Pular para o conteúdo
Alfa
  • Modelos
  • Classificações
  • Ori
Falar com vendas

Rodapé

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Produto

  • Chat
  • Classificações
  • Avaliações de desempenho
  • Aplicativos
  • Descobrir
  • Modelos
  • Ori
  • Coleções
  • Provedores
  • Ferramentas
  • Preços
  • Business
  • Enterprise
  • Laboratório

Empresa

  • Sobre
  • Blog
  • Clientes
  • Carreiras
    Vagas
  • Privacidade
  • Termos de serviço
  • Central de confiança
  • Suporte
  • Funciona com OR
  • Dados
  • Marca

Desenvolvedor

  • Documentação
  • Referência da API
  • Plataforma para desenvolvedores
  • Status
  • Mapa do site para IA

Conectar

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon de anthropic

Anthropic: Claude Opus 4.5

anthropic/claude-opus-4.5

Comparar

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.

Modalidades
Preço de entrada / saída
US$ 5 / US$ 25por 1M
Contexto
200K
Lançado
24 de nov. de 2025
Comparar
ProvedoresPreçosDesempenhoDisponibilidadeAvaliações de desempenhoAplicativosAtividadePerguntas frequentesExplorar

Provedores

Diferentes empresas hospedam o mesmo modelo. O OpenRouter encaminha sua solicitação para uma delas com base no modo de roteamento que você escolhe — Equilibrado (preço + velocidade), Nitro (mais rápido) ou Floor (mais barato).

Preços

O preço médio que os clientes realmente pagam por este modelo, ao lado dos preços publicados pelos provedores. O cache e os descontos fazem com que o preço efetivamente pago seja frequentemente bem inferior ao preço anunciado.

Desempenho

A vazão indica a velocidade com que o modelo escreve (tokens por segundo — quanto maior, melhor). A latência é o tempo total de ida e volta (quanto menor, melhor). TTFT é o tempo até o primeiro token — quanto tempo leva para você ver algo aparecer (quanto menor, melhor).

Disponibilidade

A disponibilidade é a porcentagem dos últimos 3 dias em que pelo menos um provedor estava respondendo às solicitações. A disponibilidade é a porcentagem de tempo em que a inferência foi realizada com sucesso. O OpenRouter monitora continuamente e usa o próximo melhor provedor quando um deles retorna um erro.

Avaliações de desempenho

Pontuações em avaliações padronizadas e as próprias saídas deste modelo para prompts compartilhados de testes de desempenho. Porcentagens maiores são melhores — e cada posição mostra onde este modelo fica entre os modelos avaliados naquela fonte.

Resumo das pontuações de avaliações comparativas para Anthropic: Claude Opus 4.5 (Artificial Analysis, Design Arena e Vals AI)
FonteAvaliação comparativaPontuação
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%

Aplicativos

Aplicativos públicos que enviam mais tráfego para este modelo. Um bom indicador de como são as cargas de trabalho reais em produção — e uma pista sobre os casos de uso para os quais este modelo é mais adequado.

Atividade

Volume de tokens e tráfego de requisições para este modelo ao longo do tempo.

API

Código pronto para chamar este modelo. A API do OpenRouter é compatível com a OpenAI — a maioria dos SDKs funciona apenas trocando a URL base. A única coisa que muda entre os modelos é o slug do modelo abaixo.

Disponível por meio do roteamento intrarregional da UE

Anthropic: Claude Opus 4.5 está disponível por meio do roteamento regional na UE. As solicitações enviadas para eu.openrouter.ai são descriptografadas na UE e roteadas apenas para endpoints compartilhados de provedores na Europa (UE/EEE, Reino Unido e Suíça).

Provedores na Europa
Amazon Bedrock
Preços na Europa
  • Amazon Bedrock: US$ 5,50/M tokens de entrada, US$ 27,50/M tokens de saída
URL base
https://eu.openrouter.ai/api/v1
Plano
Requer Business ou Enterprise. Autoatendimento no Business: sem contrato, sem mínimo mensal. OpenRouter Business para roteamento dentro da região da UE

Falha em modo fechado: se nenhum endpoint de provedor compartilhado na Europa estiver disponível, a solicitação retorna um erro em vez de sair da região. As solicitações atendidas pela sua própria chave BYOK vão para a região da sua implantação, que você controla. Documentação de roteamento na região

