Head-to-Head Model Comparison

Claude Sonnet 4.5 vs Claude Haiku 4.5

Benchmarks, API Token Pricing, Context Window & Speed Comparison

Ditinjau oleh tim riset GetInfoUsPeninjauan terakhir: October 2026Kebijakan editorial

Ganti & Bandingkan Model Apa Saja

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

Claude Sonnet 4.5Profile

Claude Haiku 4.5Profile

Multi-Model Arena Stack:

5-Model Matrix Workbench

Popular Matchups:

Anthropic

Claude Sonnet 4.5

Model Unggulan Garis Depan

Claude Sonnet 4.5 dari Anthropic adalah model AI yang dirancang untuk penalaran perusahaan garis depan, pemrograman tingkat lanjut, dan produksi AI, menghadirkan jendela konteks 1M, kecepatan 90 token/detik, indeks kecerdasan 91/100, serta

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

Inferensi Super Cepat

Claude Haiku 4.5 dari Anthropic adalah model AI yang dirancang untuk interaksi real-time dengan latensi sangat rendah dan routing bervolume tinggi, menghadirkan jendela konteks 200K, kecepatan 140 token/detik, indeks kecerdasan 54/100, sert

Intelligence Index54 / 100

Input Token:

$1.00 / 1M

Output Token:

$5.00 / 1M

Context Window:

200K tokens

SWE-bench Verified:

58.2%

Perbedaan Utama Sekilas

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 →

Feature	Claude Sonnet 4.5	Claude Haiku 4.5
Intelligence Index Composite reasoning & knowledge score (0-100)	91	54
Provider	Anthropic	Anthropic
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 text	200K tokens~300 A4 pages of text
Max Output Tokens Per single request	64K	64K
Throughput Speed Tokens generated per second	90 tok/s	140 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

Siapa Unggul di Mana?

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

Skor Benchmark Terverifikasi

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

Latensi & Waktu Respons

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

Simulator Biaya Token Interaktif

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

Daily Input Tokens100K / day

10K500K1M

Daily Output Tokens30K / day

5K150K300K

Prompt Cache Hit Ratio50% 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

Jendela konteks 1M dengan kapasitas output maksimum hingga 64K token (SWE-bench Verified 77.8% · GPQA Diamond 70.2%)
Kecepatan generasi tinggi 90 token/detik dengan latensi token pertama (TTFT) hanya 900 ms
Skema harga API kompetitif (tarif $3/$15 per 1M token) dengan dukungan cache prompt dan output JSON terstruktur

Considerations & Trade-offs

Model cloud proprietari tertutup; bobot model tidak dapat diunduh untuk penggunaan lokal offline
Untuk trafik produksi skala besar, disarankan mengaktifkan fitur Prompt Caching dan Batch API guna menghemat biaya

Claude Haiku 4.5 · Strengths & Key Advantages

Jendela konteks 200K dengan kapasitas output maksimum hingga 64K token (SWE-bench Verified 58.2% · GPQA Diamond 62.1%)
Kecepatan generasi tinggi 140 token/detik dengan latensi token pertama (TTFT) hanya 280 ms
Skema harga API kompetitif (tarif $1/$5 per 1M token) dengan dukungan cache prompt dan output JSON terstruktur

Considerations & Trade-offs

Model cloud proprietari tertutup; bobot model tidak dapat diunduh untuk penggunaan lokal offline
Pada tugas pembuktian ilmiah tingkat ekstrem, model penalaran berat kelas atas memberikan kedalaman lebih tinggi

Token Use & Task Economics

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

Metric	Claude Sonnet 4.5	Claude Haiku 4.5
Cost per Task Estimated USD to finish one task	$2.10	$0.70
Output Tokens / Task Tokens generated per task	55K	20K
Reasoning Tokens / Task Thinking tokens burned per task	30K	10K

Spesifikasi Teknis

Architecture, release timeline, capabilities, and modalities.

Claude Sonnet 4.5 vs Claude Haiku 4.5: Jawaban Cepat (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.

