Model Details

Claude Sonnet 4.6 Thinking API

Advanced reasoning with extended thinking capabilities. Perfect for complex problem-solving, code generation, and analytical tasks.

Pricing Comparison

ProviderInput / 1MOutput / 1MCache / 1M
Anthropic Official$3.00$15.00$0.30
Crouter$0.42$3.00$2.10$15.00$0.08$0.30
You Save86%86%73%

All prices per 1M tokens. No hidden fees, no monthly minimums.

Key Features

Extended Thinking

Internal reasoning process for complex problems. Sonnet thinks through multi-step tasks before responding, improving accuracy.

1M Context Window

Process entire codebases, long documents, and extended conversations. Five times larger than Haiku context window.

Advanced Code Generation

Write production-ready code with proper error handling, testing, and documentation. Understands complex architectures.

Prompt Caching

Save 73% on repeated context with automatic caching. Ideal for applications with large system prompts or documentation.

Perfect For

AI Coding Assistants

Power tools like Cursor, Windsurf, and Claude Code with advanced reasoning. The 1M context handles entire project codebases.

Complex Problem Solving

Analyze multi-step problems with extended thinking. Sonnet breaks down complex tasks and provides structured solutions.

Technical Writing

Generate documentation, API references, and technical guides. Maintains consistency across large documentation sets.

Research Analysis

Analyze research papers, extract insights, and synthesize findings. The 1M context processes multiple papers simultaneously.

Technical Specifications

Model IDclaude-sonnet-4-6-thinking
Context Window1,000,000 tokens
API FormatAnthropic Messages API (/v1/messages)
Thinking ModeExtended (automatic)
StreamingYes (SSE)
Prompt CachingYes (automatic)
Rate Limit70 requests/minute

Quick Start

curl https://api.crouter.dev/v1/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-6-thinking",
    "max_tokens": 4096,
    "messages": [
      {"role": "user", "content": "Explain quantum computing"}
    ]
  }'

View full documentation for more examples and integration guides.

Ready to start building?

Get your API key in 30 seconds. Works with all major AI tools and frameworks.