Estimated40.8

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Reference: wan2.5-i2v-preview · 55.3Reference: wan2.5-t2v-preview · 48.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

qwen-万相-图像局部重绘wanx-x-painting独立モデルWan · 正式カタログ追加（公開日未確認）: 2026-10-05固定単価なし。実際のサービスに応じて課金

性能 · Estimated37.0費用対効果 · Estimated40.9

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Reference: wan2.5-i2v-preview · 55.3Reference: wan2.5-t2v-preview · 48.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent arena · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

语音生成cosyvoice-v2大模型cosyvoice-v2独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10利用可能・音声ツール価格の最終確認
確認待ち (UTC+8)

性能 · Estimated75.4費用対効果 · Estimated52.8

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6qwen-tts-public · Official

音声 · 10,000文字あたり547,946 ポイント

语音生成CosyVoice-v3-flash大模型cosyvoice-v3-flash独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10利用可能・音声ツール価格の最終確認
確認待ち (UTC+8)

性能 · Estimated75.4費用対効果 · Estimated75.5

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6qwen-tts-public · Official

音声 · 10,000文字あたり273,973 ポイント

语音生成CosyVoice-v3-plus大模型cosyvoice-v3-plus独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10利用可能・音声ツール価格の最終確認
確認待ち (UTC+8)

性能 · Estimated75.4費用対効果 · Estimated52.8

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6qwen-tts-public · Official

音声 · 10,000文字あたり547,946 ポイント

GUI-Plusgui-plus独立モデルQwen · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能 · Estimated56.6費用対効果 · Estimated61.7

0/41 fixed-panel observations; remaining cells are marked estimates

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Official mistral-codestral · Official openai-simple-evals · Official arena · Independent arena · Independent arena · Independent livebench · Independent

入力使用量 · 100万 Token あたり410,959 ポイントキャッシュヒット使用量 · 100万 Token あたり0 ポイント出力使用量 · 100万 Token あたり1,232,877 ポイント

通用多模态向量multimodal-embedding-v1独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated62.3費用対効果 · Estimated48.1

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Official aliyun-embedding · Official

埋め込み入力 · 100万 Token あたり191,781 ポイント入力使用量 · 画像 · 100万 Token あたり246,576 ポイント動画入力 · 100万 Token あたり246,576 ポイント

Qwen2.5-VL-Embeddingqwen2.5-vl-embedding独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能 · Estimated62.3費用対効果 · Estimated48.1

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Official aliyun-embedding · Official

埋め込み入力 · 100万 Token あたり191,781 ポイント入力使用量 · 画像 · 100万 Token あたり493,151 ポイント

Qwen3-ASR-Flashqwen3-asr-flash独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10利用可能・音声ツール価格の最終確認
確認待ち (UTC+8)

性能 · Estimated91.4費用対効果 · Estimated94.0

Estimate basis

文字起こし · 1秒あたり61 ポイント

千问3-Rerankqwen3-rerank独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能 · Estimated72.5費用対効果 · Estimated80.8

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3-Reranker-4B · 73.9Reference: Qwen3-Reranker-8B · 74.2Reference: Qwen3-Reranker-0.6B · 68.8qwen-rerank-public · Official

入力使用量 · 100万 Token あたり136,987 ポイント

Qwen3-VL-Embeddingqwen3-vl-embedding独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能 · Estimated62.3費用対効果 · Estimated48.1

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Official aliyun-embedding · Official

埋め込み入力 · 100万 Token あたり191,781 ポイント入力使用量 · 画像 · 100万 Token あたり493,151 ポイント

Qwen3-VL-Rerankqwen3-vl-rerank独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated72.5費用対効果 · Estimated80.8

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3-Reranker-4B · 73.9Reference: Qwen3-Reranker-8B · 74.2Reference: Qwen3-Reranker-0.6B · 68.8qwen-rerank-public · Official

入力使用量 · 100万 Token あたり136,987 ポイント動画入力 · 100万 Token あたり493,154 ポイント

ユーザー確認済みの動画入力の暫定責任価格です。提供元は正式な動画価格とフレームからTokenへの換算を公開していません。公開カタログ表示と受入検証の予約額にのみ使用し、仕入原価として計上せず、過去の請求も変更しません。

Qwen-Image-2.0-Proqwen-image-2.0-pro独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10利用可能・生成と編集価格の最終確認
確認待ち (UTC+8)

性能 · Estimated66.4費用対効果 · Estimated46.5

Estimate basis

出力使用量 · 画像 · 1枚あたり136,987 ポイント

Qwen-Image-3.0-Proqwen-image-3.0-pro独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10利用可能・生成と編集価格の最終確認
確認待ち (UTC+8)

性能85.0費用対効果59.5

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent

画像入力使用量 1K · 1枚あたり5,480 ポイント画像入力使用量 2K · 1枚あたり5,480 ポイント画像出力使用量 1K · 1枚あたり68,494 ポイント画像出力使用量 2K · 1枚あたり136,987 ポイント

QwenVL-OCRqwen-vl-ocr独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能 · Estimated81.8費用対効果 · Estimated72.3

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mistral-ocr-4-0 · 81.8Reference: cohere-parse-v5 · 79.2Reference: mistral-document-ai-2512 · 96.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.mistral-ocr · Official cohere-parsebench · Official mistral-ocr · Official

入力使用量 · 100万 Token あたり82,192 ポイント出力使用量 · 100万 Token あたり136,987 ポイント

通用文本向量-v1text-embedding-v1独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能58.3費用対効果45.3

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · Official

埋め込み入力 · 100万 Token あたり191,781 ポイント

通用文本向量-v2text-embedding-v2独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能60.1費用対効果46.6

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · Official

埋め込み入力 · 100万 Token あたり191,781 ポイント

通用文本向量-v3text-embedding-v3独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能63.4費用対効果53.9

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · Official

埋め込み入力 · 100万 Token あたり136,987 ポイント

通用文本向量-v4text-embedding-v4独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能71.6費用対効果59.6

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · Official

埋め込み入力 · 100万 Token あたり136,987 ポイント

视觉向量-flashtongyi-embedding-vision-flash独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能 · Estimated62.3費用対効果 · Estimated70.9

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Official aliyun-embedding · Official

埋め込み入力 · 100万 Token あたり41,096 ポイント

视觉向量-plustongyi-embedding-vision-plus独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能 · Estimated62.3費用対効果 · Estimated53.1

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Official aliyun-embedding · Official

埋め込み入力 · 100万 Token あたり136,987 ポイント

Wan2.2-I2V-Flashwan2.2-i2v-flash独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能 · Estimated11.7費用対効果 · Estimated38.2

