Tools Howto
A 429 is free. The ninth retry is not.
A 429 bills you nothing - the request never reaches the model. The cost arrives when your backoff outlives the cache TTL and the cold retry burns 101x the limit.
Tag Independent editorial
Tag / openai
8 posts tagged "openai".
8
2
16min avg
About
Every post tagged "openai" in the journal. Tag archives are auto-generated from post frontmatter -- one entry per unique tag across non-draft posts. Currently 8 posts share this tag. Use the category filter above to scope by editorial type.
§ Filter by category
Category
Editor's pick
1 of 8 Showing 7 of 8 posts — page 1 of 1
Tools Howto 02
input_tokens means three different things. Your cost function knows one of them.
Anthropic's input_tokens excludes cached tokens, OpenAI's includes them. Port a cost function between the two and a $0.082 request bills $0.378. Fields, traps, code.
Tools Howto 03
The Batch API discount isn't 50% -- and it isn't always a discount
Batch halves token rates at OpenAI, Anthropic and Google -- but takes 20% at SpaceXAI and nothing on its flagship. When batch beats a warm cache, and when it costs more.
Tools Howto 04
How to actually get prompt cache hits (and why yours are missing)
Prompt caching fails silently -- no error, no warning, just a full-price bill. The floors, the breakpoint rules, and everything that quietly invalidates a cache.
Analysis 05
Routing by task complexity: what the 2026 evidence actually shows
Ten routers launched on HN in five weeks. The peer-reviewed 2026 benchmarks say they barely beat a baseline. The arithmetic that decides it, on verified rates.
Analysis 06
Hidden LLM API costs nobody quotes (2026)
The $/M input/output sticker hides cache-write premiums, a tokenizer tax, context surcharges, invisible reasoning tokens, and more. Ten verified costs, with proofs.
Analysis 07
The reasoning dial nobody touches: why your thinking-model bill is so high
In 2026 the biggest lever on your LLM bill isn't which model. It's how hard the model thinks: reasoning tokens bill as output, and most models think by default.
Analysis 08
How prompt caching actually changes the LLM cost math
Anthropic charges 10% of input for cache reads, with a 1.25x write fee. OpenAI auto-caches above 1024 tokens. The math changes which LLM is cheapest -- here is when.