Ein Claude-Modell auswählen
Einsteiger
Anthropic bietet eine Modellfamilie an verschiedenen Punkten von Fähigkeit/Kosten/Geschwindigkeit an. Gut zu wählen heißt vor allem: das Modell auf die Aufgabe zuschneiden — und keine Fähigkeit zu bezahlen, die du nicht brauchst.
- Die Leiter Haiku → Sonnet → Opus als Fähigkeit/Kosten/Geschwindigkeit-Tradeoff lesen
- Vom richtigen Default starten statt zu raten und dann bewusst hoch oder runter gehen
- Tiers in einem System mischen — der größte Kostenhebel, den die meisten nie ziehen
- Die exakte Model-ID richtig nachschlagen, damit Upgrades eine Ein-Zeilen-Änderung bleiben
Die aktuellen Modelle
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.
Probier's aus: welches Modell passt?
Beantworte drei Fragen und bekomme eine Startempfehlung:
Modellauswahl
Aufgabenschwierigkeit
Was am wichtigsten ist
Anfragevolumen
Recommended
Claude Sonnet
Der ausgewogene Standard — starkes Schlussfolgern und Coden zu einem Bruchteil der Opus-Kosten. Fang hier an und steig nur höher, wenn du an eine echte Qualitätsgrenze stößt.
Schlag die genaue Modell-ID nach in der Modelltabelle. Nur als Faustregel — führe zur Sicherheit eine schnelle Eval mit deinen eigenen Eingaben durch.
Das mentale Modell: eine Fähigkeitsleiter
- Starte mit Sonnet. Das ist der Standard-Zugpferd — starkes Reasoning und Coding zu vernünftigen Kosten. Die meisten Aufgaben sollten hier beginnen.
- Steige zu Opus auf, wenn Sonnet strauchelt und Qualität mehr zählt als Kosten (hartes Reasoning, kniffelige Agenten, verhedderter Code).
- Steige auf Haiku ab für hohe Volumen, latenzsensible oder einfache Arbeit (Klassifikation, Extraktion, Routing, günstige Sub-Agenten).
So wählst du tatsächlich
Guided walkthrough1 of 4
- Es ist das ausgewogene Zugpferd. Woanders zu starten heißt zu optimieren, bevor du Evidenz über deine tatsächliche Aufgabe hast.
- Rüste nicht die gesamte Workload hoch. Finde die Fälle, in denen Sonnet scheitert, und route nur die zu Opus — du kaufst die Qualität, ohne sie überall zu bezahlen.
- Klassifikation, Extraktion, Routing und günstige Subagenten brauchen selten ein größeres Modell. Teste es, statt anzunehmen.
- Nutze Haiku für günstiges Pre-/Post-Processing und Sonnet/Opus für den harten Kern. Dieses Model-Tiering ist einer der größten Kostenhebel — siehe Kosten & Latenz.
Model-Tiering verdient einen eigenen Read: Kosten & Latenz.
Wähle nicht allein nach Benchmarks
Öffentliche Benchmarks sind ein Starthinweis, kein Urteil für deine Aufgabe. Fahre eine winzige Eval auf einer Handvoll deiner echten Inputs über zwei Modelle — dauert Minuten und schlägt Raten.
Die exakte Model-ID nachschlagen
Übergib immer die aktuelle API-Model-ID (z. B. in deinem messages.create-Call). Hol sie aus der Modelltabelle oben oder der offiziellen Models-Seite — und lies sie lieber aus der Config, statt sie an vielen Stellen hart zu codieren, damit Modell-Upgrades eine Ein-Zeilen-Änderung sind.
Prüfe dich selbst
0/4- Haiku → Sonnet → Opus ist eine Fähigkeit/Kosten/Geschwindigkeit-Leiter — wähle eine Sprosse, rate kein Modell.
- Auf Sonnet defaulten und ausliefern; nur mit Evidenz aus deiner eigenen Aufgabe hoch oder runter gehen.
- Rüste die harte Teilmenge auf, nicht die ganze Workload — Routing schlägt Pauschal-Upgrades.
- Tiers in einem System zu mischen ist einer der größten verfügbaren Kostenhebel.
- Benchmarks sind ein Hinweis; eine winzige Eval auf deinen echten Inputs ist das Urteil.
- Model-ID aus der Config lesen und in der Live-Modelltabelle nachschlagen — Modellfakten niemals hart codieren.