Explorar mais modelos

Modelos de IA com visão: LLMs multimodais para compreensão de imagensColeçãoClassificações de modelos de IAClassificação
Latência / taxa de transferência
US$ 5,00US$ 25,00US$ 0,502,10s46 tps
100,00%
US$ 5,00US$ 25,00US$ 0,503,32s27 tps
--
US$ 5,00US$ 25,00US$ 0,505,58s54 tps
--
US$ 5,00US$ 25,00US$ 0,501,69s42 tps
100,00%
US$ 5,00US$ 25,00US$ 0,501,09s41 tps
100,00%
Não utilizado no roteamento Standard:Por que estes endpoints não são usados
US$ 5,50US$ 27,50US$ 0,551,37s55 tps
100,00%
Taxa de transferência
55tok/s

P50, melhor entre os provedores

Latência
1,09s

P50, melhor provedor

Avaliações de desempenho do AutoExacto
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 provedores adicionais
Disponibilidade (3d)O modelo estava acessível. Requisição roteada para um provedor.
100,00%
Disponibilidade (3d)O modelo retornou inferência de qualquer provedor. Erros e respostas vazias contam negativamente para essa métrica.
99,37%

Disponibilidade nos últimos 3 dias

Últimas 72 horas
Disponibilidade 99,37%
Há 3 diasHá 2 diasOntemAgora

Disponibilidade nas últimas 24 horas

OpenRouter Availability
99,32%
Without Routing
99,02%

Quando ocorre um erro em um provedor upstream, podemos nos recuperar roteando para outro provedor saudável, se os filtros da sua solicitação permitirem. Você pode acessar os dados de disponibilidade por provedor de forma programática pela API de endpoints. Saiba mais sobre nossas opções de balanceamento de carga e roteamento de provedores.

1.
Favicon de https://claude.ai/apple-touch-icon.png
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.
3,18Btokens
2.
Favicon de https://sillytavern.app/
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.
2,14Btokens
3.
Favicon de https://chub.ai/
Chub AI
GenAI for everyone
2,03Btokens
4.
Favicon de https://engine.tastelabs.com/
Taste Engine
novo
1,24Btokens
5.
Favicon de https://janitorai.com/
Janitor AI
Janitor AI is a chatbot platform where users create and chat with custom AI characters for interactive roleplay, storytelling, and immersive fiction.
868Mtokens

Perguntas frequentes

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 custa US$ 5,00/M de tokens de entrada e US$ 25,00/M de tokens de saída, com taxas separadas para Cache Read por US$ 0,50/M tokens, Cache Write por US$ 6,25/M tokens, Cache Write (1h) por US$ 10,00/M tokens e Web Search por US$ 10,00/1K calls.

Claude Opus 4.5 tem uma janela de contexto de 200.000 tokens. Ele aceita até 64.000 tokens de conclusão.

Sim. Claude Opus 4.5 aceita tools e tool_choice para chamadas de função. Também oferece suporte a saídas estruturadas por meio de um esquema JSON em response_format.

Claude Opus 4.5 aceita arquivos como PDFs, imagens e texto como entrada e retorna texto.

Claude Opus 4.5 é disponibilizado por 5 provedores no OpenRouter: Claude Platform on AWS, Azure, Google Vertex, Amazon Bedrock e Anthropic. As solicitações são roteadas para o melhor provedor disponível, com alternância automática para os demais em caso de falha, e você pode fixar ou excluir provedores com o roteamento de provedores.

Claude Opus 4.5 foi lançado em 24 de novembro de 2025.

Mais modelos de 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.

TextoContexto de 1MUS$ 0,10 / US$ 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.

TextoContexto de 1MUS$ 0,05 / US$ 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.

TextoContexto de 1MUS$ 2 / US$ 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.

TextoContexto de 1MUS$ 1 / US$ 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.

TextoContexto de 1MUS$ 4 / US$ 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.

TextoContexto de 1MUS$ 2 / US$ 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.

TextoContexto de 1MUS$ 10 / US$ 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.

TextoContexto de 1MUS$ 5 / US$ 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

TextoContexto de 1M
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.

TextoContexto de 1MUS$ 5 / US$ 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.

TextoContexto de 1MUS$ 2,50 / US$ 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.

TextoContexto de 1MUS$ 2 / US$ 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.

TextoContexto de 1MUS$ 1 / US$ 5
Claude Fable Latest

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

TextoContexto de 1M
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.

TextoContexto de 1MUS$ 10 / US$ 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.

TextoContexto de 1MUS$ 5 / US$ 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

TextoContexto de 1M
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.

TextoContexto de 1MUS$ 5 / US$ 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.

TextoContexto de 1MUS$ 2,50 / US$ 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

TextoContexto de 1M