◉CLAUDE LABJP
●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
TAG

Multi-tenant

3 articles
← Back to all tags
Related:
production2Managed Agents1Agent SDK1MCP1Operations1Claude API1SaaS1cost attribution1rate limiting1Row Level Security1TypeScript1claude-api1
⬡ API & SDK/2026-07-24Advanced

Running Four Sites From One Managed Agent Definition

A design for collapsing four near-identical Managed Agents into one base definition, using agent version pinning and session-local overrides — with a validated factory and the traps I hit along the way.

⬡ API & SDK/2026-06-17Advanced

Making the Numbers Add Up in a Multi-Tenant Claude API SaaS — Field Notes on Isolation and Cost Attribution

The first thing that breaks when you make a Claude API SaaS multi-tenant is the month-end reconciliation. Here are field notes on a single metering chokepoint, atomic counters, reconciling against Anthropic's bill, and proving tenant isolation with adversarial tests — with production TypeScript.

⬡ API & SDK/2026-04-29Advanced

Production Semantic Cache for Claude API — Similarity Thresholds, Pollution Defense, and What to Track

A production playbook for adding a semantic cache in front of Claude API — threshold tuning, multi-tenant isolation, pollution prevention, fallbacks, and the metrics that actually prove it works.