Estimate basis

動画生成 480P · 1秒あたり27,398 ポイント動画生成 720P · 1秒あたり54,795 ポイント動画生成 1080P · 1秒あたり131,507 ポイント

Wan2.2-I2V-Pluswan2.2-i2v-plus独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

動画生成 480P · 1秒あたり38,357 ポイント動画生成 1080P · 1秒あたり191,781 ポイント

Wan2.2-T2V-Pluswan2.2-t2v-plus独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能 · Estimated11.7費用対効果 · Estimated23.2

Estimate basis

動画生成 480P · 1秒あたり38,357 ポイント動画生成 1080P · 1秒あたり191,781 ポイント

Wan2.5-I2V-Previewwan2.5-i2v-preview独立モデルAlibaba Cloud · プレビューカタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能55.3費用対効果46.8

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent

動画生成 480P · 1秒あたり82,192 ポイント動画生成 720P · 1秒あたり164,384 ポイント動画生成 1080P · 1秒あたり273,973 ポイント

Wan2.5-T2V-Previewwan2.5-t2v-preview独立モデルAlibaba Cloud · プレビューカタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能48.9費用対効果42.3

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent

動画生成 480P · 1秒あたり82,192 ポイント動画生成 720P · 1秒あたり164,384 ポイント動画生成 1080P · 1秒あたり273,973 ポイント

wan2.6-I2V-flashwan2.6-i2v-flash独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能 · Estimated54.9費用対効果 · Estimated60.3

Estimate basis

動画生成 720P · 1秒あたり82,192 ポイント動画生成 1080P · 1秒あたり136,987 ポイント

Wan2.1-I2V-Pluswanx2.1-i2v-plus独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能 · Estimated11.7費用対効果 · Estimated13.2

Estimate basis

動画生成 720P · 1秒あたり191,781 ポイント

Wan2.1-I2V-Turbowanx2.1-i2v-turbo独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能 · Estimated11.7費用対効果 · Estimated34.6

Estimate basis

動画生成 480P · 1秒あたり65,754 ポイント動画生成 720P · 1秒あたり65,754 ポイント

Wan2.1-T2V-Pluswanx2.1-t2v-plus独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能 · Estimated11.7費用対効果 · Estimated13.2

Estimate basis

動画生成 720P · 1秒あたり191,781 ポイント

Wan2.1-T2V-Turbowanx2.1-t2v-turbo独立モデルAlibaba Cloud · 正式カタログ追加（公開日未確認）: 2026-09-10価格の最終確認
確認待ち (UTC+8)

性能 · Estimated11.7費用対効果 · Estimated34.6

Estimate basis

動画生成 480P · 1秒あたり65,754 ポイント動画生成 720P · 1秒あたり65,754 ポイント

doubao-hitem3d-2-0-251223doubao-hitem3d-2-0-251223固定スナップショット／版 · 唯一の入口Hitem3D · 正式カタログ追加（公開日未確認）: 2026-09-09価格の最終確認
確認待ち (UTC+8)

性能 · Estimated82.2費用対効果 · Estimated57.5

Estimate basis

出力使用量 · 3D · 100万 Token あたり21,917,809 ポイント

doubao-hyper3d-gen2-260112doubao-hyper3d-gen2-260112固定スナップショット／版 · 唯一の入口Hyper3D · 正式カタログ追加（公開日未確認）: 2026-09-09価格の最終確認
確認待ち (UTC+8)

性能 · Estimated82.2費用対効果 · Estimated87.5

Estimate basis

出力使用量 · 3D · 100万 Token あたり16,438,357 ポイント

doubao-seedance-2-0-260128doubao-seedance-2-0-260128固定スナップショット／版 · 唯一の入口ByteDance · 正式カタログ追加（公開日未確認）: 2026-09-09価格の最終確認
確認待ち (UTC+8)

性能 · Estimated91.5費用対効果 · Estimated68.5

Estimate basis

出力使用量 · 動画生成 · 100万 Token あたり12,602,740 ポイント

doubao-seedance-2-0-fast-260128doubao-seedance-2-0-fast-260128固定スナップショット／版 · 唯一の入口ByteDance · 正式カタログ追加（公開日未確認）: 2026-09-09価格の最終確認
確認待ち (UTC+8)

性能 · Estimated91.5費用対効果 · Estimated70.8

Estimate basis

出力使用量 · 動画生成 · 100万 Token あたり7,602,740 ポイント

doubao-seedance-2-0-mini-260615doubao-seedance-2-0-mini-260615固定スナップショット／版 · 唯一の入口ByteDance · 正式カタログ追加（公開日未確認）: 2026-09-09価格の最終確認
確認待ち (UTC+8)

性能 · Estimated91.5費用対効果 · Estimated75.9

Estimate basis

出力使用量 · 動画生成 · 100万 Token あたり2,520,548 ポイント

doubao-seedream-5-0-260128doubao-seedream-5-0-260128固定スナップショット／版 · 唯一の入口ByteDance · 正式カタログ追加（公開日未確認）: 2026-09-09利用可能・生成と編集価格の最終確認
確認待ち (UTC+8)

性能 · Estimated54.4費用対効果 · Estimated53.4

Estimate basis

出力使用量 · 画像 · 1枚あたり60,274 ポイント

GPT-4o Transcribe Diarizegpt-4o-transcribe-diarize独立モデルOpenAI · 正式カタログ追加（公開日未確認）: 2026-08-28利用可能・音声ツール価格の最終確認
確認待ち (UTC+8)

性能 · Estimated91.4費用対効果 · Estimated64.0

Estimate basis

GPT Audiogpt-audio独立モデルOpenAI · 正式カタログ追加（公開日未確認）: 2026-08-28全機能価格の最終確認
確認待ち (UTC+8)

性能 · Estimated52.6費用対効果 · Estimated36.8

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9openai-realtime-public · Official

入力使用量 · 100万 Token あたり5,000,000 ポイント出力使用量 · 100万 Token あたり20,000,000 ポイント入力使用量 · 音声 · 100万 Token あたり80,000,000 ポイント出力使用量 · 音声 · 100万 Token あたり160,000,000 ポイント

Mistral Document AI 2512mistral-document-ai-2512独立モデルMistral AI · 正式カタログ追加（公開日未確認）: 2026-08-28価格の最終確認
確認待ち (UTC+8)

性能96.1費用対効果76.1

暫定評価

2026-10-08 16:22 (UTC+8) · Confidence 18%mistral-ocr · Official

文書処理 · 1,000ページあたり6,000,000 ポイント

Model Routermodel-router独立ルーティングサービスOpenAI · 正式カタログ追加（公開日未確認）: 2026-08-28固定単価なし。実際のサービスに応じて課金

性能 · Estimated50.0費用対効果 · Estimated50.0

Estimate basis

2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: o1-mini · 50.0Reference: qwen3.6-plus · 50.2Reference: gemini-2.0-flash-001 · 50.3Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-simple-evals · Official arena · Independent arena · Independent livebench · Independent

動的料金：ルーター入力加算と実際に選択されたモデルのポイント。

検証済み機能の説明 · 44

Claude Fable 5.1: complete within the verified, safely available deployment scope

Five adaptive efforts, high by default. Native/shared tools, structured output, real Codex continuation, image/PDF, cache and Key-owned files were verified.

