AIYVO usage analysis
SYNTHETIC: fictitious example data, not customer data. No provider-verified billing used. No savings are claimed.
Records 672 · groups 5 · row kind request · currency USD · period 2026-09-28T00:00:00+00:00 to 2026-10-04T23:45:00+00:00
The value AIYVO uncovered
Figures are synthetic. Nothing here is a verified saving.
$50.00Total AI spend analyzed
Not yet quantifiedPotential savings identified
$10.73Spend requiring further reviewInvestigation spend, not recoverable savings
5Evidence-backed findings
Observed facts
The lowest price per request is not the lowest cost per successful request
Judged on price per request, provider_c/model-c1 has the lowest figure. Counting what failures cost, provider_b/model-b1 has the lowest cost per successful request ($0.0684 against $0.1474). A choice made on price per request alone would miss this. The groups served different requests, so this is an observation, not a recommendation.
Calculation and sources
- provider_c/model-c1: reported cost per request: $0.0147. reported cost of provider_c/model-c1's requests with a cost ÷ those requests. Sources: report.json groups[provider_c/model-c1].metrics.reported_cost_per_record; input file (SHA-256 under Provenance), reported_cost column (synthetic).
- provider_b/model-b1: cost per successful request: $0.0684. reported cost of all provider_b/model-b1's requests, failures included ÷ its successful requests. Sources: report.json groups[provider_b/model-b1].metrics.cost_per_success; input file (SHA-256 under Provenance), reported_cost column (synthetic).
- provider_c/model-c1: cost per successful request: $0.1474. reported cost of all provider_c/model-c1's requests, failures included ÷ its successful requests. Sources: report.json groups[provider_c/model-c1].metrics.cost_per_success; input file (SHA-256 under Provenance), reported_cost column (synthetic).
21.0% of reported spend went to requests that failed
$10.49 of $50.00 paid for requests whose outcome was failure. Failures are paid for, so they belong in what AI work really costs; why they failed is worth reviewing.
Calculation and sources
- Reported cost of failed requests: $10.49. sum of reported_cost over the 289 requests with outcome failure and a cost. Sources: input file (SHA-256 under Provenance), reported_cost column (synthetic); input file, outcome column.
Spend AIYVO could not assess
$0.34 is in 1 group with too few requests to compare (provider_d/model-d1). AIYVO draws no conclusion from it.
Calculation and sources
- Reported cost in groups withheld from comparison: $0.34. sum of reported_cost over the 12 requests with a cost in provider_d/model-d1. Sources: input file (SHA-256 under Provenance), reported_cost column (synthetic); report.json groups[provider_d/model-d1].evidence.exclusions.
4 requests with no reported cost
Their spend is not in any total and is not estimated (provider_e/model-e1). Complete cost data would make the comparison stronger.
Calculation and sources
- Spend of requests without a reported cost: Not yet quantified. 4 requests have an empty cost; AIYVO never fills in a missing cost. Sources: input file (SHA-256 under Provenance), reported_cost column (synthetic).
Estimated opportunities
Reported cost above the list-price estimate
$0.08 more was reported than the supplied list prices would give for the same requests (provider_e/model-e1: 5.0% above). Worth checking against the provider's prices and invoices. This is an estimate: the price table (synthetic) is not verified, and the difference is not a saving.
Calculation and sources
- provider_e/model-e1: reported cost minus list-price estimate: $0.08. sum over the 56 of 60 requests with a cost of (reported_cost − list-price estimate from token counts × the price table's rates). Sources: input file (SHA-256 under Provenance), reported_cost column (synthetic); input file, token columns; price table (basis synthetic, SHA-256 under Provenance, not verified); report.json groups[provider_e/model-e1].metrics.reported_vs_list_estimate.
Verified realized savings
None verified. A realized saving needs provider billing from before and after a change; none was supplied, and AIYVO has made no change to your usage.
How the headline figures are calculated
- Total AI spend analyzed: sum of reported_cost over the 668 of 672 requests that have a cost; 4 requests without a cost are not included Sources: input file (SHA-256 under Provenance), reported_cost column (synthetic).
