콘텐츠로 건너뛰기
  • 모델
  • 순위
  • Ori
ElevenLabs launch offer: every ElevenLabs model is 50% off through October 19, 2026. See ElevenLabs models

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

제품

  • 채팅
  • 순위
  • 벤치마크
  • 앱
  • 찾아보기
  • 모델
  • Ori
  • 컬렉션
  • 제공업체
  • 도구
  • 가격
  • Business
  • Enterprise
  • 랩

회사

  • 정보
  • 블로그
  • 채용
    채용
  • 개인정보 보호
  • 서비스 약관
  • 신뢰 센터
  • 지원
  • OR과 호환
  • 데이터
  • 브랜드

개발자

  • 문서
  • API 참조
  • 개발자 플랫폼
  • 상태
  • AI 사이트맵

연결

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
anthropic의 파비콘

Anthropic: Claude Opus 4.8

anthropic/claude-opus-4.8

비교

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.

모달리티
입력/출력 가격
US$5 / US$251M당
컨텍스트
1.0M
출시
2026년 5월 27일
비교
제공업체가격성능가동 시간벤치마크앱활동자주 묻는 질문탐색

제공업체

같은 모델을 서로 다른 회사가 호스팅합니다. OpenRouter는 사용자가 선택한 라우팅 모드에 따라 요청을 그중 한 곳으로 라우팅합니다 — Balanced(가격 + 속도), Nitro(가장 빠름), Floor(가장 저렴함) 또는 Exacto(가장 높은 도구 호출 정확도).

가격

고객이 이 모델에 실제로 지불하는 평균 가격으로, 제공업체가 게시한 가격과 함께 표시됩니다. 캐싱과 할인으로 인해 실제 지불 가격은 게시된 가격보다 훨씬 낮은 경우가 많습니다.

성능

처리량은 모델이 얼마나 빠르게 출력하는지를 나타냅니다(초당 토큰 수 — 높을수록 좋음). 지연 시간은 전체 왕복 시간입니다(낮을수록 좋음). TTFT는 첫 토큰까지 걸리는 시간으로, 무언가 화면에 표시되기 시작할 때까지의 시간을 뜻합니다(낮을수록 좋음).

가동 시간

가동 시간은 지난 3일 동안 하나 이상의 제공업체가 요청에 응답한 시간의 비율입니다. 가용성은 추론이 성공적으로 제공된 시간의 비율입니다. OpenRouter는 지속적으로 모니터링하며, 한 제공업체에서 오류를 반환하면 다음으로 적합한 제공업체를 사용합니다.

벤치마크

표준화된 평가와 공유 벤치마크 프롬프트에 대한 이 모델 자체의 출력 점수입니다. 백분율이 높을수록 더 좋으며, 각 순위는 이 모델이 해당 출처에서 평가된 모델 중 어디에 위치하는지를 보여줍니다.