Five adaptive efforts, high by default. Native/shared tools, structured output, real Codex continuation, image/PDF, cache and Key-owned files were verified.
Code execution uses the HCD free-combination billing bridge, adding fetch restricted to a non-resolving domain while preserving client tools. Execution/extremes are not live-tested (high-cost exemption); standalone native timing metering is not claimed.
Performance71.6/value55.1 are estimates:7 direct and34 estimated metrics in the fixed41-panel, using exact LiveBench max data.

Claude Haiku 5.5：Complete within the verified deployment scope

The exact available scope is verified; optional parameters and resources retain explicit bounds.

none disables thinking; low/medium/high/xhigh/max remain their real values; medium is the default. Native between_tools is rejected for this exact model.
Native Messages and the shared Chat/Responses path, strict tool schemas, inline image/PDF, SSE and signed history passed. The actual Codex complete tools, MCP echo and saved-thread continuation passed.
Bounded hosted search/fetch with citations and one-use owned remote MCP passed and settled once. Arbitrary remote URLs and unconstrained hosted execution are not enabled.
Ordinary input, output, cache reads and 5m/1h writes have separate rates. Input including cache reads/writes above100K uses the whole-request long-context tier at5x; the threshold boundary was checked offline.
The current deployment has no Files/Batch/container/skills API. Client function tools run on the client; no new native computer/browser toolset, durable background Responses resource or native compaction pass is claimed.
1M context and HCD128000 output limits retain safe reservation/settlement. Expensive extremes were not live-tested (high-cost exemption).
Performance55.1 and value61.9 are estimated:8 directly attributed fixed-panel cells and33 estimates out of41. Benchmark effort high is separate from the medium inference default.

Claude Opus 5.5: complete verified deployment scope

Text, image/PDF, tools, thinking, cache and web access through Messages, Chat, Responses and Codex compatibility.

Adaptive thinking is always on; medium is the default. Only temperature 1 is supported; top_p/top_k are unavailable.
Verified client bridging supplies tool discovery. Native server tool search returned a safety refusal and is not claimed passed.
1M context and 128K output. Expensive limits are not live-tested (high-cost exemption).
Files, Batch, code execution and native background jobs are not exposed. URL media generation is verified; token counting accepts supported inline inputs.
Client-side compaction and same-thread continuation are verified; unpriced server compaction remains closed.
Performance and value scores await exact-model evidence.

Claude Sonnet 5.5: complete within the verified, safely available deployment scope

Completion covers the exact model’s available scope. Optional hosted capabilities, resource quantities and budgets retain explicit bounds.

none, low, medium, high, xhigh and max; high is default. none uses between_tools: no up-front thinking, while progress between tools is retained. none is never aliased to low.
Native Messages and shared Chat/Responses conversion, strict structured output, advisory task-budget beta, functions, original SSE/signed thinking history, inline image/PDF, both cache TTLs and cache reads were verified.
Actual Codex complete default tools, discovery, top-level composed-schema bridging, an in-memory MCP round trip and a persisted second turn passed. Advanced beta controls require the corresponding official header.
Basic hosted search/fetch, citations and actual-usage accounting passed. No provider-native server Tool Search pass is claimed; client discovery bridging passed.
A funded owned remote-MCP HTTPS echo and Key/project lifecycle were verified; its lease was closed. Arbitrary remote URLs, variable results and external credential management remain closed.
The offering has no Batch, Files, code execution/containers/skills or new computer/browser toolsets. Messages has no native durable background-response resource. Native compaction remains closed; HCD’s existing client context path is reused without claiming an additional Sonnet compaction-generation live test.
Official 1M context and 128K output use uniform full-context rates. Expensive extremes are not live-tested (high-cost exemption); offline limits, safe holds and settlement remain enforced.
Performance 70.6 and value 61.1 are explicitly estimated: exact-model LiveBench observations cover 7 of the fixed 41-panel metrics at max effort. Value uses the same current official points tariff.

Codestral 2501: complete within the verified dedicated deployment scope

Verified Codestral-2501 native text chat, fill-in-the-middle, prefix/suffix completion, streaming and sampling through a dedicated code-tool entry.

It is a text/code tool, not a function-tool-capable Codex main or subagent model.
Exact FIM rejects metadata, prompt_cache_key and explicit null sampling/suffix values; HCD rejects them before dispatch rather than silently dropping them.
Native responses and actual token usage are retained. Estimated scores are not derived from this interface acceptance.

Cohere Parse v5: complete within the verified dedicated deployment scope

Verified Cohere Parse v5 dedicated image parsing with text/Markdown, blocks, tables, image regions and coordinates. The public directory labels it preview.

The Parse API accepts images only. PDF is rejected before upload; no hidden rasterization or fallback model is used.
Image regions contain original source pixels from returned boxes, not generated images. This is document parsing, not ordinary chat.

Cohere Rerank v4.0 Pro: complete within the verified dedicated deployment scope

Verified Cohere Rerank v4.0 Pro dedicated multilingual document reranking with structured text, top_n, priority and ranked scores.

Reranking only: chat and coding-agent requests are not admitted, regardless of misleading deployment metadata.
The provider truncates document tails at max_tokens_per_doc; HCD does not rewrite source text and discloses that policy. Estimated scores are separate from capability acceptance.

decision-model-preview: Full structured decisions (verified deployment scope)

Classification, yes/no probabilities and ordinal scoring preserve original probabilities, confidence and input usage; no chat text is generated.

Text, object or array state. HCD:1–16 questions, up to255 choices,2–10 score levels,32768 UTF-8 bytes total. Provider input context:65536 tokens.
Rounded probabilities and sums remain unchanged, without normalization. Confidence is not verified accuracy. Currently limited-time free; normal account/Key authorization, metering and single settlement apply.
No chat, streaming, tools, search, cache, Batch, media or persistent jobs. Maximum context not live-tested (high-cost exemption). Generic fixed-panel estimate:0/41 direct coverage, not decision accuracy; value uses this model own input tariff and decision workload.

DeepSeek V4.1 Flash: complete within the verified dedicated deployment scope

Verified DeepSeek Flash text reasoning, tools, streaming/history/cache, native Chat prefix FIM and image input within the exact deployed scope.

