Claude 모델 선택하기
초급
Anthropic은 성능·비용·속도 지점이 서로 다른 모델 제품군을 제공합니다. 잘 선택한다는 것은 결국 작업에 맞는 모델을 고르는 일이며, 필요하지 않은 성능에 과지출하지 않는 일입니다.
- Haiku → Sonnet → Opus 사다리를 성능/비용/속도 트레이드오프로 이해합니다
- 추측 대신 올바른 기본값에서 시작해, 근거를 가지고 위 또는 아래로 이동합니다
- 한 시스템 안에서 여러 티어를 섞습니다 — 대부분의 사람이 절대 당기지 않는 가장 큰 비용 레버입니다
- 정확한 모델 ID를 올바른 방법으로 조회해, 업그레이드가 한 줄 변경으로 끝나게 만듭니다
현재 모델들
Last verified: 2026-11-02 · Official models & pricing
| Model | API model ID | Tier | Best for |
|---|---|---|---|
| Claude Fable 5.1 | claude-fable-5-1 | Mythos-classflagship (above Opus) | Released September 1, 2026. For demanding reasoning and long-horizon agentic work, or when Opus 5.5 at higher effort still falls short on your evals — Anthropic's models overview recommends starting with Opus 5.5 for most workloads and reaching for Fable 5.1 only when it falls short. Same list price as Fable 5 with cache reads at a quarter of the cost. Three breaking changes vs Fable 5: forced tool_choice (any/tool) returns 400, thinking blocks are readable only by Fable 5.1 or newer, and editing earlier turns invalidates thinking blocks. Refuses in-band (HTTP 200, stop_reason: refusal); fallback targets are Opus 5 and Opus 4.8. 30-day retention (not ZDR-eligible unless expressly authorized by Anthropic); not on Priority Tier. (Supersedes Claude Fable 5, now a legacy model.) |
| Claude Mythos 5.1 | claude-mythos-5-1 | Mythos-classverification required | Same capabilities, specs and pricing as Fable 5.1, available only to organizations verified through Anthropic's verification programs. Since October 6, 2026 that is an application, not an invitation: Project Glasswing was restructured into the Cyber Verification Program's three tiers — Defense Access (organizations, and individuals on paid plans), Red Team Access (organizations only) and Specialized Access (organizations only, reviewed with the US government, where Glasswing members landed) — each granting Opus 5.5, Sonnet 5.5 and Mythos 5.1. Apply at portal.anthropic.com/programs; decisions typically within seven business days. Does not run the conversation-binding check on thinking blocks. Customers without access should use Fable 5.1. |
| Claude Opus 5.5 | claude-opus-5-5 | Opusmost capable | Anthropic's recommended starting point for most workloads, released September 22, 2026: long-running agentic coding and knowledge work, 1M context, 128k output, June 2026 reliable knowledge cutoff. Beats the larger Fable 5.1 on every row of Anthropic's launch table at 40% of its list price. Default effort is 'medium' (shared only with Haiku 5.5 — every other model that supports effort defaults to 'high'), and at a given level it thinks more per turn than Opus 5 — re-run your effort sweep instead of carrying settings over. Four breaking changes vs Opus 5: thinking cannot be disabled at any effort level (400), forced tool_choice (any/tool) returns 400 including on token counting, thinking blocks are bound to both the model and the conversation prefix, and computer_20251124 is rejected on the Claude API and Google Cloud (still accepted on Bedrock). A fifth change returns 200: text between tool calls now arrives in progress-update thinking blocks, empty at the default display of 'omitted'. Refuses in-band (HTTP 200, stop_reason: refusal) with new 'bio' and 'reasoning_extraction' categories; server-side fallback does NOT retry 'reasoning_extraction'. Fast mode is Claude API only. Retirement no sooner than September 22, 2027. (Supersedes Claude Opus 5, now a legacy model.) |
| Claude Opus 5 | claude-opus-5 | Opusmost capable | Legacy since September 22, 2026 (superseded by Opus 5.5) but still available. Complex agentic coding and enterprise work, 1M context, 128k output. Two reasons to stay on it for now: it accepts thinking: {type: 'disabled'} at 'high' effort or below, and its thinking blocks are readable by more models than Opus 5.5's (only Fable 5.1 and Mythos 5.1 read Opus 5.5's). (Supersedes Claude Opus 4.8, now a legacy model.) |
| Claude Sonnet 5.5 | claude-sonnet-5-5 | Sonnetbalanced | The best combination of speed and intelligence, released September 28, 2026: well-scoped everyday tasks, bug fixes, multistep tool use and polished documents, 1M context, 128k output (300k on Batches with a beta header), June 2026 reliable knowledge cutoff. Exactly Sonnet 5's prices and the same tokenizer, yet Anthropic claims output 30%+ faster and up to 30% less per task — the saving is in the token and turn counts, not the rate card. Beats Opus 5.5 on Terminal-Bench 4.0 (70.6% vs 66.4%) and ties it on knowledge-work Elo, but trails it by ~8 points on FrontierCode 1.1. Default effort is 'high' and levels are recalibrated — re-run your sweep. Minimum cacheable prompt drops to 512 tokens (1,024 on Sonnet 5). Five breaking changes vs Sonnet 5: thinking: {type: 'disabled'} returns 400 (use 'between_tools', accepted only at 'high' effort or below and with no companion field), forced tool_choice (any/tool) returns 400 including on token counting, thinking blocks are bound to the model, the conversation prefix and the producing account, computer_20251124 is rejected on the Claude API and Google Cloud (still accepted on Bedrock), and Opus 4.8 / Opus 4.7 / Sonnet 5 are rejected as advisor-tool advisors. A sixth change returns 200: text between tool calls arrives in progress-update thinking blocks, empty at the default display of 'omitted'. Refuses in-band (HTTP 200, stop_reason: refusal) in five categories; server-side fallback retries only 'cyber' and 'frontier_llm', on Sonnet 5. temperature/top_p/top_k at non-default values return 400. Retirement no sooner than September 28, 2027. (Supersedes Claude Sonnet 5, now a legacy model.) |