벤치마크 점수 요약: Anthropic: Claude Opus 4.8 (Artificial Analysis, Design Arena and Vals AI)
출처벤치마크점수
Artificial AnalysisClaude Opus 4.8 (Max) Intelligence Index41.8
Artificial AnalysisClaude Opus 4.8 (Max) Coding Index74.3
Artificial AnalysisClaude Opus 4.8 (Max) Agentic Index41.9
Artificial AnalysisClaude Opus 4.8 (Max) GPQA Diamond92.0%
Artificial AnalysisClaude Opus 4.8 (Max) HLE48.7%
Artificial AnalysisClaude Opus 4.8 (Max) IFBench62.2%
Artificial AnalysisClaude Opus 4.8 (Max) τ²-Bench Telecom94.4%
Artificial AnalysisClaude Opus 4.8 (Max) AA-LCR77.7%
Artificial AnalysisClaude Opus 4.8 (Max) τ-Bench Banking34.2%
Artificial AnalysisClaude Opus 4.8 (Max) GDPval-AA47.8%
Artificial AnalysisClaude Opus 4.8 (Max) CritPt20.9%
Artificial AnalysisClaude Opus 4.8 (Max) SciCode54.4%
Artificial AnalysisClaude Opus 4.8 (Max) Terminal-Bench Hard58.3%
Artificial AnalysisClaude Opus 4.8 (Max) Terminal-Bench 4.021.7%
Artificial AnalysisClaude Opus 4.8 (Max) Terminal-Bench 2.184.6%
Artificial AnalysisClaude Opus 4.8 (Max) AA-Omniscience Accuracy48.8%
Artificial AnalysisClaude Opus 4.8 (Max) AA-Omniscience Non-Hallucination Rate60.7%
Design ArenaClaude Opus 4.8 Agents Arena Agenticgamedev Elo1238
Design ArenaClaude Opus 4.8 Agents Arena Agentichtmlslides Elo1227
Design ArenaClaude Opus 4.8 Agents Arena Agenticslides Elo1294
Design ArenaClaude Opus 4.8 Agents Arena Agenticslides(Html) Elo1230
Design ArenaClaude Opus 4.8 Agents Arena Agenticslides(Python-Pptx) Elo1310
Design ArenaClaude Opus 4.8 Agents Arena Androidnative Elo1247
Design ArenaClaude Opus 4.8 Agents Arena Full Stack Elo1248
Design ArenaClaude Opus 4.8 Agents Arena Godotgamedev Elo1231
Design ArenaClaude Opus 4.8 Agents Arena Htmlslides Elo1220
Design ArenaClaude Opus 4.8 Agents Arena Mobile Apps Elo1220
Design ArenaClaude Opus 4.8 Agents Arena Pptxslides Elo1306
Design ArenaClaude Opus 4.8 Agents Arena Python-Pptxslides Elo1298
Design ArenaClaude Opus 4.8 Agents Arena Python-Pptxslides Elo1227
Design ArenaClaude Opus 4.8 Agents Arena Webapps Elo1224
Design ArenaClaude Opus 4.8 Models Arena 3D Elo1226
Design ArenaClaude Opus 4.8 Models Arena Asciiart Elo1277
Design ArenaClaude Opus 4.8 Models Arena Code Categories Elo1258
Design ArenaClaude Opus 4.8 Models Arena Data Visualization Elo1241
Design ArenaClaude Opus 4.8 Models Arena Game Development Elo1269
Design ArenaClaude Opus 4.8 Models Arena SVG Elo1193
Design ArenaClaude Opus 4.8 Models Arena UI Component Elo1260
Design ArenaClaude Opus 4.8 Models Arena Website Elo1262
Vals AIClaude Opus 4.8 Code Migration47.3%
Vals AIClaude Opus 4.8 CorpFin v266.7%
Vals AIClaude Opus 4.8 EMB69.4%
Vals AIClaude Opus 4.8 Finance Agent (v2)53.9%
Vals AIClaude Opus 4.8 GPQA Diamond92.4%
Vals AIClaude Opus 4.8 Harvey's Legal Agent Benchmark9.6%
Vals AIClaude Opus 4.8 LiveCodeBench87.8%
Vals AIClaude Opus 4.8 LegalBench83.6%
Vals AIClaude Opus 4.8 Legal Research Bench43.8%
Vals AIClaude Opus 4.8 MedCode53.2%
Vals AIClaude Opus 4.8 MedScribe85.8%
Vals AIClaude Opus 4.8 MMLU Pro89.6%
Vals AIClaude Opus 4.8 MMMU Pro86.6%
Vals AIClaude Opus 4.8 MortgageTax69.9%
Vals AIClaude Opus 4.8 ProgramBench1.0%
Vals AIClaude Opus 4.8 ProofBench v169.0%
Vals AIClaude Opus 4.8 Vals RSI Index24.0%
Vals AIClaude Opus 4.8 SAGE54.8%
Vals AIClaude Opus 4.8 SkillsBench59.2%
Vals AIClaude Opus 4.8 SWE-bench88.6%
Vals AIClaude Opus 4.8 Tax Agent Bench30.0%
Vals AIClaude Opus 4.8 TaxEval v275.6%
Vals AIClaude Opus 4.8 Terminal-Bench 4.023.2%
Vals AIClaude Opus 4.8 Vals Index55.1%
Vals AIClaude Opus 4.8 Vals Multimodal Index70.9%
Vals AIClaude Opus 4.8 Vibe Code Bench v1.182.7%

앱

이 모델로 가장 많은 트래픽을 보내는 공개 앱입니다. 실제 프로덕션 워크로드가 어떤 모습인지 파악하는 데 유용하며, 이 모델이 어떤 사용 사례에 가장 적합한지 알려 주는 단서이기도 합니다.

활동

시간 경과에 따른 이 모델의 토큰 사용량과 요청 트래픽입니다.

API

이 모델을 호출하는 데 바로 사용할 수 있는 코드입니다. OpenRouter의 API는 OpenAI와 호환되므로 대부분의 SDK는 기본 URL만 바꾸면 작동합니다. 모델 간에 변경되는 것은 아래의 모델 슬러그뿐입니다.

