A 75% cheaper cache read moved one bill by 29% and another by 2.8%
Fable 5.1 and Mythos 5.1 changed the cache read multiplier from 0.1 to 0.025. Here is how to estimate your own saving from your token mix, and how to fix code that hard-codes the multiplier.
I decide the prompt cache TTL by where I come back to, not how long I was away
Claude Code v2.1.242 added promptCacheTtl and subagentPromptCacheTtl. Whether the one-hour cache pays off depends on returning to the same directory and the same git state, not on how long the break was. Here is the order I check things in.
A Two-Tier Setup — Haiku 4.5 Orchestrator with Opus 4.6 Worker for Balancing Cost and Quality
An indie developer's two-tier setup — Haiku 4.5 as orchestrator, Opus 4.6 as worker — costed line by line against published rates, plus the price increase I planned around that never arrived and the tokenizer split that quietly moves every token-denominated threshold.
Cutting Claude API Costs in Half with Messages Batches API — Design Patterns from an Indie Developer
How to reduce Claude API costs by up to 50% using the Messages Batches API. Includes async design patterns, real cost calculations, and production-ready error handling from an indie developer's own workloads.
Design Decisions Every Indie Developer Faces When Integrating Claude API into Mobile Apps
The design decisions indie mobile developers hit when integrating Claude API — model selection, async UX, context management, offline resilience, and cost control — with working code and a per-user cost table recalculated for the September 2026 price change.
The Real Cost of Claude API Extended Thinking in Production — ROI Data by Task Type
Three months of measured cost, quality, and speed data for Extended Thinking across five task categories. Learn exactly when extended thinking is worth it—and when it's not.
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, how it stacks with Anthropic's prompt caching, and the metrics that actually prove it works.
How I Cut My Claude API Bill in Half With Prompt Caching
Done right, Anthropic's prompt caching can roughly halve your monthly API spend on workloads with long, repeated system prompts. Here is the design playbook I use after six months in production, including the arithmetic that links hit rate to the bill and the break-even points (about 22% on the 5-minute TTL, 53% on the 1-hour TTL).
Using tool_choice to Cut Wasted Inference: Four Modes and Cost Patterns for Production
tool_choice is one of the most underused parameters in the Claude API. The four modes — auto, any, tool, and none — each change both behavior and token cost. Here are the patterns I reach for in production, with runnable code.
Intelligent Model Routing with Claude API — Auto-Selecting Sonnet 4.6 and Haiku 4.5 for Optimal Cost and Quality
Build an intelligent routing layer that automatically selects between Claude Sonnet 4.6 and Haiku 4.5 based on request complexity. Covers classifier design, circuit breakers, fallback chains, and cost monitoring for production deployments.
Running Claude Sonnet 4.6 in Production While Scouting the Move to Sonnet 5
Claude Sonnet 4.6 shipped February 17, 2026 and is now legacy, with retirement no sooner than February 17, 2027. Real prices against Opus 4.6, the 1M context, thinking, Computer Use, and the five places a Sonnet 5 migration returns 400.
Claude Haiku 4.5 — Build Real-Time AI Apps at a Fraction of the Cost
Claude Haiku 4.5: 200K context, SWE-bench 73.3%, Extended Thinking, $1/$5 pricing. When to use Haiku vs Sonnet/Opus, with Prompt Caching and Batch API tips.