コンテンツへスキップ
アルファ版
  • モデル
  • ランキング
  • Ori
営業担当に相談

フッター

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

製品

  • チャット
  • ランキング
  • ベンチマーク
  • アプリ
  • 見つける
  • モデル
  • Ori
  • コレクション
  • プロバイダー
  • ツール
  • 料金
  • Business
  • Enterprise
  • ラボ

会社情報

  • 概要
  • ブログ
  • お客様
  • 採用情報
    採用情報
  • プライバシー
  • 利用規約
  • トラストセンター
  • サポート
  • OR 対応
  • データ
  • ブランド

開発者

  • ドキュメント
  • API リファレンス
  • 開発者プラットフォーム
  • ステータス
  • AI サイトマップ

接続

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
anthropic のファビコン

Anthropic: Claude Opus 4.5

anthropic/claude-opus-4.5

比較

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection. The model is designed to operate efficiently across varied effort levels, enabling developers to trade off speed, depth, and token usage depending on task requirements. It comes with a new parameter to control token efficiency, which can be accessed using the OpenRouter Verbosity parameter with low, medium, or high.

Opus 4.5 supports advanced tool use, extended context management, and coordinated multi-agent setups, making it well-suited for autonomous research, debugging, multi-step planning, and spreadsheet/browser manipulation. It delivers substantial gains in structured reasoning, execution reliability, and alignment compared to prior Opus generations, while reducing token overhead and improving performance on long-running tasks.

モダリティ
入力 / 出力料金
$5 / $251M あたり
コンテキスト
200K
公開日
2025年11月24日
比較
プロバイダー料金パフォーマンス稼働率ベンチマークアプリアクティビティよくある質問探索

プロバイダー

同じモデルを複数の企業がホストしています。OpenRouter は、選択したルーティングモード（Balanced（価格と速度）、Nitro（最速）、Floor（最安））に基づいて、そのうちの一社にリクエストをルーティングします。

料金

プロバイダーが提示する価格と並べて、このモデルに対して顧客が実際に支払う平均価格を表示しています。キャッシュと割引により、実際の支払価格は表示価格を大幅に下回ることがよくあります。

パフォーマンス

スループットはモデルが出力する速さです（毎秒のトークン数で、数値が高いほど優れています）。レイテンシは往復にかかる合計時間です（短いほど優れています）。TTFT は最初のトークンが出力されるまでの時間、つまり何かが表示され始めるまでの時間です（短いほど優れています）。

稼働率

稼働率は、過去 3 日間に少なくとも一社のプロバイダーがリクエストに応答していた時間の割合です。可用性は、推論が正常に提供された時間の割合です。OpenRouter は継続的に監視し、プロバイダーがエラーを返すと、次に最適なプロバイダーを使用します。

ベンチマーク

標準化された評価のスコアと、共通のベンチマークプロンプトに対するこのモデル自身の出力です。パーセンテージが高いほど優れており、各順位は、その情報源で評価されたモデルの中でのこのモデルの位置を示します。

