Anthropic Frontier Flagship Live Rates • September 2026

Claude Sonnet 5 Pricing & Token Economics

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.

Context Window 1M
Max Completion 128K Tokens
Inference Speed Fast
CostRatio Score A

Normalized Token Pricing Matrix

Real-time input, completion, and cache rates normalized to $/1M tokens.

📥 Prompt Tokens
$ 2.00 / 1M tokens

Cost for prompts, instructions, document retrieval, and system context sent into the model.

~$0.0020 per 1K tokens
📤 Completion Tokens
$ 10.00 / 1M tokens

Cost for generated text, code, tool calls, and structured JSON responses returned by the model.

~$0.0100 per 1K tokens
⚡ Prompt Caching
$ 0.200 / 1M tokens

Massive 90% savings on repeated context, documents, and system instructions.

Cached Read Discount
⚖️ 3:1 Blended Benchmark
$ 4.000 / 1M tokens

Standard industry benchmark assuming 75% prompt reads and 25% completion generation.

Weighted Benchmark

Claude Sonnet 5 Monthly Bill Estimator

Estimated monthly costs across four standardized enterprise and developer workloads.

Workload Scenario Monthly Token Volume Standard Bill With Prompt Caching
💬
Customer Support Chatbot
10M prompt tokens + 2.5M output tokens per month
12.5M tokens (10M in / 2.5M out) $45.00/mo $32.40/mo -28%
📑
Document Analysis & RAG
30M prompt tokens (PDFs/context) + 3M output summaries
33.0M tokens (30M in / 3M out) $90.00/mo $52.20/mo -42%
💻
Coding Agent / IDE Swarm
60M prompt tokens (repo context) + 15M code completions
75.0M tokens (60M in / 15M out) $270.00/mo $194.40/mo -28%
🤖
Enterprise Agentic Workflow
120M prompt tokens (reasoning loops) + 30M output actions
150.0M tokens (120M in / 30M out) $540.00/mo $388.80/mo -28%

Need custom token inputs or prompt volumes?

Use our interactive multi-model token calculator to test exact prompt and completion sliders.

Open Interactive Token Calculator →

Architecture & Capabilities

Technical parameters, supported modalities, and optimal developer use cases.

🎯 Recommended Use Cases

Complex software architecture, full-repo autonomous agents, advanced reasoning

Supported Modalities

📝 Text 👁️ Vision & Images 🛠️ Function / Tool Calling

📐 Context & Output Limits

  • Maximum Context Window: 1,000,000 tokens (1M)
  • Maximum Output Length: 128,000 tokens
  • Speed / Latency Tier: Fast
  • Official Provider: Anthropic

Frequently Asked Questions

Everything you need to know about Claude Sonnet 5 API pricing and token calculations.

How much does Claude Sonnet 5 cost per 1M tokens?

Claude Sonnet 5 charges $2.00 per 1M input tokens and $10.00 per 1M output tokens. For standard balanced workloads (3:1 input:output ratio), the effective blended rate is $4.000/1M tokens.

Does Claude Sonnet 5 support prompt caching?

Yes. Cached prompt reads are billed at $0.2000 per 1M tokens, saving you up to 90% on repeated context, RAG documents, and system instructions.

What is Claude Sonnet 5's maximum context window?

Claude Sonnet 5 supports up to 1,000,000 tokens (1M) in its context window, allowing you to ingest large files and multi-turn chat history with up to 128,000 tokens generated per response.

How does Claude Sonnet 5 compare to other models?

With a CostRatio rating of A, Claude Sonnet 5 provides competitive token economics for frontier flagship tasks. Review the peer comparison table above to compare input and completion rates directly against alternative models.

Explore all latest-generation models and interactive calculators

View Full AI Model Matrix →