docs/provider-config/anthropic.mdx
Website: https://www.anthropic.com/
Cline supports the following Anthropic Claude models:
claude-opus-4-7 - Most capable Opus model, best for complex reasoning and long-horizon tasksclaude-opus-4-7:1m - 1M context window variantclaude-sonnet-4-6 - Latest Sonnet with extended thinking supportclaude-sonnet-4-6:1m - 1M context window variant with tiered pricingclaude-sonnet-4-5-20250929 (Recommended) - Stable default Sonnet with reasoning supportclaude-sonnet-4-5-20250929:1m - 1M context window variant with tiered pricingclaude-haiku-4-5-20251001 - Fast, affordable model with reasoning supportclaude-sonnet-4-20250514 - High-performance coding and reasoningclaude-sonnet-4-20250514:1m - 1M context window variantclaude-opus-4-6 - Previous Opus generationclaude-opus-4-6:1m - 1M context window variantclaude-opus-4-5-20251101 - Earlier Opus releaseclaude-opus-4-1-20250805 - Earlier Opus releaseclaude-opus-4-20250514 - Original Opus 4claude-3-7-sonnet-20250219 - Extended thinking supportclaude-3-5-sonnet-20241022 - Previous generation Sonnetclaude-3-5-haiku-20241022 - Fast and affordableclaude-3-opus-20240229 - Previous generation Opusclaude-3-haiku-20240307 - Most affordable Claude modelSee Anthropic's Model Documentation for more details on each model's capabilities.
Anthropic models offer an "Extended Thinking" feature, designed to give them enhanced reasoning capabilities for complex tasks. This feature allows the model to output its step-by-step thought process before delivering a final answer, providing transparency and enabling more thorough analysis for challenging prompts.
When extended thinking is in Cline, the model generates thinking content blocks that detail its internal reasoning. These insights are then incorporated into its final response.
Cline users can leverage this by checking the Enable Extended Thinking box below the model selection menu after selecting a Claude Model from any provider.
Key Aspects of Extended Thinking:
thinking blocks, can be streamed.For comprehensive details on how extended thinking works, including API examples, interaction with tool use, prompt caching, and pricing, please refer to the official Anthropic documentation on Extended Thinking.