Image files use Key-owned authorization and lifecycle handling; compatibility media URLs require HTTPS. Hosted web/file search, native namespace discovery, encrypted reasoning and native background jobs are not exposed.
Official maximum context/output and large-media bounds use guards and offline checks; expensive extremes are not live-tested (high-cost exemption).
Earlier 74.9/75.3 figures were incomplete-panel estimates, not exact-model acceptance scores. Public composite performance/value scores await exact evidence.
Current exact protocol output bounds:393216 tokens for Chat/Responses and4096 for FIM. Former384000 corrected from exact schema; no extreme live test.

DeepSeek V4 Pro: complete in the verified deployment scope

Verified text, structured output, reasoning, functions/client tool discovery and real Codex continuation; native Chat streaming/Prefix, Messages and FIM.

Hosted web search, image/file input and upstream stored/background state are unsupported; the model profile disables web search.
Performance69.3 and value65.7 are estimates:7 exact0813 public metrics and34 estimates in the fixed41-metric panel.
Maximum context/output/concurrency: not live-tested (high-cost exemption); official limits and offline guards apply.
Current exact protocol output bounds:393216 tokens for Chat/Responses and4096 for FIM. Former384000 corrected from exact schema; no extreme live test.

doubao-deepseek-v4-1-flash: verified deployment scope

Text, image and video; four reasoning levels, JSON Schema, functions, streaming and saved history. Actual Codex tools and continuation verified. Native remote MCP and owned Responses; HCD owned-file and controlled web-search bridges.

Context 1,048,576 tokens; input maximum 1,048,576; default/maximum output 393,216 including thought, within the combined context. Compatibility image limit 1,500; native 3,600; each media item 50 MiB, request 64 MiB. Owned inline files: 5 MiB each, 24-hour retention.
Implicit cache is metered. Explicit cache, native hosted search, Flex, Batch and background generation are closed and rejected. HCD MCP search reserves and bills separately. Actual Work client remains unverified. Performance 77.5/value 76.8 are estimates over 41 metrics, 12 direct model sources, no direct offering benchmark. Expensive boundaries checked offline.

doubao-DeepSeek V4 Flash GA (2026-07-31) — Full integration (verified deployment scope)

Native knowledge search has no authorized resource and is closed. Cache with context edits, unregistered native MCP servers, Batch/background/images are closed and rejected before dispatch.
Default low. Deleting a response does not end cache storage liability before TTL. Performance56.6/value58.8 estimated,0/41 direct; high-cost extremes not live-tested.
Account points/M tokens, standard input/output/cache:821918/2465753/27397; flex:410959/1232877/27397. No extra token cache-write fee. Storage4658 points/M-token/hour; search5480 points/call. Key multiplier and per-item rounding apply separately.

doubao-DeepSeek V4 Pro GA (2026-08-13) — Full integration (verified deployment scope)

Verified text, none/low/high/max, JSON Schema, functions, bounded search, full tool history, MCP, implicit/explicit cache and native response resources. Native knowledge search has no authorized resource and is closed. Cache with context edits, unregistered native MCP servers, Batch/background/images are closed and rejected before dispatch. Flex returned upstream ModelLoading and is not verified or open; rejected before dispatch. Its reviewed rate is reference only. Cache continuation must explicitly stay within the original TTL; cross-model references, context edits and native hosted tools are rejected. Missing reasoning breakdown keeps a funded storage upper bound without posting an estimated charge.

Native knowledge search has no authorized resource and is closed. Cache with context edits, unregistered native MCP servers, Batch/background/images are closed and rejected before dispatch.
Default low. Deleting a response does not end cache storage liability before TTL. Performance59.4/value56.2 estimated,7/41 direct; high-cost extremes not live-tested.
Account points/M tokens, standard input/output/cache:2465753/7397260/82192; flex:1232877/3698630/82192. No extra token cache-write fee. Storage4658 points/M-token/hour; search5480 points/call. Key multiplier and per-item rounding apply separately.
Flex returned upstream ModelLoading and is not verified or open; rejected before dispatch. Its reviewed rate is reference only. Cache continuation must explicitly stay within the original TTL; cross-model references, context edits and native hosted tools are rejected. Missing reasoning breakdown keeps a funded storage upper bound without posting an estimated charge.

FLUX.2 Pro: complete within the verified dedicated deployment scope

Verified FLUX.2 Pro dedicated image generation, editing and up to eight reference images. The public directory currently marks it as planned.

PNG/JPEG output and the model-specific prompt enhancement mapping were checked; tuning fields from another model are explicitly rejected.
Image streaming, transparent output, mask editing and steps/guidance controls are outside this exact interface. Image acceptance is neither a quality score nor a chat-route claim.

Google Gemini 3.8 Flash-100: fully reviewed deployed scope

Native GenerateContent, Chat and Interactions support text, image, audio, video and PDF input, thinking, JSON, functions, streaming and continuation. Codex uses the HCD Responses bridge.

Knowledge Studio adds isolated Python (NumPy, SymPy and Matplotlib), URL reading, video-frame inspection and controlled web search. These are HCD bridges; native hosted code, search and AGENTIC video loops are not enabled. Computer use returns proposed actions only.
Combined context: 1,048,576 tokens; no disclosed independent input maximum. Default and maximum output: 65,536 tokens including thinking, subject to remaining context. Explicit cache read/delete/expiry and owned HCD files, background responses and Batch preserve original results. Batch uses standard call prices.
Per million tokens: input 3,000,000 points, cache hits 300,000 and output including thinking 15,000,000. Explicit cache creation uses the input rate; storage costs 2,000,000 points per million token-hours. Supplier promotional credits have not been received and do not promise customer refunds. Performance 76.6 and value 66.1 are estimates: 12 model-wide public metrics and 29 estimated metrics, with no direct performance measurement for this offering. Expensive limits were checked offline.
Work Responses live web search uses an HCD controlled bridge. In auto mode the model decides whether to search, at most once per response; model and search usage are metered separately from original receipts. Authenticated actual Work client and search roundtrip verification remains pending.
Gemini 3.8 Flash-100 supports HCD summary views: auto keeps the provider automatic summary; detailed shows the full available provider summary; concise explicitly shows an HCD bounded extract and truncation status; none hides the public summary. These views do not control provider summary length or add model calls. Thinking tokens retain original receipt billing. Actual remote Work roundtrip verification is pending.

Gemini 3.8 Live-100 · Current deployment fully integrated

Realtime audio/video, camera/images, prebuilt Avatar, function follow-ups, native resume, interruption and bounded web search.

