Source Intelligence
Reading a new release v2.1.251 Analysing changes · 2/5 Deeper second pass · 0/5 agents 427 findings $12.75 so far

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

All of v0.2.101 Home All releases olderv0.2.100 v0.2.102newer

Usage Examples

Setting a preferred model:

# Via environment variable
export ANTHROPIC_MODEL="claude-3-7-sonnet"
claude "Help me write a Python script"

# The CLI will use Claude 3.7 Sonnet for this request

Using platform-specific routing:

# For AWS Bedrock
export CLAUDE_CODE_USE_BEDROCK=true
claude "Analyze this codebase"

# For Google Cloud Vertex
export CLAUDE_CODE_USE_VERTEX=true
claude "Review this pull request"

The model selection interface provides clear pricing information and performance characteristics to help users choose the most appropriate model for their needs.

See this entry in the whole of v0.2.101 →