- Potential savings identified: The groups in this file served different requests, and quality and prices are not verified, so moving work between them has no measured price. A saving needs the same work measured on both options, or confirmed prices and volumes; this analysis has neither, so AIYVO estimates no saving.
- Spend requiring further review: sum of reported_cost over the 297 requests with a cost that failed, have no known outcome, or are in a group too small to compare; each request is counted once. Investigation spend, not recoverable savings: money already spent on requests that are worth looking into. AIYVO does not estimate how much of it, if any, could be recovered. Sources: input file (SHA-256 under Provenance), reported_cost column (synthetic); input file, outcome column; report.json groups[*].eligible_for_comparison.
- Evidence-backed findings: findings below, each with its figures, calculation and sources
What the figures mean
Each record is one request (row_kind request; declared in the mapping file). Cost per successful request: reported cost of all requests, failures included / number of successful requests. Cost per completed task is not shown: AIYVO does not group requests into tasks.
Reported costs: basis not declared. An empty cost is missing, never 0, and is not filled in. Zero costs: not declared; a reported 0 is shown as reported, and cost orderings that include a group reporting 0 are withheld.
List-price estimates: price table basis synthetic, not verified; not necessarily current.
Metric definitions
- record
- one row of the input file
- row_kind
- request; declared in the mapping file
- success
- a record whose outcome is success: a successful request
- success_rate
- request success rate: successful requests / (requests with outcome success or failure)
- cost_per_success
- cost per successful request: reported cost of all requests, failures included / number of successful requests
- task_level
- withheld: rows are requests and AIYVO does not group requests into tasks, so cost per completed task cannot be derived from this file
Results
Figures in parentheses are coverage (records with the value / all records) where it is below 100%.
| group | records | reported cost | cost / record | list estimate | reported vs list | request success rate | cost / successful request | median latency ms | p90 latency ms |
|---|---|---|---|---|---|---|---|---|---|
| provider_a/model-a1 | 200 | $34.8651 | $0.1743 | $34.8651 | 0.0% | 86.5% | $0.2015 | 25190.5 | 33178 |
| provider_b/model-b1 | 200 | $10.1953 | $0.0510 | $11.3281 | -10.0% | 74.5% | $0.0684 | 15090.5 | 18910 |
| provider_c/model-c1 | 200 | $2.9489 | $0.0147 | $2.9489 | 0.0% | 10.0% | $0.1474 | 6924.5 (190/200) | 9394 (190/200) |
| provider_d/model-d1 | 12 | WITHHELD | WITHHELD | WITHHELD | WITHHELD | WITHHELD | WITHHELD | WITHHELD | WITHHELD |
| provider_e/model-e1 | 60 | WITHHELD | $0.0296 (56/60) | $1.7278 | 5.0% (56/60) | 51.7% | WITHHELD | 11619.5 | 15219 |
"Reported vs list" compares the records that have a reported cost with the list-price estimate for those same records. A difference may reflect discounts, credits, markups or a mis-mapped price; it is not verified and is not a saving. The list estimate column covers all records.
Withheld figures
- provider_d/model-d1: all comparison figures withheld (insufficient sample: 12 valid records; at least 30 are required).
- provider_e/model-e1: reported cost total withheld (cost missing on 4 of 60 records; a total would count them as free).
- provider_e/model-e1: cost per successful request withheld (requires 100% cost and outcome coverage; cost present in 56 of 60 records (93.3%), success or failure known in 60 of 60 records (100.0%)).
Comparison
Observational ordering of eligible groups only; not a recommendation and not a controlled benchmark. cost_per_success is cost per successful request (see metric_definitions). Values equal at 4 decimal places share a rank.
- Comparability
- every compared group has the same share of each task type (
same_task_mix) - Ordered by cost per successful request
- 1.
provider_b/model-b1: 0.0684 USD (149 of 200 requests succeeded) - 2.
provider_c/model-c1: 0.1474 USD (20 of 200 requests succeeded) - 3.
provider_a/model-a1: 0.2015 USD (173 of 200 requests succeeded)
- 1.
