Character counts won't predict PDF input tokens — bracket the cost per page before you send
How to estimate the input tokens of a PDF before sending it to the Claude API, by bracketing from page count rather than character count. Includes a measured 6.6x gap on a nine-page A4 document, the two separate increases that come with current models, and the count_tokens limitation that bites when you use file_id.
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.
Handing Monthly Revenue CSVs to the Claude API Code Execution Tool — Files API Wiring, Container Reuse, and Billing Traps
How I moved monthly revenue-CSV reconciliation into the Claude API Code Execution tool — a pre-upload sanity check, Files API integration, container reuse, the 5-minute billing minimum, and the file recovery that pause_turn quietly drops.
Stabilizing Claude API Structured Responses in Production — Notes on tool_use, JSON Schema, and Layered Validation
Getting Claude to return JSON takes a few lines. Keeping that JSON usable in production is a different problem. Here is the layered design I landed on after running a wallpaper classification pipeline through Claude API, built around tool_use, JSON Schema, and domain validation.
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.
Designing a Model-Selection Fallback That Survives this model is currently unavailable on Claude API
When Claude API answers 'this model is currently unavailable', treating it like a 529 Overloaded or a rate limit sends you the long way round. Here is how I tell the rejections apart by SDK exception class, switch model IDs per request, and the assumptions I had to fix along the way.
Why tool_result could not be submitted Keeps Coming Back, and How to Build a Recovery Handler That Actually Holds
Run a Claude agent long enough and one day it starts: 'tool_result could not be submitted', back to back, and retries change nothing. The error message hides four completely different root causes. Here is what I learned debugging it on the always-on agent jobs I run as an indie developer, with the TypeScript recovery handler I now ship in production.
Hierarchical Chat History Summarization with Claude API: A 3-Tier Design That Cut Tokens by 70%
Working TypeScript design for compressing long in-app chat histories into three tiers — recent turns kept verbatim, mid-range episodes summarized with Haiku 4.5, and long-range memory distilled to JSON by Sonnet 4.6. Includes seven weeks of production data showing input tokens down 70% and monthly API cost down from $480 to $145.
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.
Bulletproof JSON Output with Claude API Prefill: A Four-Layer Defense Pattern from Indie SaaS
How I went from late-night JSON parse failures to a 99.98% parse success rate across thousands of monthly Claude API requests, and what a 1,081-sample truncation benchmark revealed about the repair code I had originally published here.
A Five-Layer Preflight Design for Claude API — How I Cut Hundreds of 400/422/529 Errors to Zero
A production-tested five-layer preflight design that catches Claude API failures before the network call — schema, token budget, model capability, content policy, and spend cap — with full TypeScript implementation and one month of operational numbers.
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.