●MODEL — Claude Fable 5.1 and Claude Mythos 5.1 arrived on September 1. They are the same model; only the level of safeguards differs between them●PRICING — Cache reads dropped 75%, from $1.00 to $0.25 per million tokens. Anthropic measures that as roughly 25% lower cost on typical workloads and up to 45% on agentic ones●CAVEAT — Only cache reads got cheaper. Base input stays at $10 and output at $50, so the savings land on setups that re-read the same long context, not on one-off prompts●API — The model ID is claude-fable-5-1, generally available through the Claude API as well as AWS, Google Cloud, and Microsoft Azure●EFFORT — At low and medium effort it matches or beats Fable 5; at higher effort it pulls further ahead. The choice is the same result for less, or more reach for the same spend●CLI — Claude Code v2.1.263 shipped on September 6 with a single CLI change: fewer crashes and steadier commands. No new features in this one●MODEL — Claude Fable 5.1 and Claude Mythos 5.1 arrived on September 1. They are the same model; only the level of safeguards differs between them●PRICING — Cache reads dropped 75%, from $1.00 to $0.25 per million tokens. Anthropic measures that as roughly 25% lower cost on typical workloads and up to 45% on agentic ones●CAVEAT — Only cache reads got cheaper. Base input stays at $10 and output at $50, so the savings land on setups that re-read the same long context, not on one-off prompts●API — The model ID is claude-fable-5-1, generally available through the Claude API as well as AWS, Google Cloud, and Microsoft Azure●EFFORT — At low and medium effort it matches or beats Fable 5; at higher effort it pulls further ahead. The choice is the same result for less, or more reach for the same spend●CLI — Claude Code v2.1.263 shipped on September 6 with a single CLI change: fewer crashes and steadier commands. No new features in this one