GetInfoUs
Head-to-Head Model Comparison

Claude Sonnet 4.5 vs Claude Haiku 4.5

Benchmarks, API Token Pricing, Context Window & Speed Comparison

Geprüft vom GetInfoUs-ForschungsteamZuletzt geprüft: October 2026Redaktionelle Richtlinien
Teilen
Related topics (12)
AI CompareAI BenchmarkToken PricingModel CostModel SpecsSWE-bench CodingModel VersusWhich AI ModelLLM Speed & LatencyReasoning ModelsExtended ThinkingPrompt Caching ROI
Claude Sonnet 4.5 vs Claude Haiku 4.5: Benchmarks, Pricing & Speed Comparison

Claude Sonnet 4.5 von Anthropic und Claude Haiku 4.5 von Anthropic gehören zu den führenden KI-Modellen. Claude Sonnet 4.5 bietet ein Kontextfenster von 1M Tokens bei API-Preisen von $3.00/$15.00 pro 1M Tokens, während Claude Haiku 4.5 200K Tokens Kontext zu $1.00/$5.00 pro 1M Tokens bereitstellt. Hier finden Sie den vollständigen Benchmark-, Latenz- und Kostenvergleich.

Direktvergleich (VS)

Beliebige Modelle wechseln & vergleichen

Select any AI models from our verified benchmark database to generate live side-by-side matrices.

Profile
Profile
Multi-Model Arena Stack:
5-Model Matrix Workbench
Popular Matchups:
Anthropic

Claude Sonnet 4.5

Frontier-Flaggschiff-Modell

Claude Sonnet 4.5 von Anthropic ist ein KI-Modell für anspruchsvolles Enterprise-Reasoning, Softwareentwicklung und produktive KI-Workflows mit 1M Kontextfenster, 90 Token/s Durchsatz, einem Intelligenz-Index von 91/100 und $3/$15 pro 1M To

Intelligence Index91 / 100
Input Token:

$3.00 / 1M

Output Token:

$15.00 / 1M

Context Window:

1M tokens

SWE-bench Verified:

77.8%

Anthropic

Claude Haiku 4.5

Ultraschnelle Echtzeit-Inferenz

Claude Haiku 4.5 von Anthropic ist ein KI-Modell für ultraschnelle Echtzeit-Antworten, niedrige Latenz und Hochdurchsatz-Routing mit 200K Kontextfenster, 140 Token/s Durchsatz, einem Intelligenz-Index von 54/100 und $1/$5 pro 1M Token.

Intelligence Index54 / 100
Input Token:

$1.00 / 1M

Output Token:

$5.00 / 1M

Context Window:

200K tokens

SWE-bench Verified:

58.2%

Wichtigste Unterschiede auf einen Blick

  • Claude Haiku 4.5 is 3.0x cheaper for API usage (input + output tokens combined).
  • Claude Sonnet 4.5 has a larger context window (1M vs 200K tokens).
  • Claude Haiku 4.5 is faster at 140 tok/s vs 90 tok/s.
  • Claude Sonnet 4.5 leads on SWE-bench coding (77.8% vs 58.2%).
Need definitions for token pricing, context, or benchmarks?Explore AI Glossary →
FeatureClaude Sonnet 4.5Claude Haiku 4.5
Intelligence Index
Composite reasoning & knowledge score (0-100)
9154
Provider
AnthropicAnthropic
Input Price
Cost per million input tokens
$3.00 / 1M$1.00 / 1M
Output Price
Cost per million output tokens
$15.00 / 1M$5.00 / 1M
Blended Price
Weighted 7:2:1 cache:input:output per 1M
$2.31 / 1M$0.77 / 1M
Context Window
Maximum input + output tokens
1M tokens~1,500 A4 pages of text200K tokens~300 A4 pages of text
Max Output Tokens
Per single request
64K64K
Throughput Speed
Tokens generated per second
90 tok/s140 tok/s
SWE-bench Verified
Real-world software engineering
77.8%58.2%
GPQA Diamond
Graduate-level reasoning
70.2%62.1%
Cached Input Price
Prompt caching discount per 1M tokens
$0.30 / 1M$0.10 / 1M

Wer gewinnt in welcher Disziplin?