ベンチマークスコアの概要： Anthropic: Claude Opus 4.5 （Artificial Analysis、Design Arena、Vals AI）
出典ベンチマークスコア
Artificial AnalysisClaude Opus 4.5 (Reasoning) GPQA Diamond86.6%
Artificial AnalysisClaude Opus 4.5 (Reasoning) HLE30.1%
Artificial AnalysisClaude Opus 4.5 (Reasoning) IFBench58.0%
Artificial AnalysisClaude Opus 4.5 (Reasoning) τ²-Bench Telecom89.5%
Artificial AnalysisClaude Opus 4.5 (Reasoning) AA-LCR77.3%
Artificial AnalysisClaude Opus 4.5 (Reasoning) CritPt4.6%
Artificial AnalysisClaude Opus 4.5 (Reasoning) LiveCodeBench87.1%
Artificial AnalysisClaude Opus 4.5 (Reasoning) Terminal-Bench Hard47.0%
Artificial AnalysisClaude Opus 4.5 (Reasoning) MMLU-Pro89.5%
Artificial AnalysisClaude Opus 4.5 (Reasoning) AIME 202591.3%
Artificial AnalysisClaude Opus 4.5 (Non-reasoning) GPQA Diamond81.0%
Artificial AnalysisClaude Opus 4.5 (Non-reasoning) HLE13.2%
Artificial AnalysisClaude Opus 4.5 (Non-reasoning) IFBench43.0%
Artificial AnalysisClaude Opus 4.5 (Non-reasoning) τ²-Bench Telecom86.3%
Artificial AnalysisClaude Opus 4.5 (Non-reasoning) AA-LCR70.7%
Artificial AnalysisClaude Opus 4.5 (Non-reasoning) CritPt0.3%
Artificial AnalysisClaude Opus 4.5 (Non-reasoning) LiveCodeBench73.8%
Artificial AnalysisClaude Opus 4.5 (Non-reasoning) Terminal-Bench Hard40.9%
Artificial AnalysisClaude Opus 4.5 (Non-reasoning) MMLU-Pro88.9%
Artificial AnalysisClaude Opus 4.5 (Non-reasoning) AIME 202562.7%
Design ArenaClaude Opus 4.5 Models Arena 3D Elo1211
Design ArenaClaude Opus 4.5 Models Arena Asciiart Elo1187
Design ArenaClaude Opus 4.5 Models Arena Code Categories Elo1240
Design ArenaClaude Opus 4.5 Models Arena Data Visualization Elo1243
Design ArenaClaude Opus 4.5 Models Arena Game Development Elo1229
Design ArenaClaude Opus 4.5 Models Arena SVG Elo1177
Design ArenaClaude Opus 4.5 Models Arena UI Component Elo1233
Design ArenaClaude Opus 4.5 Models Arena Website Elo1245
Design ArenaClaude Opus 4.5 Agents Arena Androidnative Elo1172
Design ArenaClaude Opus 4.5 Agents Arena Full Stack Elo1156
Design ArenaClaude Opus 4.5 Agents Arena Mobile Apps Elo1189
Design ArenaClaude Opus 4.5 Agents Arena Webapps Elo1144
Vals AIClaude Opus 4.5 (Nonthinking) AIME76.9%
Vals AIClaude Opus 4.5 (Nonthinking) CorpFin v261.3%
Vals AIClaude Opus 4.5 (Nonthinking) Finance Agent v154.5%
Vals AIClaude Opus 4.5 (Nonthinking) GPQA Diamond79.5%
Vals AIClaude Opus 4.5 (Nonthinking) IOI v123.6%
Vals AIClaude Opus 4.5 (Nonthinking) LiveCodeBench75.0%
Vals AIClaude Opus 4.5 (Nonthinking) LegalBench82.8%
Vals AIClaude Opus 4.5 (Nonthinking) MedCode45.2%
Vals AIClaude Opus 4.5 (Nonthinking) MedQA93.2%
Vals AIClaude Opus 4.5 (Nonthinking) MedScribe83.2%
Vals AIClaude Opus 4.5 (Nonthinking) MGSM94.8%
Vals AIClaude Opus 4.5 (Nonthinking) MMLU Pro85.6%
Vals AIClaude Opus 4.5 (Nonthinking) MMMU Pro81.1%
Vals AIClaude Opus 4.5 (Nonthinking) MortgageTax68.7%
Vals AIClaude Opus 4.5 (Nonthinking) Vals RSI Index14.8%
Vals AIClaude Opus 4.5 (Nonthinking) SAGE v145.0%
Vals AIClaude Opus 4.5 (Nonthinking) TaxEval v274.3%
Vals AIClaude Opus 4.5 (Nonthinking) Terminal-Bench 2.058.4%

アプリ

このモデルに最も多くのトラフィックを送信している公開アプリです。実際の本番ワークロードを把握するための有力な指標であり、このモデルに最も適したユースケースを知る手がかりにもなります。

アクティビティ

このモデルのトークン量とリクエストトラフィックの経時変化です。

API

このモデルを呼び出すために、そのまま使えるコードです。OpenRouter の API は OpenAI 互換のため、ほとんどの SDK はベース URL を変更するだけで動作します。モデル間で変わるのは、下記のモデルスラッグだけです。