Custom Avatar is unavailable on this deployment and rejected before provider contact. The user explicitly deferred and exempted it from full certification; no application was submitted.
Search and automatic VAD use bounded HCD bridges; provider-native search is not exposed.
Google supplier rates per1M tokens: TEXT/IMAGE-VIDEO/AUDIO input0.75/1/3USD; TEXT/AUDIO/VIDEO output4.5/12/1USD. Thinking uses text-output rates; transcription and retained history remain in original meters. Search has a separate quote.
Performance77.2 and value84.0 are estimates; direct panel coverage0/41. Audio/Avatar quality not benchmarked. Extreme contexts/media: not live-tested (high-cost exemption).

Google Gemini 4 Argon: verified deployed capabilities

Text, image, audio, video and PDF input; three reasoning levels, JSON, function tools and streaming. Codex tools and continuation are verified. HCD knowledge tools provide isolated Python, URL reading, video-frame inspection and separately billed controlled search. Responses builtin web_search uses the bounded HCD compatibility bridge; actual Work client verification remains pending. Preview search and unmapped explicit controls are rejected.

Combined context is 1,048,576 tokens; the independent input limit is not disclosed. Native GenerateContent defaults to and permits 1,048,576 total output tokens through manual owner-bound continuationToken requests; each segment permits 32,768 non-streaming or 65,536 streaming tokens. Responses, Chat and Interactions default and maximum per-call outputs are 32,768 non-streaming / 65,536 streaming, including reasoning within combined context. Explicit cache is unsupported; implicit cache is metered. Owned HCD files, background responses and Batch retain lifecycle controls; Batch uses standard call prices.
Per million tokens: 8,000,000 input points, 400,000 cache-hit points and 40,000,000 output/reasoning points. Full input, output and tool liabilities are reserved against both account and Key before submission; each explicit continuation is separately reserved and settled. Performance 77.2 and value 62.5 are estimates: 6 model-wide public metrics plus 35 estimates in a fixed 41-metric panel, with no direct offering performance measurement. Expensive boundaries were checked offline. Supplier promotional credits are not treated as received.

Gemini Nano Banana 2.1-100: Complete within verified deployment scope

Complete verified image-studio scope; HCD bounds are distinct from manufacturer maxima.

Image generation/editing, streaming and private-reference continuation; 1K/2K/4K, 15 aspect ratios, minimal/medium/high, up to32768 output tokens and native system instructions. One PNG/JPEG result per request.
Up to14 PNG/JPEG/WebP/HEIC/HEIF references:7MiB each,40MiB combined media,64MiB complete request/history. One PDF/UTF8 file up to8MiB/30 PDF pages, or one silent MP4/WebM up to16MiB/60s with crop and fps(0,24].
HCD controlled webpage/source-image search with sources, not Google native search or an image index. The cumulative50 CNY platform risk allowance uses conservative metered supplier upper bounds:30 CNY held per request, concurrency1; new search may stop before actual spending reaches50 CNY. It is not customer credit, free usage or an upstream bill cap.
Search and image components settle once from their original receipts. A successful search may remain charged when later image processing fails. Submitted jobs and result reading continue after the risk stop; ordinary generation/editing works independently.
HCD durable batches support create, disconnect, undispatched restart, status, cancellation and results.1..2 sequential items only:1K/1:1/minimal ormedium/max4096 output/one PNG-JPEG reference/no search. Standard realtime per-item rates apply, without Google native Batch discounts.
Native countTokens is advisory, not generation billing or the sole reservation bound. Input, implicit cache reads, text/thought output and image output are metered separately. Explicit cache/file URI/YouTube/native Batch storage are unavailable; upstream audio/function calling/structured output are unsupported. Original image bytes and provider provenance are preserved.
4K and maximum context/output/14-reference extremes: not live-tested (high-cost exemption); exact model evidence and offline resource boundaries verified. Performance92.5 comes from two public image benchmarks; value66.5 is estimated from standard prices, not route performance testing.

GPT-5.6 Luna: complete within the verified safe deployment scope

The exact model is integrated across its verified safe deployment scope. Expensive limits and unpriced optional hosted features retain explicit restrictions.

Text and image input with text output; reasoning supports none, low, medium, high, xhigh and max, with medium as the default. Structured output, functions, real Codex default tools and a saved-history second turn were verified.
Raw streams and cache metering, background completion after disconnect, owned GET, replay and DELETE were accepted. WebSocket supports a verified two-response response.create chain; mid-response steering is unavailable for this model.
A small valid image was tested for transport, meaning and metering. Bounded images reserve the full documented image-token ceiling. Unknown media and files retain strict liability bounds and may be rejected before dispatch when funds are insufficient.
The long-context tier starts above 272,000 total input tokens, including cache, and prices the whole request. Account and Key calculations for input, cache reads, cache writes and output were checked offline across the boundary. Maximum context/output, live threshold crossing and large media are not live-tested (high-cost exemption).
Pro, multi-agent work, arbitrary remote MCP, indexed search, containers, hosted tools and image generation remain closed where price or lifecycle bounds are unverified. Parameters are not silently discarded. Model audio/video input and direct non-text output are unsupported.
Current performance 64.2 and value 65.8 derive from public evaluations and coherent pricing, not an HCD live quality score.

GPT-5.6 Sol: complete within the verified safe deployment scope

Completion covers the exact model and verified safe deployment. Optional hosted capabilities and expensive boundaries retain explicit limits. Reservations, settled charges and unresolved liability stay separate.

Text and image input with text output; reasoning supports none, low, medium, high, xhigh and max, with medium as the default. Structured output, native Chat functions with explicit none, Responses functions, real Codex default tools and two-turn saved history were verified.
Raw streams, cache writes and reads, background completion after delivery disconnect, owned GET, stream replay and DELETE were accepted. WebSocket scope is text, low/default, 64 output tokens, one ordinary response.create continuation and two responses. This model does not support response.steer. The connector continues to use HTTP/SSE.
A small valid image was tested for transport, meaning and metering. Bounded images reserve the full documented image-token ceiling. Unknown media and files retain strict full-context liability or are rejected before provider contact when funds are insufficient.
The long-context tier starts above 272,000 total input tokens, including cache, and applies to the whole request across input, cache reads, cache writes and output. Account and Key math was checked offline on both sides of the threshold. Maximum context/output, live threshold crossing and large media are not live-tested (high-cost exemption).
Pro, multi-agent, arbitrary remote MCP, indexed file search, containers, hosted Shell/Skills, hosted image generation and unverified sampling parameters remain closed; no parameter is silently discarded. Model audio/video input and direct non-text output are unsupported.
Existing performance 88.2 and value 70.5 use public evaluation evidence and coherent reviewed pricing, not HCD live quality scores.

GPT-5.6 Terra: complete within the verified safe deployment scope

The exact model is integrated across its verified safe deployment scope. Expensive limits and unpriced optional hosted features retain explicit restrictions.