| Claude Sonnet 5 | claude-sonnet-5 | Sonnetbalanced | Legacy since September 28, 2026 (superseded by Sonnet 5.5) but still available. The balanced pick when speed and cost matter more than Opus-level depth, 1M context. Two reasons to stay on it for now: it accepts thinking: {type: 'disabled'} at any effort level including 'xhigh' and 'max' (Sonnet 5.5's 'between_tools' tops out at 'high'), and it supports forced tool_choice, which Sonnet 5.5 does not. It is also the server-side fallback target for Sonnet 5.5's 'cyber' and 'frontier_llm' refusals. (Supersedes Claude Sonnet 4.6, now a legacy model.) |
| Claude Haiku 5.5 | claude-haiku-5-5 | Haikufastest & cheapest | The fastest model, released October 7, 2026: high-volume, latency-sensitive work — classification, extraction, routing, and cheap sub-agents. 1M context (up from Haiku 4.5's 200k), 128k output (up from 64k, 300k on Batches with a beta header), June 2026 reliable knowledge cutoff (up from Feb 2025), and the first Haiku with adaptive thinking and the effort parameter (default 'medium'). THE ONLY CURRENT MODEL PRICED BY PROMPT LENGTH: every other 4.6-and-later model bills the full 1M window at standard rates, but Haiku 5.5 has two rate cards split at 100,000 tokens, and crossing that line reprices the WHOLE request — input, output, cache writes, cache reads and batch — at 5x. It also moves to the newer tokenizer, so the same text counts ~30% more tokens than on Haiku 4.5: the real saving is ~87% below the cliff and ~35% above it, not the 90% on the rate card. Five breaking changes vs Haiku 4.5: budget_tokens thinking returns 400, non-default temperature/top_p/top_k return 400, assistant prefill returns 400 even with thinking off, computer_20250124 is rejected on the Claude API and Google Cloud, and sending thinking blocks back after editing earlier turns returns 400. Unusually permissive where the bigger 5.5 models are not — it accepts both thinking: {type: 'disabled'} (at 'high' effort or below) and forced tool_choice, which Opus 5.5 and Sonnet 5.5 both reject. Refuses in-band (HTTP 200, stop_reason: refusal) in four categories with NO server-side fallback. Priority Tier is not supported. Retirement no sooner than October 7, 2027. (Supersedes Claude Haiku 4.5, now a legacy model.) |
| Claude Haiku 4.5 | claude-haiku-4-5-20251001 | Haikufastest & cheapest | Legacy since October 7, 2026 (superseded by Haiku 5.5) but still available, and still the only model with a 200k context window (not 1M), a 64k output cap, and no support for the effort parameter; its reliable knowledge cutoff is Feb 2025. Three reasons to stay on it for now: it accepts assistant prefill and manual extended thinking (budget_tokens), both of which Haiku 5.5 rejects with a 400, and it supports Priority Tier, which Haiku 5.5 does not. It is also flat-rated — Haiku 5.5's cheaper price applies only to prompts up to 100,000 tokens. Watch its lifecycle closely: its earliest-possible retirement date of October 15, 2026 has now PASSED, so it can be deprecated at any time — yet as of November 2, 2026 the status table still lists it Active with no deprecation announced. It is the only current model past its floor (Opus 4.5 is next, on November 24, 2026) and it now has a direct successor. This is a signal to plan, not an outage: Anthropic commits to at least 60 days' notice once a deprecation is announced, so a migration started now has room. |
| Claude Fable 5 | claude-fable-5 | Mythos-classflagship (above Opus) | Legacy since September 1, 2026 (superseded by Fable 5.1) but still available. Multiday autonomous runs, first-shot on ambiguous specs, dense vision, sustained delegation to parallel subagents. GA June 9 2026. Refuses in-band (HTTP 200, stop_reason: refusal) — configure server-side or client-side fallback. Adaptive thinking only; raw thinking never returned. 30-day retention (NOT ZDR-eligible). Two reasons to stay on it for now: it supports forced tool_choice and Priority Tier (existing commitments only — new ones are no longer sold), which Fable 5.1 does not. |
| Claude Mythos 5 | claude-mythos-5 | Mythos-classverification required, legacy | Superseded by Mythos 5.1. Shares Fable 5's specs and pricing, offered separately for defensive cybersecurity workflows to organizations verified through Anthropic's verification programs — originally the invite-only Project Glasswing. Since October 6, 2026 the way in is an application to the Cyber Verification Program, and what its tiers grant is Mythos 5.1, not this model. Customers without access should use Fable 5.1. |
Model IDs are exact; tiers and 'best for' are guidance. Pricing, context-window sizes and rate limits change frequently and are intentionally NOT listed here — always read them on the official page above. This file is the single source of truth: never hard-code model facts in prose, link to this table instead.