- Not ordered
provider_d/model-d1: withheld from comparison (see its evidence below)
- Rules
- at least 30 valid records per group
- coverage of at least 0.90 for partial-data figures
- cost per successful request: 100% cost and outcome coverage
- at least 10 successes to be ordered (provisional rule; not statistically validated)
- values equal when rounded half-up to 4 decimal places share a rank and are marked tied; values are reported at 6 decimal places
- a reported 0 is shown as reported; cost orderings that include a group reporting 0 are withheld unless the mapping declares zero_costs "genuine"; an empty cost is missing, never 0, and is never replaced by a list-price estimate
- What this does not show
- That any provider is better in general. The groups served different requests; this is observational, not a controlled benchmark, and not a recommendation.
Evidence by group
Every value below is copied from this analysis (the same data as report.json). Nothing is recalculated in the page, and nothing here is independently verified.
provider_a/model-a1
- Source classification
- reported values: synthetic: fictitious example data; list estimate: AIYVO estimate from the supplied price table, not verified; provider-verified billing: none
- Observation period
- 2026-09-28T00:00:00+00:00 to 2026-10-04T23:45:00+00:00
- Observations
- 200
- Outcomes
- 173 success · 27 failure · 0 unknown · 0 missing
- Cost coverage
- 200 of 200 have a cost
- Outcome coverage
- 200 of 200 succeeded or failed
- Cost data
- 200 report a cost above 0 · 0 report exactly 0 · 0 missing · reported costs: basis not declared · provider-verified: 0
- Zero costs
- not declared: a reported 0 may be a real cost of 0 or an unknown cost exported as 0
- Task types
- bugfix 100, refactor 100
- Cost per successful request
- reported cost of all requests, failures included = 34.865075 USD
÷ successful requests = 173 - Request success rate
- successful requests = 173
÷ requests with outcome success or failure = 200 - Reported cost per request
- reported cost of the requests that have a cost = 34.865075 USD
÷ requests with a reported cost = 200 - Missing evidence
- provider billing records: source evidence unavailable
- Missing data
- Nothing is imputed. Records without a cost lower cost coverage, are never counted as free, and are left out of cost averages; the cost total is withheld unless every record has a cost. Unknown and missing outcomes are left out of the success rate. The cost per successful request needs every record to have both a cost and a known outcome.
- Comparison eligibility
- eligible for comparison
- Exclusions
- none
- Withheld figures
- none
provider_b/model-b1
- Source classification
- reported values: synthetic: fictitious example data; list estimate: AIYVO estimate from the supplied price table, not verified; provider-verified billing: none
- Observation period
- 2026-09-28T00:45:00+00:00 to 2026-10-04T23:30:00+00:00
- Observations
- 200
- Outcomes
- 149 success · 51 failure · 0 unknown · 0 missing
- Cost coverage
- 200 of 200 have a cost
- Outcome coverage
- 200 of 200 succeeded or failed
- Cost data
- 200 report a cost above 0 · 0 report exactly 0 · 0 missing · reported costs: basis not declared · provider-verified: 0
- Zero costs
- not declared: a reported 0 may be a real cost of 0 or an unknown cost exported as 0
- Task types
- bugfix 100, refactor 100
- Cost per successful request
- reported cost of all requests, failures included = 10.195276 USD
÷ successful requests = 149 - Request success rate
- successful requests = 149
÷ requests with outcome success or failure = 200 - Reported cost per request
- reported cost of the requests that have a cost = 10.195276 USD
÷ requests with a reported cost = 200 - Missing evidence
- provider billing records: source evidence unavailable
- Missing data
- Nothing is imputed. Records without a cost lower cost coverage, are never counted as free, and are left out of cost averages; the cost total is withheld unless every record has a cost. Unknown and missing outcomes are left out of the success rate. The cost per successful request needs every record to have both a cost and a known outcome.
