> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.cohere.com/v1/changelog/advanced-retrieval-launch/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.cohere.com/_mcp/server.

# Advanced Retrieval Launch release

> Rerank 3 offers improved performance and inference speed for long and short documents with a context length of 4096.

We're pleased to announce the release of [Rerank 3](/docs/rerank) our newest and most performant foundational model for ranking. Rerank 3 boast a context length of 4096, SOTA performance on Code Retrieval, Long Document, and Semi-Structured Data. In addition to quality improvements, we've improved inference speed by a factor of 2x for short documents (doc length \< 512 tokens) and 3x for long documents (doc length \~4096 tokens).

> Cohere's API documentation helps developers easily integrate natural language processing and generation into their products.