At-a-glance decision framework
Coding
Claude Sonnet 4.5
+19.6% SWE-bench lead
Cost
Claude Haiku 4.5
3.0x cheaper monthly runtime
Speed
Claude Haiku 4.5
+56% faster generation
Context
Claude Sonnet 4.5
1M tokens window

Geprüfte Benchmark-Ergebnisse im Vergleich

Official evaluation metrics verified by independent third-party research labs.

Claude Sonnet 4.5Claude Haiku 4.5
SWE-bench Verified (Autonomous Coding)

Industry benchmark evaluating real-world GitHub issue resolution and multi-file debugging.

77.8%vs58.2%
GPQA Diamond (Doctorate-Level Science & Math)

Challenging questions created by domain experts to test complex PhD-level reasoning.

70.2%vs62.1%
MMLU-Pro (Multi-task Language Understanding)

Hardened reasoning and academic knowledge benchmark with reduced lucky-guess probability.

84.5%vs79.5%
LMSYS Chatbot Arena Elo

Crowdsourced human preference evaluation based on blind, head-to-head model battles.

1355ptsvs1324pts
Humanity's Last Exam (Frontier Expert Knowledge)

Extremely difficult, closed-ended questions spanning the frontier of human expert knowledge.

10.4%vsN/A
Terminal-Bench (Agentic Coding & Terminal Use)

Autonomous multi-step tasks executed inside a real command-line terminal environment.

50.1%vsN/A
SciCode (Scientific Computing)

Research-grade coding problems drawn from real scientific and numerical workloads.

43.9%vsN/A
LiveCodeBench (Competitive Coding)

Contamination-free competitive programming problems collected continuously over time.

72.6%vsN/A
AIME (Advanced Math Competition)

American Invitational Mathematics Examination — multi-step Olympiad-level reasoning.

84.7%vsN/A
Long-Context Reasoning

Accuracy when reasoning over very large inputs that fill the model context window.

74.8%vsN/A
Generation Speed (Throughput)

Tokens emitted per second during active generation streaming.

90 tok/s vs140 tok/s

Latenz & Antwortzeit

Time to first token (TTFT) and estimated end-to-end response time for a typical 500-token response.

Time to First Token (TTFT)Lower is better
Claude Sonnet 4.50.90s
Claude Haiku 4.50.28s
Est. End-to-End Response (500 tokens)TTFT + generation time
Claude Sonnet 4.56.46s
Claude Haiku 4.53.85s

Interaktiver Token-Kosten-Simulator

Adjust sliders to calculate projected monthly cloud API spending with prompt caching discounts.

100K / day
10K500K1M
30K / day
5K150K300K
50% cached
0% (Cold)50%90% (Warm)
Claude Sonnet 4.5 Monthly API Bill
$18.45 / month
$3/1M in · $15/1M out
Claude Haiku 4.5 Monthly API Bill
$6.15 / month
$1/1M in · $5/1M out
Claude Haiku 4.5 saves approximately $12.30 / month (67%) under this workload.3.0x Savings

Claude Sonnet 4.5 · Strengths & Key Advantages

  • 1M Kontextfenster und bis zu 64K maximale Output-Token (SWE-bench Verified 77.8% · GPQA Diamond 70.2%)
  • Hohe Generierungsgeschwindigkeit von 90 Token/Sekunde bei nur 900 ms Erstlatenz (TTFT)
  • Effiziente API-Struktur ($3/$15 pro 1M Token) inklusive Prompt-Caching, Tool-Calling und strikter JSON-Ausgabe
Considerations & Trade-offs
  • Proprietäres Cloud-Modell ohne Möglichkeit zum lokalen Download der Modellgewichte
  • Bei hohem Anfragevolumen empfiehlt sich der Einsatz von Prompt-Caching und Batch-API zur Kostenoptimierung