- Comparison eligibility
- eligible for comparison
- Exclusions
- none
- Withheld figures
- none
provider_c/model-c1
- Source classification
- reported values: synthetic: fictitious example data; list estimate: AIYVO estimate from the supplied price table, not verified; provider-verified billing: none
- Observation period
- 2026-09-28T01:15:00+00:00 to 2026-10-04T21:00:00+00:00
- Observations
- 200
- Outcomes
- 20 success · 180 failure · 0 unknown · 0 missing
- Cost coverage
- 200 of 200 have a cost
- Outcome coverage
- 200 of 200 succeeded or failed
- Cost data
- 200 report a cost above 0 · 0 report exactly 0 · 0 missing · reported costs: basis not declared · provider-verified: 0
- Zero costs
- not declared: a reported 0 may be a real cost of 0 or an unknown cost exported as 0
- Task types
- bugfix 100, refactor 100
- Cost per successful request
- reported cost of all requests, failures included = 2.948897 USD
÷ successful requests = 20 - Request success rate
- successful requests = 20
÷ requests with outcome success or failure = 200 - Reported cost per request
- reported cost of the requests that have a cost = 2.948897 USD
÷ requests with a reported cost = 200 - Missing evidence
- provider billing records: source evidence unavailable
- Missing data
- Nothing is imputed. Records without a cost lower cost coverage, are never counted as free, and are left out of cost averages; the cost total is withheld unless every record has a cost. Unknown and missing outcomes are left out of the success rate. The cost per successful request needs every record to have both a cost and a known outcome.
- Comparison eligibility
- eligible for comparison
- Exclusions
- none
- Withheld figures
- none
provider_d/model-d1
- Source classification
- reported values: synthetic: fictitious example data; list estimate: AIYVO estimate from the supplied price table, not verified; provider-verified billing: none
- Observation period
- 2026-09-28T18:15:00+00:00 to 2026-10-04T16:45:00+00:00
- Observations
- 12
- Outcomes
- 8 success · 4 failure · 0 unknown · 0 missing
- Cost coverage
- 12 of 12 have a cost
- Outcome coverage
- 12 of 12 succeeded or failed
- Cost data
- 12 report a cost above 0 · 0 report exactly 0 · 0 missing · reported costs: basis not declared · provider-verified: 0
- Zero costs
- not declared: a reported 0 may be a real cost of 0 or an unknown cost exported as 0
- Task types
- bugfix 6, refactor 6
- Cost per successful request
- reported cost of all requests, failures included = withheld
÷ successful requests = withheld - Request success rate
- successful requests = 8
÷ requests with outcome success or failure = 12 - Reported cost per request
- reported cost of the requests that have a cost = 0.336149 USD
÷ requests with a reported cost = 12 - Missing evidence
- provider billing records: source evidence unavailable
- Missing data
- Nothing is imputed. Records without a cost lower cost coverage, are never counted as free, and are left out of cost averages; the cost total is withheld unless every record has a cost. Unknown and missing outcomes are left out of the success rate. The cost per successful request needs every record to have both a cost and a known outcome.
- Comparison eligibility
- withheld from comparison
- Exclusions
- Not enough observations (condition not met). Observed: insufficient sample: 12 valid records; at least 30 are required. To re-evaluate: Add valid records until this group has at least 30; it has 12. Then re-run the analysis.