EU 域内ルーティング経由で利用可能

Anthropic: Claude Opus 4.5 は EU 域内ルーティングで利用できます。eu.openrouter.ai に送信されたリクエストは EU 内で復号され、ヨーロッパ（EU/EEA、英国、スイス）にあるプロバイダーの共有エンドポイントにのみルーティングされます。

ヨーロッパのプロバイダー
Amazon Bedrock
ヨーロッパでの料金
  • Amazon Bedrock：入力 $5.50/M tokens、出力 $27.50/M tokens
ベース URL
https://eu.openrouter.ai/api/v1
プラン
Business または Enterprise が必要です。Business ではセルフサービスで利用でき、契約も月額最低利用額もありません。 EU 域内ルーティング向け OpenRouter Business

フェイルクローズ方式で動作し、ヨーロッパの共有プロバイダーエンドポイントが利用できない場合、リクエストはリージョン外に送信されずにエラーになります。自身の BYOK キーで処理されるリクエストは、自身で管理するデプロイのリージョンに送信されます。 リージョン内ルーティングのドキュメント

さらにモデルを探す

視覚機能を備えた AI モデル：画像理解のためのマルチモーダル LLMコレクションAI モデルランキングランキング
レイテンシ / スループット
$5.00$25.00$0.502.07s45 tps
100.00%
$5.00$25.00$0.50----
--
$5.00$25.00$0.501.40s51 tps
--
$5.00$25.00$0.501.66s40 tps
100.00%
$5.00$25.00$0.501.14s44 tps
100.00%
Standard ルーティングでは使用されません：これらのエンドポイントが使用されない理由
$5.50$27.50$0.55----
100.00%
スループット
51トークン/秒

P50、プロバイダー全体での最良値

レイテンシ
1.14秒

P50、最適なプロバイダー

AutoExacto ベンチマーク
GPQA DiamondTAU-BenchClaude Platform on AWS86.7%76.3%Anthropic86.5%76.3%Amazon Bedrock (EU)86.6%75.5%Google Vertex85.7%76.1%auto-routing86.8%74.8%Amazon Bedrock85.8%75.8%
+1 社のプロバイダー
稼働率（3 日間）モデルに接続できました。リクエストはプロバイダーにルーティングされました。
100.00%
可用性（3 日間）モデルがいずれかのプロバイダーから推論結果を返しました。エラーと空のレスポンスはマイナスとして集計されます。
99.42%

過去 3 日間の可用性

過去 72 時間
可用性 99.42%
3 日前2 日前昨日現在

過去 24 時間の可用性

OpenRouter Availability
99.46%
Without Routing
99.17%

上流のプロバイダーでエラーが発生した場合、リクエストフィルターが許可していれば、別の正常なプロバイダーにルーティングして復旧できます。プロバイダーごとの稼働率データにプログラムでアクセスするには Endpoints APIを利用できます。詳しくは、 負荷分散とプロバイダールーティングのオプションをご覧ください。

1.
https://claude.ai/apple-touch-icon.png のファビコン
Claude Code
Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.
3.18Bトークン
2.
https://sillytavern.app/ のファビコン
SillyTavern
SillyTavern is the LLM frontend for power users, a chat interface that connects to any model and gives deep control through character creation, roleplay, and prompt customization.
2.13Bトークン
3.
https://chub.ai/ のファビコン
Chub AI
GenAI for everyone
2.03Bトークン
4.
https://engine.tastelabs.com/ のファビコン
Taste Engine
新着
1.23Bトークン
5.
https://janitorai.com/ のファビコン
Janitor AI
Janitor AI is a chatbot platform where users create and chat with custom AI characters for interactive roleplay, storytelling, and immersive fiction.
867Mトークン

よくある質問

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection.