Kesimpulan

Baik Claude Sonnet 4.5 (Sangat cocok untuk penalaran perusahaan garis depan, pemrograman tingkat lanjut, dan produksi AI, sistem RAG perusahaan, dan integrasi API skala produksi.) maupun Claude Haiku 4.5 (Sangat cocok untuk interaksi real-time dengan latensi sangat rendah dan routing bervolume tinggi, sistem RAG perusahaan, dan integrasi API skala produksi.) sangat tangguh: Claude Sonnet 4.5 unggul dalam penalaran dan pemrograman, Claude Haiku 4.5 memberikan kecepatan generasi token lebih tinggi, dan Claude Haiku 4.5 lebih hemat biaya untuk penggunaan API skala besar.

Pertanyaan Umum (FAQ)

Mana yang lebih baik untuk coding dan penalaran, Claude Sonnet 4.5 atau Claude Haiku 4.5?+

Dalam indeks kecerdasan gabungan dan benchmark coding, Claude Sonnet 4.5 memimpin. Lihat skor SWE-bench dan GPQA di atas untuk detailnya.

Berapa perbandingan harga API Claude Sonnet 4.5 vs Claude Haiku 4.5?+

Claude Sonnet 4.5 mengenakan biaya $3.00 / $15.00 per 1M token input/output, sedangkan Claude Haiku 4.5 sebesar $1.00 / $5.00. Secara keseluruhan, Claude Haiku 4.5 lebih hemat biaya.

Model mana yang memiliki jendela konteks lebih besar dan kecepatan lebih tinggi?+

Claude Sonnet 4.5 mendukung konteks 1M token dibandingkan 200K token pada Claude Haiku 4.5, sementara Claude Haiku 4.5 unggul dalam kecepatan output token per detik.

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 & Pricing Context Window AI Benchmarks Reasoning Models Tool Calling Model Context Protocol (MCP)

Feature	Claude Sonnet 4.5	Claude Haiku 4.5
Official API Model ID (SDK)	claude-sonnet-4-5-20251101	claude-haiku-4-5-20251001
API Protocol	Anthropic Messages API + AWS Bedrock + Vertex AI	Anthropic Messages API + AWS Bedrock + Vertex AI
Release Date	2025-11	2025-10
Knowledge Cutoff	March 2025	July 2025
Architecture	Hybrid Reasoning	Lightweight High-Speed Multimodal Transformer
Parameters	Confidential	Confidential
Enterprise Rate Limits (RPM / TPM)	4,000 – 10,000 RPM (Tier 4 + Priority Tier) · 4,000,000 – 10,000,000 TPM	4,000 – 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 tokens	Standard 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 Agent	Supported (Screen coordinate grounding, browser & desktop GUI action loops)	Supported (Screen coordinate grounding, browser & desktop GUI action loops)
MCP & Parallel Tool Calling	Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema	Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
Web Search Grounding & Sandbox	Native Web Search Citations + Code Execution Tool + MCP Connectors	Native Web Search Citations + Code Execution Tool + MCP Connectors
Official Fine-Tuning Support	Custom Model Tuning via Amazon Bedrock & Prompt Distillation	Custom Model Tuning via Amazon Bedrock & Prompt Distillation
Multimodal Token Billing	Text 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 VRAM	Cloud-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 Classification	Anthropic RSP ASL-2 / ASL-3 Constitutional Safety Evaluated	Anthropic 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 Tier	SOC2 Type II · GDPR · Zero Data Retention (ZDR) & HIPAA BAA Available on Enterprise Tier
Input Modalities	text, vision	text, vision
Output Modalities	text	text

Claude Sonnet 4.5 vs Claude Haiku 4.5

Ganti & Bandingkan Model Apa Saja

Claude Sonnet 4.5

Claude Haiku 4.5

Siapa Unggul di Mana?

Skor Benchmark Terverifikasi

Latensi & Waktu Respons

Simulator Biaya Token Interaktif

Claude Sonnet 4.5 · Strengths & Key Advantages

Considerations & Trade-offs

Claude Haiku 4.5 · Strengths & Key Advantages

Considerations & Trade-offs

Token Use & Task Economics

Spesifikasi Teknis

Claude Sonnet 4.5 vs Claude Haiku 4.5: Jawaban Cepat (FAQ)

Kesimpulan

Pertanyaan Umum (FAQ)

Related reading