실습: 어떤 모델이 맞을까?
세 가지 질문에 답하고 시작 추천을 받아 보세요:
모델 선택
작업 난이도
가장 중요한 것
요청량
Recommended
Claude Sonnet
균형 잡힌 기본값 — Opus의 일부 비용으로 강력한 추론과 코딩을 제공합니다. 여기서 시작하고, 실제 품질의 한계에 부딪힐 때만 상위 모델로 올리세요.
정확한 모델 ID는 다음에서 확인하세요: 모델 표. 어디까지나 경험 법칙입니다 — 확실히 하려면 자신의 입력으로 간단한 평가를 돌려보세요.
멘탈 모델: 성능 사다리
- Sonnet으로 시작하세요. 기본 주력 모델입니다 — 합리적 비용에 강력한 추론과 코딩. 대부분의 작업은 여기서 출발해야 합니다.
- Opus로 올라가는 것은 Sonnet이 힘겨워하고 품질이 비용보다 중요할 때에만입니다(어려운 추론, 까다로운 에이전트, 지저분한 코드).
- Haiku로 내려가세요 — 대량, 지연 시간 민감, 또는 단순 작업(분류, 추출, 라우팅, 저렴한 서브에이전트)이라면.
실제로 선택하는 법
Guided walkthrough1 of 4
- 균형 잡힌 주력 모델입니다. 다른 곳에서 시작한다는 것은 실제 작업에 대한 근거도 없이 최적화하고 있다는 뜻입니다.
- 전체 워크로드를 업그레이드하지 마세요. Sonnet이 실패하는 케이스를 찾아 그것만 Opus로 라우팅하세요 — 필요한 곳에서만 품질을 사는 것입니다.
- 분류, 추출, 라우팅, 저렴한 서브에이전트에는 큰 모델이 필요 없는 경우가 많습니다. 가정하지 말고 테스트하세요.
- 저렴한 전/후처리에는 Haiku를, 어려운 핵심 부분에는 Sonnet/Opus를 사용하세요. 이 모델 티어링은 가장 큰 비용 레버 중 하나입니다 — Cost & Latency 참고.
모델 티어링은 별도로 읽어볼 만합니다: Cost & Latency.
벤치마크만 보고 고르지 마세요
공개 벤치마크는 출발점의 힌트일 뿐, 당신의 작업에 대한 판결이 아닙니다. 실제 입력 몇 개로 두 모델에 대해 작은 평가를 돌려 보세요 — 몇 분이면 되고 추측보다 낫습니다.
정확한 모델 ID 조회하기
항상 현재 API 모델 ID를 전달하세요(예: messages.create 호출에서). 위 모델 표나 공식 모델 페이지에서 가져오세요 — 그리고 여러 곳에 하드코딩하기보다 설정 파일에서 읽는 것을 선호하세요. 그래야 모델 업그레이드가 한 줄 변경으로 끝납니다.
스스로 확인해 보세요
0/4- Haiku → Sonnet → Opus는 성능/비용/속도 사다리입니다 — 계단을 고르되 모델을 추측하지 마세요.
- Sonnet을 기본으로 잡고 출시하세요; 자신의 작업에 대한 근거가 있을 때만 위나 아래로 이동하세요.
- 전체 워크로드가 아닌 어려운 부분집합을 업그레이드하세요 — 라우팅이 일괄 업그레이드를 이깁니다.
- 한 시스템 안에서 티어를 섞는 것은 가장 큰 비용 레버 중 하나입니다.
- 벤치마크는 힌트이고, 실제 입력에 대한 작은 평가가 판결입니다.
- 모델 ID는 설정에서 읽고 라이브 모델 표에서 조회하세요 — 모델 사실을 절대 하드코딩하지 마세요.