The guides
Every Culpa guide
41 guides on finding, attributing and forecasting LLM spend. Every cost figure on this site carries its confidence and its source.
Metrics and definitions
What is cost per conversation?
Cost per conversation is the total model spend for one full exchange, retries and tool calls included. Definition, the arithmetic, and how to measure it.
What is cost per feature?
Cost per feature is model spend grouped by the product surface that triggered it. Why provider data can't produce it, and how to tag calls so it can.
What is effective cost?
Effective cost is your real blended rate per token after caching, retries and failed calls. Why it always runs above the list price, with worked math.
What is token accounting?
Token accounting is tracking input, output and cached tokens per call and pricing them exactly. Why rounding and float math corrupt LLM cost data.
What is a blended rate?
A blended rate is your average cost per token across every model you run. Useful for forecasting, dangerous for optimisation. Worked example inside.
What is gross margin per customer?
Gross margin per customer is revenue minus what that customer costs you in model spend. How to compute it per account and why averages hide losses.
What is an LLM burn forecast?
An LLM burn forecast projects model spend forward from your own usage curve. What makes one credible, and the three inputs teams usually get wrong.
What is LLM cost attribution?
LLM cost attribution links each dollar to the call, conversation, feature and customer behind it. Why it has to happen at request time, not in reporting.
What is prompt cache hit rate?
Prompt cache hit rate is the share of input tokens billed at the cached rate. Why a low rate wastes money and a high write rate can cost more.
What is cost per user?
Cost per user is model spend divided by active users, and the average lies. Why the 90th percentile sets your pricing floor, with worked math.
Cost problems and diagnostics
Why did my OpenAI bill go up?
Your OpenAI bill went up for one of four reasons: more calls, longer calls, a pricier model, or retries. How to tell which one, with the math.
What an LLM retry loop actually costs
A retry loop bills every attempt, including the ones that produced nothing you kept. How to price your retry waste and cap it, with worked math.
Agent fan out cost, and why one request becomes thirty calls
An agent turns one user request into many model calls, and cost grows with steps rather than requests. How to price agent fan out before it ships.
What a prompt cache miss costs you
A prompt cache miss bills your repeated tokens at full rate, and on some providers a cache write costs more than input. The math, and the fix.
Context creep cost, the increase nobody shipped on purpose
Context creep is the slow growth of prompt size across releases. It raises cost per call with no traffic change. How to measure and cap it.
Why your LLM cost spikes after a launch
A launch spike is rarely just traffic. Free-tier users, curiosity sessions and unbounded retries drive it. How to forecast and cap the next one.
LLM model mix drift, and why the bill moved without a deploy
Model mix drift is traffic quietly shifting toward pricier models. Volume holds, the bill climbs. How to detect it and price the shift.
LLM eval job cost, the spend with no customer attached
Evaluation runs bill like production but serve no customer. Why eval spend hides, how to price a run, and how to cut it without losing coverage.
Tool definition token cost, billed whether the tool runs or not
Tool schemas are input tokens billed on every call, whether the model uses them or not. How to price your tool block and trim it safely.
Unattributed LLM spend, and why it keeps growing
Unattributed spend is every dollar your breakdown can't assign to a feature or customer. Why it grows, and how to drive it toward zero.
Model pricing
GPT-5.4 pricing, and what it really costs per month
GPT-5.4 pricing is $2.50 per million input and $15.00 output, verified 2026-07-02. Output bills 6x input, with worked monthly math.
GPT-5.5 pricing, and when the premium earns itself
GPT-5.5 pricing is $5.00 per million input and $30.00 output, exactly double GPT-5.4. When the premium earns itself, with the break-even math.
GPT-5.4 mini pricing, and where the saving disappears
GPT-5.4 mini pricing is $0.75 per million input and $4.50 output, about a third of GPT-5.4. Where it saves money and where volume eats the saving.
GPT-5.4 Pro pricing, and the missing cached rate
GPT-5.4 Pro and GPT-5.5 Pro both bill $30 per million input and $180 output, with no cached rate. What that means for repeated prompts.
Claude Sonnet 5 pricing, and the rate change on 2026-09-01
Claude Sonnet 5 pricing is $2.00 per million input and $10.00 output on an introductory rate that ends 2026-08-31, rising 50% to $3.00 and $15.00.
Claude Opus 4.8 pricing, and why five versions cost the same
Claude Opus 4.8 pricing is $5.00 per million input and $25.00 output, identical to Opus 4.5, 4.6, 4.7 and Opus 5. Why the version upgrade is free.
Claude Haiku 4.5 pricing at a million calls a month
Claude Haiku 4.5 pricing is $1.00 per million input and $5.00 output, with cached reads at $0.10. The million-call tier where small errors get large.
Gemini 2.5 Flash pricing and the eight-to-one output spread
Gemini 2.5 Flash pricing is $0.30 per million input and $2.50 output, an 8.3x spread. Why answer format is the whole optimisation here.
Gemini 2.5 Pro pricing for long-context work
Gemini 2.5 Pro pricing is $1.25 per million input and $10.00 output, the widest output spread in this price book at 8x. Long-context math inside.
GPT-5.6 Terra pricing against the model it replaces
GPT-5.6 Terra pricing is $2.00 per million input and $12.00 output, undercutting GPT-5.4 by 20% on both sides. The migration math, worked.
GPT-5.6 Luna pricing at high call volume
GPT-5.6 Luna pricing is $0.20 per million input and $1.20 output, the cheapest OpenAI tier. Why volume, not rate, decides what it costs you.
Claude Fable 5 pricing and the cost of a cache write
Claude Fable 5 pricing is $10.00 per million input and $50.00 output, matched by Claude Mythos 5. The top Anthropic tier and what a cache write costs.
Provider cost
OpenAI API cost across the whole model line
OpenAI API cost runs from $0.20 to $30.00 per million input tokens, a 150x spread. Why model choice matters more here than on any other provider.
Anthropic API cost and the cache-write charge
Anthropic API cost runs $1.00 to $10.00 per million input, with every model at exactly 5x output. The only provider here charging for cache writes.
Gemini API cost and why output length dominates
Gemini API cost runs $0.25 to $2.00 per million input, with output spreads up to 8.3x. Why answer length is the lever on this provider.
Groq API cost and the flattest output ratios anywhere
Groq API cost runs $0.05 to $1.00 per million input, with output ratios as flat as 1.34x. Why the usual cost advice stops working here.
OpenRouter API cost and the cached rate you give up
OpenRouter re-lists Anthropic models at identical headline rates but records no cached rate. What routing costs you on a repeated prompt.
Pricing and margin
How to price an AI SaaS product on real unit costs
How to price an AI SaaS product: start from your 90th-percentile customer cost, not the average, and cap what sits beyond it. Worked math inside.
AI COGS, and what actually belongs in it
An AI COGS calculator totals model spend, retries and cache behaviour per customer. What belongs in cost of goods sold, and what doesn't.
Setting an AI usage cap that binds the right accounts
An AI usage cap calculator sets the ceiling from your 90th-percentile account, not the average. How to pick a cap that binds the tail and nobody else.
Pricing an unlimited AI plan against a tail you haven't measured
Pricing an unlimited AI plan means pricing against a maximum nobody has measured. What unlimited really costs, and the safer alternatives.