더 많은 모델 살펴보기

비전 기능을 갖춘 AI 모델: 이미지 이해를 위한 멀티모달 LLM컬렉션AI 모델 순위순위
US$5.00US$25.00US$0.501.32s64 tps
100.00%
US$5.00US$25.00US$0.50----
100.00%
US$5.00US$25.00US$0.501.99s77 tps
100.00%
US$5.00US$25.00US$0.501.03s77 tps
99.96%
US$5.00US$25.00US$0.501.02s63 tps
99.88%
Standard 라우팅에서 사용되지 않음:이 엔드포인트를 사용하지 않는 이유
US$5.50US$27.50US$0.551.28s30 tps
100.00%
US$5.50US$27.50US$0.55----
100.00%
US$5.50US$27.50US$0.55----
100.00%
US$5.50US$27.50US$0.55----
100.00%
US$5.50US$27.50US$0.55----
100.00%
Fast
US$10.00US$50.00US$1.001.99s165 tps
100.00%
처리량
165tok/s

P50, 제공업체 전체 중 최고

지연 시간
1.02초

P50, 최고 제공업체

AutoExacto benchmarks
GPQA DiamondTAU-BenchGoogle Vertex90.3%78.0%Anthropic89.4%78.8%Claude Platform on AWS89.9%78.2%Azure (US)89.9%77.9%Amazon Bedrock (EU)90.0%77.2%Amazon Bedrock89.9%77.2%Google Vertex (EU)90.1%77.0%Azure90.1%76.7%Google Vertex (US)90.4%76.4%Amazon Bedrock (US)90.0%75.7%
+1 개 추가 제공업체
가동 시간(3일)모델에 연결할 수 있습니다. 요청이 제공업체로 라우팅되었습니다.
100.00%
가용성(3일)모델이 어떤 제공업체에서든 추론 결과를 반환한 비율입니다. 오류와 빈 응답은 가동 시간을 낮춥니다.
99.98%

지난 3일간의 가용성

최근 72시간
가용성 99.98%
3일 전2일 전어제지금

지난 24시간 동안의 가용성

OpenRouter Availability
99.98%
Without Routing
99.51%

업스트림 제공업체에서 오류가 발생하면 요청 필터에서 허용하는 경우 정상 상태인 다른 제공업체로 라우팅하여 복구할 수 있습니다. 제공업체별 가동 시간 데이터는 프로그래밍 방식으로 엔드포인트 API를 통해 확인할 수 있습니다. 로드 밸런싱 및 사용자 지정 옵션에 대해 자세히 알아보세요.

1.
https://claude.ai/apple-touch-icon.png의 파비콘
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.
213B토큰
2.
https://nousresearch.com의 파비콘
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
74.4B토큰
3.
https://openclaw.ai/의 파비콘
OpenClaw
OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.
27B토큰
4.
https://portal.nousresearch.com/api-docs의 파비콘
Nous Research API
Nous Research is an AI research team focused on advancing open-source AI.
23.6B토큰
5.
https://pi.dev/의 파비콘
pi
There are many coding agents, but this one is yours.
14.9B토큰

자주 묻는 질문

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.

Claude Opus 4.8의 비용은 US$5.00/M 입력 토큰 및 US$25.00/M 출력 토큰, US$0.50/M tokens의 Cache Read, US$6.25/M tokens의 Cache Write, US$10.00/M tokens의 Cache Write (1h) 및 US$10.00/1K calls의 Web Search에 대한 요금은 별도입니다.

Claude Opus 4.8의 컨텍스트 윈도우는 1,000,000토큰입니다. 최대 128,000개의 완료 토큰을 지원합니다.

예. Claude Opus 4.8은(는) 함수 호출을 위해 tools 및 tool_choice를 지원합니다. 또한 response_format에서 JSON 스키마를 사용하여 구조화된 출력을 지원합니다.

Claude Opus 4.8은(는) 텍스트, 이미지 및 PDF와 같은 파일을(를) 입력으로 받고 텍스트을(를) 반환합니다.

Claude Opus 4.8은(는) OpenRouter에서 5개 제공업체가 제공합니다: Claude Platform on AWS, Azure, Amazon Bedrock, Google Vertex 및 Anthropic. 요청은 사용 가능한 최적의 제공업체로 라우팅되며, 다른 제공업체로 자동 장애 조치됩니다. 제공업체 라우팅을 사용하여 제공업체를 고정하거나 제외할 수도 있습니다.

Claude Opus 4.8은(는) 2026년 5월 27일에 출시되었습니다.

다음 제공업체의 추가 모델 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.

텍스트컨텍스트 1MUS$0.10 / US$0.50
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.

텍스트컨텍스트 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.

텍스트컨텍스트 1MUS$2 / US$10
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.

텍스트컨텍스트 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.

텍스트컨텍스트 1MUS$4 / US$20
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.

텍스트컨텍스트 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.

텍스트컨텍스트 1MUS$10 / US$50
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.

텍스트컨텍스트 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

텍스트컨텍스트 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.

텍스트컨텍스트 1MUS$5 / US$25
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.

텍스트컨텍스트 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.

텍스트컨텍스트 1MUS$2 / US$10
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.

텍스트컨텍스트 1MUS$1 / US$5
Claude Fable Latest

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

텍스트컨텍스트 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.

텍스트컨텍스트 1MUS$10 / US$50
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.

텍스트컨텍스트 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

텍스트컨텍스트 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.

텍스트컨텍스트 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

텍스트컨텍스트 1M
Claude Haiku Latest

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

텍스트컨텍스트 200K