Claude Sonnet 3.5

anthropic

Claude's breakthrough mid-tier model from 2024, setting new standards for intelligence at its price point. The original June 2024 release and October 2024 update both delivered exceptional coding, analysis, and multimodal capabilities with 200K context and 8K output. The v2 update added computer use and PDF support. Both versions have been retired and are no longer available for use.

Try Now

Capabilities

Tool Use

PDF Input

Image Input

Example Use Cases

Advanced coding at sonnet-tier pricing

Document and pdf analysis with vision

Computer use and agentic browser tasks

Technical Specifications

Context Window

200,000 tokens

Max Output

8,192 tokens

Cache Miss Cost

$3 per 1M tokens

Non-Reasoning Cost

$15 per 1M tokens

Cache Read Cost

$0.30 per 1M tokens

Cache Write Cost

$3.75 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Retired model

Recommended Replacement

Claude Opus 4.6