Claude Opus 4.5 の料金は $5.00/M 入力トークン と $25.00/M 出力トークン、Cache Read：$0.50/M tokens、Cache Write：$6.25/M tokens、Cache Write (1h)：$10.00/M tokens、Web Search：$10.00/1K calls には別料金が適用されます です。

Claude Opus 4.5 のコンテキストウィンドウは 200,000 トークンです。最大 64,000 トークンの補完に対応しています。

はい。Claude Opus 4.5 は関数呼び出し用の tools と tool_choice を受け付けます。 response_format の JSON スキーマによる構造化出力にも対応しています。

Claude Opus 4.5 は PDF などのファイル、画像、テキスト を入力として受け取り、テキスト を返します。

Claude Opus 4.5 は OpenRouter 上で 5 社のプロバイダー（Claude Platform on AWS、Azure、Google Vertex、Amazon Bedrock、Anthropic）によって提供されています。リクエストは利用可能な最適のプロバイダーにルーティングされ、他のプロバイダーへの自動フェイルオーバーに対応し、プロバイダールーティングでプロバイダーを固定または除外できます。

Claude Opus 4.5 は 2025年11月24日 にリリースされました。

その他のモデル：提供元 Anthropic

Claude Haiku 5.5

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and knowledge work, and accepts text and image input with a 1M-token context window.

It is the first Haiku model with adjustable effort. Thinking is adaptive and on by default, with effort as the main lever for trading off depth, latency, and cost; it can be turned off at low, medium, and high effort.

テキスト1M コンテキスト$0.10 / $0.50
Claude Haiku 5.5 (batch)

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and knowledge work, and accepts text and image input with a 1M-token context window.

It is the first Haiku model with adjustable effort. Thinking is adaptive and on by default, with effort as the main lever for trading off depth, latency, and cost; it can be turned off at low, medium, and high effort.

テキスト1M コンテキスト$0.05 / $0.25
Claude Sonnet 5.5

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing polished documents, slides, and spreadsheets, and it writes and communicates more clearly than its predecessor.

Thinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops.

テキスト1M コンテキスト$2 / $10
Claude Sonnet 5.5 (batch)

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing polished documents, slides, and spreadsheets, and it writes and communicates more clearly than its predecessor.

Thinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops.

テキスト1M コンテキスト$1 / $5
Claude Opus 5.5

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up.

The model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.

テキスト1M コンテキスト$4 / $20
Claude Opus 5.5 (batch)

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up.

The model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.

テキスト1M コンテキスト$2 / $10
Claude Fable 5.1

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.

テキスト1M コンテキスト$10 / $50
Claude Fable 5.1 (batch)

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.

テキスト1M コンテキスト$5 / $25
Claude Opus 5

Fast-mode variant of Opus 5 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5.

Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Note: As of September 1, 2026, this dedicated fast model is deprecated. Fast mode is now served by the fast service tier endpoint on Claude Opus 5 — request it with service_tier: "fast" or speed: "fast". Requests to this model keep working and are served by the same fast tier capacity, so no action is required, but new integrations should target the regular model. Learn more in our service tier docs: https://openrouter.ai/docs/guides/features/service-tiers

テキスト1M コンテキスト
Claude Opus 5

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.

The model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.

テキスト1M コンテキスト$5 / $25
Claude Opus 5 (batch)

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.

The model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.

テキスト1M コンテキスト$2.50 / $12.50
Claude Sonnet 5

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.

テキスト1M コンテキスト$2 / $10
Claude Sonnet 5 (batch)

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.

テキスト1M コンテキスト$1 / $5
Claude Fable Latest

This model always redirects to the latest model in the Claude Fable family.

テキスト1M コンテキスト
Claude Fable 5

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.

It is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.

テキスト1M コンテキスト$10 / $50
Claude Fable 5 (batch)

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.

It is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.

テキスト1M コンテキスト$5 / $25
Claude Opus 4.8

Fast-mode variant of Opus 4.8 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.

Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Note: As of September 1, 2026, this dedicated fast model is deprecated. Fast mode is now served by the fast service tier endpoint on Claude Opus 4.8 — request it with service_tier: "fast" or speed: "fast". Requests to this model keep working and are served by the same fast tier capacity, so no action is required, but new integrations should target the regular model. Learn more in our service tier docs: https://openrouter.ai/docs/guides/features/service-tiers

テキスト1M コンテキスト
Claude Opus 4.8

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.

It is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.

テキスト1M コンテキスト$5 / $25
Claude Opus 4.8 (batch)

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.

It is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.

テキスト1M コンテキスト$2.50 / $12.50
Claude Opus 4.7

Fast-mode variant of Opus 4.7 - identical capabilities with higher output speed at premium 6x pricing.

Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

テキスト1M コンテキスト