Reading path · 12 stops · 44 min of reading · 8 tools and data pages

AI API costs, and how to cut them.

What you'll learnWhat models really cost per job, how to count tokens, and the caching, retry and proxy tricks that cut the bill.

Start with part 1 →See every stop

Not started

The path, in order

Topics: LLMs, Coding agents. Ticks show what you have read in this browser.

1. DataLLM API prices, and the cheapest model for your job

   LLM API pricing for 71 models per 1M tokens, checked at the source. Pick for me: your job, volume and budget give 3 models with the monthly cost. Filters, CSV.

2. Free toolToken counter

   Exact GPT token counts, labelled Claude and Gemini estimates, cost per request on 24 models.

3. Free toolLLM API cost calculator

   Tokens in, tokens out, requests a day: monthly cost on 24 GPT, Claude and Gemini models.

4. Article · 3 minI stopped paying twice for the same LLM answer (and why embeddings alone can't dedupe prompts)

   Retries, double clicks and parallel workers send the same prompt twice. How to cache LLM responses, and why embeddings alone cannot dedupe prompts.

5. Article · 16 minLLM proxy benchmark: 200 duplicate calls became 1 (and a 30 s bug)

   I put a Rust LLM proxy in front of the OpenAI SDK: 200 duplicate calls became 1, outage calls fell 89 to 5, and a test found a 30 s serialization bug.

6. Article · 13 minExponential backoff with jitter: 64 of 100 LLM calls still failed

   100 LLM calls hit a rate limit at once. Backoff with 10% jitter answered 36. Retry-After answered all in 11.8 s; a client-side limiter in 8.0 s, zero 429s.

7. Article · 12 minLLM JSON output: one setting dropped valid JSON from 75% to 4%

   432 real replies from 3 small LLMs in Chrome: no_repeat_ngram_size took valid JSON from 75% to 4%. The fix, a 4-step parse ladder and a free repair tool.

8. Free toolLLM JSON repair

   Paste a model reply, get valid JSON: fences, prose, bare keys, cut-off replies.

9. DataClaude vs GPT API pricing

   Anthropic vs OpenAI API pricing: every listed model priced on the same chatbot and coding-agent workloads, closest-price matches, cheapest of each. Checked Oct

10. DataDeepSeek vs Claude API pricing

    DeepSeek vs Anthropic API pricing: every listed model priced on the same chatbot and coding-agent workloads, closest-price matches, cheapest of each. Checked Oc

11. DataLLM API Price Index

    LLM API Price Index, a monthly Tensorust report. What 1,000 requests cost across every listed OpenAI, Anthropic, Google and DeepSeek model, indexed to the first

12. DataLLM API price changes

    Every LLM API price change we have recorded for 71 OpenAI, Anthropic, Google and DeepSeek models, dated and linked to the provider page, plus announced price ch

When you finish

Paths that pick up where this one stops.

Reading path · 5 stops

Run models yourself

When open weights pay off: browser inference, the RAM a giant model needs, and the parts of an inference stack nobody gives away.

Not started

Start the path →

Reading path · 9 stops

Coding agents that do not cheat

When agents edit tests instead of code, how to make that impossible, how to review their output and keep your keys safe.

Not started

Start the path →

All reading paths →   All articles →