Text and image input with text output; reasoning supports none, low, medium, high, xhigh and max, with medium as the default. Structured output, functions, real Codex default tools and a saved-history second turn were verified.
Raw streams and cache metering, background completion after disconnect, owned GET, replay and DELETE were accepted. WebSocket supports a verified two-response response.create chain; mid-response steering remains closed pending exact-model verification.
A small valid image was tested for transport, meaning and metering. Bounded images reserve the full documented image-token ceiling. Unknown media and files retain strict liability bounds and may be rejected before dispatch when funds are insufficient.
The long-context tier starts above 272,000 total input tokens, including cache, and prices the whole request. Account and Key calculations for input, cache reads, cache writes and output were checked offline across the boundary. Maximum context/output, live threshold crossing and large media are not live-tested (high-cost exemption).
Pro, multi-agent work, arbitrary remote MCP, indexed search, containers, hosted tools and image generation remain closed where price or lifecycle bounds are unverified. Parameters are not silently discarded. Model audio/video input and direct non-text output are unsupported.
Current performance 73.8 and value 62.9 derive from public evaluations and coherent pricing, not an HCD live quality score.

GPT-6 Astra: complete within the verified, safely available deployment scope

Completion covers the verified deployment scope, not every optional hosted capability. Known prices and provable quantity bounds govern availability. Holds and settled charges remain separate; authorization and budget gates remain active.

Verified text, low/medium/high/xhigh/max reasoning, structured output, Responses functions/namespaces/parallel and async tools, tool search, client computer/patch protocols, streaming, saved and encrypted history, cache, compaction and background resource lifecycle. Actual Codex default tools and saved-history continuation were independently tested.
PNG and bounded simple single-frame WebP/non-animated GIF were verified. The latter use low detail, dimensions up to 512 pixels and files up to 1 MiB. JPEG transport and metering passed, but a red fixture was described as Purple; that semantic case failed. Unknown media and remote URLs retain strict holds or rejection.
WebSocket scope is text, low reasoning, 64 output tokens, one queued steer and an automatic second response. The original response completes normally; immediate interruption and unverified tool/history combinations are not enabled.
The deployment rejects temperature on native Responses, and logit_bias/function tools on native Chat. Local guards remain. Other sampling controls and max_tokens are not verified; use max_completion_tokens for Chat and max_output_tokens for Responses.
file_search index size and retention bounds remain unresolved. Code Interpreter/container pricing has conflicting minute versus Session units. Pro/multi_agent aggregate quantities and costs lack proven bounds. These features remain restricted or disabled.
Hosted remote MCP was tested only with an owned fixed HTTPS echo, same-Key/project approval and two metered responses. Its temporary entry is closed. Arbitrary remote servers, variable results, credentials and broader lifecycle are not enabled; local MCP tests are not substitutes.
Batch, Flex and Fast/Priority are not offered by this deployment. Audio/video input and direct media output are outside its verified scope. Unavailable hosted image generation, Shell/Skills and other optional tools remain gated.
The 272,000-token tier uses total input including cache. An actual 272,022-input-token long-tier receipt was verified. Maximum context/output and other expensive boundaries retain offline checks and explicit high-cost live-test exemptions, not claims of maximum-size live generation.

GPT-6 Luna: complete within the verified, safely available deployment scope

Completion covers the verified safe deployment. Optional upstream features remain limited where bounds are unproved. Reservation and settlement stay separate, with exact-model authorization and cost gates.

Verified text, default medium and none/max, structured output, original streams, Chat functions with none, Responses async functions, a small image semantic case, actual Codex default tools and in-memory MCP across two turns, cache usage, background disconnect/completion/retrieve/stream replay/delete, and bounded WebSocket steering with two responses.
Reasoning choices are none, low, medium, high, xhigh and max, with medium as default. Chat functions require explicit none; max uses Responses.
WebSocket is limited to native text, low reasoning, default tier, 64 output tokens, one queued steer and two responses. The connector uses HTTP/SSE.
Maximum context/output, long-context threshold, large media and high-output compaction use official limits and offline checks: not live-tested (high-cost exemption). A small image was tested, but unknown media retains full-context reservation; no low-cost image bound is claimed.
Pro, multi-agent, automatic compaction, arbitrary remote MCP, indexed file search, containers and hosted Shell/Skills stay restricted where safe cost or lifecycle bounds are unproved. Model audio/video input and direct non-text model output are unsupported. Unverified sampling parameters are explicitly rejected.
Some exact-model public benchmarks exist, but the fixed 41-cell scoring panel has not passed a like-for-like review. Composite performance and value scores remain pending; no other model's estimate is reused.

GPT-6 Sol: complete within the verified, safely available deployment scope

Completion covers the verified safe deployment, not all optional official capabilities. Reservation bounds and actual settlement remain separate; exact-model authorization and cost gates remain active.

Verified text, default medium and none/max parameters, structured output, original streams, Chat function calling with none, Responses async functions, actual Codex default tools and in-memory MCP with two persisted turns, cache usage, and background disconnect/completion/replay/retrieve/delete.
Reasoning choices are none, low, medium, high, xhigh and max, with medium as the model default. Chat functions require explicit none; max uses Responses.
WebSocket availability is native text with low reasoning, default tier, 64 output tokens, one queued steer and two responses. The connector continues to use HTTP/SSE.
Maximum context/output, long-context thresholds, large media and high-output compaction use exact official limits and offline boundary checks: not live-tested (high-cost exemption). Unknown media retains full-context reservation; no low-cost or live image-understanding claim is made.
Conflicting official sampling descriptions remains unresolved, so those parameters are rejected. Pro, multi-agent, automatic compaction, arbitrary remote MCP, indexed file search, containers and hosted Shell/Skills remain restricted where safe cost or lifecycle bounds are unproved. Model audio/video inputs and direct non-text model outputs are unsupported.
Composite performance and value scores are marked estimated: 13 of 41 panel cells have exact-model public observations and 28 use same-metric peer estimates. These are not HCD deployment tests. Value uses reviewed public account-point rates, not actual charges. Rankings against GPT-5.6 Sol and other models apply only to this fixed panel; overlapping estimate ranges do not establish general capability order. Image semantics and dedicated tool-search/computer/apply-patch semantic cases were not separately live-tested.

GPT-6.1 Sol: complete within the verified deployment scope

The exact model is integrated across its currently verified scope. Expensive boundaries and unpriced hosted capabilities retain explicit restrictions.