- Withheld figures
- reported cost total: insufficient sample: 12 valid records; at least 30 are required
- reported cost per record: insufficient sample: 12 valid records; at least 30 are required
- list price estimate total: insufficient sample: 12 valid records; at least 30 are required
- reported vs list estimate: insufficient sample: 12 valid records; at least 30 are required
- success rate: insufficient sample: 12 valid records; at least 30 are required
- cost per success: insufficient sample: 12 valid records; at least 30 are required
- latency ms median: insufficient sample: 12 valid records; at least 30 are required
- latency ms p90: insufficient sample: 12 valid records; at least 30 are required
- quality score mean: insufficient sample: 12 valid records; at least 30 are required
provider_e/model-e1
- Source classification
- reported values: synthetic: fictitious example data; list estimate: AIYVO estimate from the supplied price table, not verified; provider-verified billing: none
- Observation period
- 2026-09-28T02:30:00+00:00 to 2026-10-04T23:00:00+00:00
- Observations
- 60
- Outcomes
- 31 success · 29 failure · 0 unknown · 0 missing
- Cost coverage
- 56 of 60 have a cost
- Outcome coverage
- 60 of 60 succeeded or failed
- Cost data
- 56 report a cost above 0 · 0 report exactly 0 · 4 missing · reported costs: basis not declared · provider-verified: 0
- Zero costs
- not declared: a reported 0 may be a real cost of 0 or an unknown cost exported as 0
- Task types
- bugfix 30, refactor 30
- Cost per successful request
- reported cost of all requests, failures included = withheld
÷ successful requests = withheld - Request success rate
- successful requests = 31
÷ requests with outcome success or failure = 60 - Reported cost per request
- reported cost of the requests that have a cost = 1.658308 USD
÷ requests with a reported cost = 56 - Missing evidence
- 4 of 60 records have no cost: missing, not counted as free
- provider billing records: source evidence unavailable
- Missing data
- Nothing is imputed. Records without a cost lower cost coverage, are never counted as free, and are left out of cost averages; the cost total is withheld unless every record has a cost. Unknown and missing outcomes are left out of the success rate. The cost per successful request needs every record to have both a cost and a known outcome.
- Comparison eligibility
- eligible for comparison
- Exclusions
- Cost data incomplete (condition unknown: data missing). Observed: cost present in 56 of 60 records (93.3%). To re-evaluate: Supply a reported cost for every record (0 where a record was free), then re-run. Records without a cost are not estimated or filled in.
- Withheld figures
- reported cost total: cost missing on 4 of 60 records; a total would count them as free
- cost per success: requires 100% cost and outcome coverage; cost present in 56 of 60 records (93.3%), success or failure known in 60 of 60 records (100.0%)
Sources
- Source data The input usage file named when the analyzer was run (synthetic: fictitious example data), SHA-256
809be4b64ba5651786634621983900e884ce922c675594e9f6865a2dde171a60. - AIYVO-generated This report and report.json and report.md, written together from the same analysis. Not independent verification.
- Unavailable Provider billing records: source evidence unavailable. No provider-verified billing was used.
Provenance
SHA-256 fingerprints identify the exact files and analyzer source used, so the report can be reproduced. They prove nothing about whether the data is true or complete: the data is not independently verified, and the fingerprints are not a signature or a custody record.
- Analyzer
- AIYVO offline usage analyzer, source SHA-256
dc759f963d31da373750dfd674f9ddd0824fffe2bbd29e531460b907e2dfcf70 - Input
- SHA-256
809be4b64ba5651786634621983900e884ce922c675594e9f6865a2dde171a60 - Mapping
- SHA-256
7e3152d4614714c543c4c165324fc0680d070ecea41ce5672f4d229aebe92551 - Price table
- SHA-256
0e70df3c41b6fecc5ead10fde57ed91908d16545dc954b556ca47befb5fb3b67(basis synthetic) - Reference time
- 2026-10-11T00:00:00+00:00 (--as-of)
- Data source
- synthetic (the input is AIYVO's bundled synthetic example)
Limitations
- All usage, cost, outcome and latency values are synthetic (fictitious example data), not customer data, and were not independently verified.
- No provider-verified billing was used. Reported cost may differ from what a provider invoices.
- List-price estimates are AIYVO estimates from the supplied price table; those prices are not verified and not necessarily current.
- Comparisons are observational: different groups served different requests. This is not a controlled experiment.
- Token counts from different models are not directly comparable (different tokenizers).
- No savings, quality superiority or recommendation is claimed.
- Rows are requests, so a success is a successful request, not a completed task. AIYVO does not group requests into tasks: when a task takes several requests (retries, agent steps), cost per successful request can be far below the cost of a completed task, and no per-task figure is given.
- The file mixes task types. The compared groups have the same mix, but results for one task type can differ from the mix; use --by-task-type to see each task type separately.
Generated offline by the AIYVO offline usage analyzer. This page loads no scripts, fonts, images or network resources.