UsageTap Compress · measured prompts, modeled API spend
What compression saves—and what the answers retain
OriginalSelected compressionCompression fee
Quality alongside savings
| Benchmark | Metric | Before score | After score | Change | Pairs / questions | 95% source interval |
|---|
Observed means on the sampled questions, with each metric kept separate. Repeated calls are not independent documents. Both compression and generation variation can affect score changes; this cohort does not establish broad quality equivalence.
Intervals resample source documents, keeping shared-context questions and their three repeats together. They describe uncertainty in official-score changes across this sample, with no adjustment for five dataset comparisons. They do not establish semantic equivalence.
Supplementary semantic review
| Benchmark | Before | After | Change | Scored / eligible pairs | Uncertain pairs |
|---|
Supplementary model judgments, not official scores or proof of semantic equivalence. Exact source quotes support inspection; model agreement is not ground truth. Exact duplicate answers share one judgment, so repeated mapped judgments are not independent reviews. Reviewer rationales and evidence are available with each answer below.
Savings at other models’ API prices
Cost-only extrapolation from the same Terra prompt counts and observed output counts. No new model calls. These estimates do not measure Sol, Astra or Opus answer quality, latency, or tokenization; Claude’s actual tokenizer and responses can differ.
| Model | Input | Cached input | Output |
|---|
Projected before and after cost components
| Model | Before input | Before output | Before total | After input | After output | Compression | After total | Net saved | Saved % |
|---|
Context tokens
Proxy token counts; instructions and questions excluded.API-equivalent cost
Matched answer calls; after includes the modeled compression fee.Net savings by workload
After compression fees, under the current pricing scenario.Answer scores across repeats
Official task metric; points are individual calls. Compare within each task.Request-time estimate
Median Codex time plus recorded compression preparation time.Input cost and output cost
API prompt scenario, with output usage measured by Codex.Before and after: the cost ledger
| Input | Pairs | Before API | After API | Compression | After total | Net saved |
|---|
Pricing, cache and compression assumptions
Cache reads, ordinary input and writes are disjoint input categories. A 30-minute write costs 1.25× input; a 12-hour write costs 2.5×. The long-context rate adjustment is applied above 272k input tokens. Scenario controls alter estimates only; they never alter measured results. Changing an early prompt prefix can reduce cache reuse.
Exact token and cost components
| Input / stage | Prompt input | Output | Ordinary input $ | Cached reads $ | Cache writes $ | Output $ | Compression $ | Total $ |
|---|
Before = ordinary input + cached reads + cache writes + output
After = ordinary input + cached reads + cache writes + output + compression charge
Net saving = Before − After
See what compression removes
Original input with removed text struck through. The answer checks below show the measured quality for these tasks.
Original, with removals
Compression details
Answers and quality checks
The published benchmark score is retained exactly. Normalized exact match is supplementary. Review the answers alongside the references: equivalent wording, digits versus spelled-out numbers, and extra detail can affect lexical scores.
Lexical scores can penalize digits versus spelled-out numbers, such as “3” versus “three”; inspect the actual answers and references below. Net cost differences also include variation in output length between calls.
| Variant | Repeat | Status | Actual answer | Official score | Normalized exact match | Semantic review |
|---|
The cases are different tasks and use different metrics. Scores are never averaged across QA F1 and structured-data accuracy. Repeated calls share the same source input; they are not independent documents.
Experiment usage, provenance and limits
API dollar values are modeled estimates; answer generation ran through a Codex subscription. The primary cost comparison prices the application prompt and measured output, excluding Codex's agent instructions/tool envelope. The separate experiment diagnostic prices the complete CLI usage envelope. Output-token usage includes reasoning when reported; reasoning tokens are not added a second time. Prompt counts use a proxy tokenizer. Network and compression times vary with startup/cache conditions. Taxes, regional premiums, Batch/Flex discounts, Fast mode and unknown account-specific terms are excluded. The compression free allowance remaining is unknown; its toggle is a scenario.