Claude Haiku 4.5 · Strengths & Key Advantages

  • 200K Kontextfenster und bis zu 64K maximale Output-Token (SWE-bench Verified 58.2% · GPQA Diamond 62.1%)
  • Hohe Generierungsgeschwindigkeit von 140 Token/Sekunde bei nur 280 ms Erstlatenz (TTFT)
  • Effiziente API-Struktur ($1/$5 pro 1M Token) inklusive Prompt-Caching, Tool-Calling und strikter JSON-Ausgabe
Considerations & Trade-offs
  • Proprietäres Cloud-Modell ohne Möglichkeit zum lokalen Download der Modellgewichte
  • Bei extrem komplexen mehrstufigen Forschungsfragen bieten schwere Reasoning-Spezialmodelle noch tiefere Analysen

Token Use & Task Economics

Estimated cost and token consumption to complete one representative agentic task.

MetricClaude Sonnet 4.5Claude Haiku 4.5
Cost per Task
Estimated USD to finish one task
$2.10$0.70
Output Tokens / Task
Tokens generated per task
55K20K
Reasoning Tokens / Task
Thinking tokens burned per task
30K10K

Technische Spezifikationen

Architecture, release timeline, capabilities, and modalities.

FeatureClaude Sonnet 4.5Claude Haiku 4.5
Official API Model ID (SDK)claude-sonnet-4-5-20251101claude-haiku-4-5-20251001
API ProtocolAnthropic Messages API + AWS Bedrock + Vertex AIAnthropic Messages API + AWS Bedrock + Vertex AI
Release Date2025-112025-10
Knowledge CutoffMarch 2025July 2025
ArchitectureHybrid ReasoningLightweight High-Speed Multimodal Transformer
ParametersConfidentialConfidential
Enterprise Rate Limits (RPM / TPM)4,000 – 10,000 RPM (Tier 4 + Priority Tier) · 4,000,000 – 10,000,000 TPM4,000 – 10,000 RPM (Tier 4 + Priority Tier) · 800,000 – 2,000,000 TPM
Long-Context Tier (>128K/200K)Standard rate up to 200K tokens; 2x input/output tier above 200K tokensStandard rate up to 200K tokens; 2x input/output tier above 200K tokens
Prompt Cache Policy & TTL$0.3/1M cached read (90% off); 5-min default & 1-hour extended TTL$0.1/1M cached read (90% off); 5-min default & 1-hour extended TTL
Computer Use / GUI AgentSupported (Screen coordinate grounding, browser & desktop GUI action loops)Supported (Screen coordinate grounding, browser & desktop GUI action loops)
MCP & Parallel Tool CallingNative MCP Client/Server ready · Parallel function calling · 100% Strict JSON SchemaNative MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
Web Search Grounding & SandboxNative Web Search Citations + Code Execution Tool + MCP ConnectorsNative Web Search Citations + Code Execution Tool + MCP Connectors
Official Fine-Tuning SupportCustom Model Tuning via Amazon Bedrock & Prompt DistillationCustom Model Tuning via Amazon Bedrock & Prompt Distillation
Multimodal Token BillingText BPE (~4 chars/token) · Vision (~258–765 tokens per image tile)Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile)
Quantization & Min GPU VRAMCloud-Hosted Proprietary (FP8 / BF16 Tensor Core Cluster) · Zero Local VRAM Required (100% Serverless Cloud API)Cloud-Hosted Proprietary (FP8 / BF16 Tensor Core Cluster) · Zero Local VRAM Required (100% Serverless Cloud API)
Safety & Frontier ClassificationAnthropic RSP ASL-2 / ASL-3 Constitutional Safety EvaluatedAnthropic RSP ASL-2 / ASL-3 Constitutional Safety Evaluated
Enterprise Compliance (ZDR/HIPAA/SOC2)SOC2 Type II · GDPR · Zero Data Retention (ZDR) & HIPAA BAA Available on Enterprise TierSOC2 Type II · GDPR · Zero Data Retention (ZDR) & HIPAA BAA Available on Enterprise Tier
Input Modalitiestext, visiontext, vision
Output Modalitiestexttext