Text and image input, text output. Five reasoning efforts: low, medium, high, xhigh and max; medium is default. none/minimal and native Chat tool calling are unsupported; use Responses for tools.
Strict structured output, functions and async options, streams and cache metering, real Codex default tools, an in-memory MCP round trip and a persisted second turn were verified.
Background completion after delivery disconnect, owned GET, stream replay and DELETE were verified. Narrow WebSocket allows one ordinary response.create continuation; steer remains pending and closed. Codex uses HTTP/SSE.
Points use the user-approved exact-model official tariff as an estimate. Supplier formal rates remain unconfirmed. Estimated pricing is used for reservation and account/Key service settlement, not confirmed supplier charges.
The whole request switches to long-context pricing above 272,000 total input tokens including cache. Maximum context/output, threshold crossing and large media are not live-tested (high-cost exemption); official limits and offline boundaries apply.
Unknown media/files retain full-context liability bounds and are rejected before dispatch when budgets are insufficient. Unpriced Pro, multi-agent, automatic compaction and hosted resources stay closed. Performance and value await exact numerical evidence.

GPT Audio: complete within the verified dedicated deployment scope

Verified dedicated audio inference with text/audio input and text/audio output, streaming and function calls. The public directory currently marks this entry as planned; access depends on the actual entry permissions.

This is acceptance of the exact audio interface, not a general Codex conversation-model claim. Image I/O, realtime sockets, structured-output schemas and discounted prompt cache are outside the verified scope.
Signed input limits bound resources; unsupported parameters are rejected before submission. Capability acceptance is not a quality benchmark, and directory scores retain their stated evidence grade.

GPT Audio 1.5: complete within the verified dedicated deployment scope

Verified GPT Audio 1.5 dedicated audio inference: text/audio input and text/audio output, streaming and function calls. The public directory currently marks it as planned.

Acceptance covers this exact audio interface; it does not activate a general Codex chat route. Images, realtime sockets, structured-output schemas and discounted cache pricing are outside scope.
Signed input contracts bound resources and reject unsupported parameters before submission. Directory scores are separate from this capability acceptance.

GPT Audio Mini: complete within the verified dedicated deployment scope

Verified GPT Audio Mini dedicated text/audio I/O, streaming and function calls. The public directory currently marks it as planned.

This is not a general Codex chat integration. Image I/O, realtime sockets and structured-output schemas are outside scope.
Cache hints and native usage reporting were verified, but live calls reported zero cached tokens; no actual hit or discount was proven. Unpublished discounted rates are not guessed.
Functional acceptance is not a quality benchmark; estimated directory scores remain estimates.

GPT Live Transcribe: complete within the verified dedicated deployment scope

Verified dedicated live audio transcription with context hints and streaming. The public directory currently marks it as planned.

This is a transcription entry, not general chat, function tools, a file-transcription endpoint or audio generation.
Signed contracts bound inputs and reject unsupported fields; capability acceptance is not a transcription-quality score.

GPT Realtime: complete within the verified dedicated deployment scope

Verified dedicated realtime text/audio/image input, text/audio output, streaming, functions and prompt caching. The public directory currently marks it as planned.

The entry uses HCD browser audio transport and a WebSocket proxy; it does not establish full WebSocket support for ordinary Codex chat clients.
Generated image/video output, structured-output schemas, reasoning-effort control, external SIP and hosted remote MCP are not offered. Functional acceptance is not a quality score.

GPT Realtime 1.5: complete within the verified dedicated deployment scope

Verified GPT Realtime 1.5 dedicated realtime text/audio/image input, text/audio output, streaming, functions and caching. The public directory currently marks it as planned.

Acceptance covers browser audio transport and its WebSocket proxy, not full WebSocket capability in general Codex clients.
Generated image/video output, structured-output schemas, reasoning-effort control, external SIP and hosted remote MCP are unavailable; directory scores are separate from this acceptance.

GPT Realtime Mini: complete within the verified dedicated deployment scope

Verified GPT Realtime Mini dedicated realtime text/audio/image input, text/audio output, streaming, functions and caching. The public directory currently marks it as planned.

Scope is browser audio transport and its WebSocket proxy, not full WebSocket support for ordinary Codex clients.
Generated image/video output, structured-output schemas, reasoning-effort control, external SIP and hosted remote MCP are unavailable. Capability acceptance and estimated scores are separate.

Grok 4.7 — Full verified deployment scope

Native Chat, automatic-reasoning Responses and a four-effort Codex Chat bridge support text/images, JSON, tools and saved-thread history.

low, medium, high and xhigh passed live; high is the default and none is unsupported. Codex uses the Chat bridge; native Responses uses automatic reasoning.
Output includes reasoning tokens. Input including cache reads above200000 tokens applies the2x long-context tariff to the whole request. Cache hints are explicitly not forwarded; cache hits are not promised.
Actual full Codex tools, MCP echo and saved-thread continuation passed. Performance70.3 and value61.4 are estimates with0/41 direct coverage. Expensive context/media limits were not live-tested.
No provider-hosted Web/X/code tools or encrypted state claimed for this deployment. Google-100 has its own reviewed scope and prices.
xAI states No text output limit: no separate text-output cap. The500000 combined context still applies; HCD uses a finite supported ceiling and upstream actual-token handling, never reduces the default using fee estimates or claims a second independent500000 output budget.

Google Grok 4.7-100 — Fully reviewed deployed scope

Native Responses and Chat: text/images, four reasoning levels, JSON, complete tools and encrypted continuation.

low, medium, high and xhigh reviewed; high is the default and reasoning cannot be disabled. Adjustable native Google Responses was live verified.
Actual connector-generated Codex configuration, complete tools, MCP echo and same saved-thread continuation passed. Encrypted reasoning was replayed unchanged; cache keys and real cache hits were verified.
Performance70.3 and value61.4 are estimates, direct coverage0/41. Expensive context/media extremes were checked offline. Provider-hosted Web/X/code tools, Batch, upstream files, reasoning summaries and cache retention are not exposed.
Combined context524288 tokens; independent output maximum not disclosed. HCD context_bound support and default are constrained by remaining context, not a published independent output maximum.

MAI Thinking 1: complete within the verified dedicated deployment scope

Verified MAI Thinking 1 native text reasoning, function tools, history continuation, streaming/nonstreaming and token usage for a dedicated text-tool conversation.

The Responses bridge validates a complete result before replay; incremental Responses delivery is not implemented. Native API streaming preserves original events.
The directory labels it preview. Client support follows the verified entry and does not imply that every Codex function is exposed.

Mistral Medium 3.5: complete within the verified dedicated deployment scope

Verified Mistral Medium 3.5 native text/image input, text chat, JSON objects, streaming, multiple candidates and sampling through a dedicated text/code-tool entry.

The exact hosted offering does not advertise tool calling; HCD rejects tool fields before generation and does not present it as an ordinary Codex tool agent.
Explicit temperature=null or top_p=null is rejected locally after upstream rejection; omission uses defaults. The directory labels it preview, and estimated scores are separate.

