Claude/Mid-tier

Claude Sonnet 4.5

Claude Sonnet 4.5 is Claude's balanced performance model, priced at $3.00/MTok input and $15.00/MTok output with a 200K context window. Added 2026-09-27 after the backfill hold. Prices from the provider pricing page; 200K window (no long-context tier) from the provider context-windows page. Not yet benchmarked, so never recommended.

Input $/MTok

$3.00

Output $/MTok

$15.00

Context window

200K

Cache read discount

90% off

Claude Sonnet 4.5 pricing breakdown

RateInput $/MTokOutput $/MTok
Standard$3.00$15.00
Cached read (90% off input)$0.30-
Cached write (25% surcharge)$3.75-
Batch (50% off)$1.50$7.50

All rates in USD per million tokens. Prices verified against provider documentation.

Claude Sonnet 4.5 task benchmarks

Confidence scores (0-100) and cross-provider rank for each task type. Rank 1 is best across all 73 models.

Not benchmarked. The third-party benchmark source used for confidence scores does not cover Claude models yet. Scores will appear here once independent benchmarks are published.

Claude Sonnet 4.5 cost by use case

Estimated cost per API call using default token counts for each workload.

Use caseInput tokensOutput tokensCost / call
Code Generation2,0004,000$0.0660
Unit Test Generation3,0005,000$0.0840
SQL Generation1,5001,000$0.0195
API Generation3,0006,000$0.0990
Code Refactoring4,0004,000$0.0720
Code Review5,0002,000$0.0450
PR Review8,0003,000$0.0690
Security Review6,0002,500$0.0555
Bug Detection5,0002,000$0.0450
Document Summarization10,0001,000$0.0450
PDF Summarization15,0001,500$0.0675
Meeting Notes8,0002,000$0.0540

Monthly cost projections

Projected monthly spend at different call volumes, using code generation as a representative workload (2,000 input / 4,000 output tokens per call).

Calls / monthWithout cachingWith caching (90% read discount)
1K$66$62.22
10K$660$622.2
100K$6,600$6,222
500K$33,000$31,110
1M$66,000$62,220

Caching estimate assumes 70% of input tokens are cache reads. Your actual cache hit rate will depend on prompt structure and reuse.

Mid-tier alternatives to Claude Sonnet 4.5

Same-tier models from other providers, sorted by input price.

ModelProviderInput $/MTokOutput $/MTokInput savings
GPT 5GPT$1.25$10.0058% cheaper
GPT 5.1GPT$1.25$10.0058% cheaper
Gemini 2.5 ProGemini$1.25$10.0058% cheaper
Grok 4.3Grok$1.25$2.5058% cheaper
Grok 4.20 Non-ReasoningGrok$1.25$2.5058% cheaper
Grok 4.20 ReasoningGrok$1.25$2.5058% cheaper
Grok 4.20 Multi-AgentGrok$1.25$2.5058% cheaper
GPT 5.2GPT$1.75$14.0042% cheaper
GPT 5.6 TerraGPT$2.00$12.0033% cheaper
GPT 4.1GPT$2.00$8.0033% cheaper
o3GPT$2.00$8.0033% cheaper
Gemini 3.1 ProGemini$2.00$12.0033% cheaper
Gemini 3.1 Pro Custom ToolsGemini$2.00$12.0033% cheaper
GPT 5.4GPT$2.50$15.0017% cheaper
GPT 4oGPT$2.50$10.0017% cheaper

Track your Claude Sonnet 4.5 spend

See exactly how much you spend on Claude Sonnet 4.5 and where you can save. Two-line wrapper install, no API keys shared.