Claude Sonnet 4.5 vs Claude Haiku 4.5: Schnelle Antworten (FAQ)

Which is more intelligent, Claude Sonnet 4.5 or Claude Haiku 4.5?

Claude Sonnet 4.5 is more intelligent. It scores 91 compared with 54 on the composite Intelligence Index.

Which model is faster?

Claude Haiku 4.5 is faster, generating 140 tokens per second compared with 90 tokens per second.

Which model is cheaper to run?

Claude Haiku 4.5 is cheaper at $0.77 per 1M tokens blended, compared with $2.31 (7:2:1 cache:input:output ratio).

Which model has lower latency?

Claude Haiku 4.5 has lower latency, with a time to first token of 0.28s compared with 0.90s.

Which model has a larger context window?

Claude Sonnet 4.5 has a larger context window, supporting 1M tokens compared with 200K tokens.

Fazit

Sowohl Claude Sonnet 4.5 (Optimal für anspruchsvolles Enterprise-Reasoning, Softwareentwicklung und produktive KI-Workflows, Enterprise-RAG-Systeme und skalierbare API-Pipelines.) als auch Claude Haiku 4.5 (Optimal für ultraschnelle Echtzeit-Antworten, niedrige Latenz und Hochdurchsatz-Routing, Enterprise-RAG-Systeme und skalierbare API-Pipelines.) überzeugen im Produktionseinsatz: Claude Sonnet 4.5 führt bei komplexem Reasoning und Coding, Claude Haiku 4.5 liefert den höheren Token-Durchsatz und Claude Haiku 4.5 ist die kosteneffizienteste Wahl für große API-Workloads.

Häufig gestellte Fragen (FAQ)

Welches Modell ist besser für Coding und Reasoning – Claude Sonnet 4.5 oder Claude Haiku 4.5?+

Im Gesamt-Intelligenzindex und bei Software-Benchmarks liegt Claude Sonnet 4.5 vorn. Prüfen Sie oben die SWE-bench- und GPQA-Werte für Ihren Anwendungsfall.

Wie unterscheiden sich die API-Preise von Claude Sonnet 4.5 und Claude Haiku 4.5?+

Claude Sonnet 4.5 kostet $3.00 / $15.00 pro 1M Input-/Output-Tokens, Claude Haiku 4.5 liegt bei $1.00 / $5.00. Beim gewichteten Gesamtpreis ist Claude Haiku 4.5 günstiger.

Welches Modell hat das größere Kontextfenster und die höhere Geschwindigkeit?+

Claude Sonnet 4.5 bietet 1M Tokens Kontext gegenüber 200K Tokens bei Claude Haiku 4.5. Bei der Generierungsgeschwindigkeit liegt Claude Haiku 4.5 vorn.

AI Terminology & Guide
Explore Glossary →

Understand key metrics like context window, token pricing, reasoning mode, and SWE-bench scores in our comprehensive AI glossary.

Tokens & PricingContext WindowAI BenchmarksReasoning ModelsTool CallingModel Context Protocol (MCP)

Related reading

Benchmark scores, token prices, and rate limits evolve rapidly as AI labs release model updates. Always verify current specifications and pricing on the official provider documentation.

Offizielle Quellen: Offizielle API-Dokumentation von Anthropic und Anthropic, Systemkarten und unabhängige Benchmark-Auswertungen (2026).