Mistral OCR 4: complete within the verified dedicated deployment scope

Verified Mistral OCR 4.0 dedicated image/PDF recognition, text/table/image extraction, layout, page selection and multilingual OCR. This is a document entry, not a chat model.

The exact deployment accepts token, word and page confidence granularity; upstream rejects block granularity with 422, so it is rejected before submission.
The public directory labels it preview. Capability acceptance and performance/value score evidence remain separate.

通用多模态向量: complete within the verified dedicated deployment scope

Verified Multimodal Embedding v1 dedicated independent text, image and video vectors with ordered mixed batches. The public directory currently marks it as planned.

At most 20 inputs per batch, each producing a fixed 1024-dimensional vector. The provider processes at most 512 tokens per text item and truncates longer text; HCD preserves the submitted text and discloses this behavior.
Dense output, image URL/local input and relevant parameter forwarding are supported. No measured retrieval gain, modality fusion, variable dimensions, streaming or async Batch is claimed.
Performance 62.3 and value 48.1 remain low-confidence estimates, not direct exact-model evaluation. Media reservations and settled charges are separate.

qwen-DeepSeek-V4-Flash-0731：Verified integration (currently open scope)

Full integration within the verified open deployment scope: text, none/low/high/max, structured output, functions, complete default Codex tools, pure in-memory MCP, explicit saved-thread continuation and implicit cache. Hosted search/extraction/interpreter and native storage/response-ID/conversation/background are closed and explicitly rejected before provider dispatch.

Closed because aggregate agent iteration/charge bounds are unverified. max_output_tokens limits reply only; undocumented max_tool_calls is not a hard cap. The separate393216 reasoning-token maximum is reserved; high-cost extremes are not live-tested.
Original search receipts and historical charges are preserved; hosted search is currently closed. Own prices and scores unchanged.
Current official reply/reasoning total shares393216; reservation uses that shared ceiling, preserving separate raw usage and once-only settlement.

qwen-DeepSeek-V4-Pro · Verified open deployment scope

Full integration within the verified open deployment scope: text, none/high/max, structured output, functions, complete default Codex tools, pure in-memory MCP, explicit saved-thread continuation and implicit cache. Hosted search/extraction/interpreter and native storage/response-ID/conversation/background are closed and explicitly rejected before provider dispatch.

Performance 61.3, value 56.9: estimated fixed panel with 7 model-wide public observations and 34 estimates. Own standard tariff 3287671/6575342/cache273973 points per million tokens; no peak/off-peak tariff. Provider alias has no declared immutable snapshot. Separate Responses thinking reservation uses a conservative deployed output upper bound; expensive limits not live-tested. Supplier invoice cash remains unknown.
Current official reply/reasoning total shares393216; reservation uses that shared ceiling, preserving separate raw usage and once-only settlement.

qwen-DeepSeek-V4-Pro-0813 · Verified open deployment scope

Closed because aggregate agent iteration/charge bounds are unverified. max_output_tokens limits reply only; undocumented max_tool_calls is not a hard cap. The separate393216 reasoning-token maximum is reserved; high-cost extremes are not live-tested.
Performance71.7/value67.7 estimated;7 exact public model metrics and34 estimates in41 fixed panel. Value uses this offering's reviewed off-peak base workload; cache separate. Off-peak22:00–08:00 UTC+8; peak token rates x2. Supplier invoice cash unknown.
Current official reply/reasoning total shares393216; reservation uses that shared ceiling, preserving separate raw usage and once-only settlement.

Qwen-Image-2.1-Pro：complete within the verified deployment scope

Image-studio-only model; completion covers verified generation, editing, parameters, metering and native task lifecycle.

Unified generation/editing, up to10 reference images and1–6 outputs; transparent images, seed, prompt enhancement, Direct/Agent, enable_thinking and watermark. Agent is generation-only.
Static PNG/JPEG/WebP/BMP/TIFF/GIF inputs; native PNG output, with HCD JPEG/WebP conversion. Masks guide reference editing; HCD completion events are not native partial-image streaming.
Native async tasks return result_ref and continue after client disconnect. Original usage settles once; same-Key original-result reads are free. Provider results expire after24 hours; save returned images.
HCD bounds:18,000 prompt characters,10MB per image,64MiB aggregate,40M input pixels,8000-pixel sides and10:1 input ratio. Output area512²–2048² and ratio1:8–8:1. Six-output/ten-reference extremes use offline checks and high-cost live exemptions.
No ordinary Chat, function tools, web search, context cache or native Batch inference. Performance is a same-family public-data estimate, separate from functional acceptance.

Qwen3-VL-Rerank: complete within the verified dedicated deployment scope

Verified Qwen3 VL Rerank synchronous text, image, video and mixed-input reranking. The public directory currently marks it as planned.

Image queries, top_n, instructions, returned documents and native responses are supported. Video fps is strictly 0 < fps <= 1; exact deployment rejects zero and HCD rejects it before provider dispatch.
Official 4,000 query and 8,000 per-item token descriptions conflict. Exact limits remain upstream-enforced pending clarification; no invented truncation is applied.
493154 points per million tokens for video-containing requests is an approved liability estimate, not a published supplier tariff or verified supplier cost. This synchronous entry has no streaming, Batch or file jobs.

千问3.7-通用文本重排序: complete within the verified dedicated deployment scope

Verified Qwen3.7 Text Rerank synchronous text reranking, instructions, top_n, all results and large candidate sets. The public directory currently marks it as planned.

Each document is limited to 50,000 characters; over-limit input is rejected before submission without truncation.
This dedicated reranking entry has no image/video, streaming, hosted tools, uploaded files or async jobs. Parameters from other models are not substituted. Estimated scores are not quality results from this acceptance.

現在の境界

現在の提供範囲

Google 以外の32モデルを追加：テキスト27、Mistral Document AI、埋め込み3、Sora 2。接続ツール1.0.86.0に更新し、各プラグインとAPIキー権限を有効にしてください。テキストAPIは34モデル、Codexメニューはツール対応32モデルです。PhiとLlamaはAPIでの質問用です。文書は30 MB・30ページまで。ナレッジは選択したローカル文書から引用付きで検索し、索引を再利用します。動画は4/8/12秒・720p、参照画像と完成動画のリミックスに対応。動画は早めに保存してください。完了した利用分を課金し、ローカルキャッシュの読み取りは無料です。Googleとmodel-routerは対象外です。設備ID、プロトコル、運転データ、エージェント、制御は、顧客が許可したローカル、エッジ、またはプライベート環境に置きます。公開サイトはサービス紹介のみで、クラウド設備制御基盤ではありません。

プロジェクト相談ログイン