ReportAiPerformance report.ai-performance@1
Generated at from
openvibe-contracts v0.443.0 and
openvibe-sdk v0.177.0.
- Version
- 1.0.0
- Owner
- report
- Visibility
- internal
- Status
- active
- Compatibility
- backward
- Schema
https://openvibe.network/contracts/report/ai-performance.v1.json
report.ai-performance@1 (ai-metrics.md): how AI calls performed over a range, for one group (a model, a provider, an operation, a system, a task). Percentiles come from log-scale histograms (within one bucket’s width). Public answers group by model, provider or operation only and show a group with at least 20 calls; system and task groups are for staff. Money is USD; tokens per second is the decode speed after the first token; cost per task sums the calls that share a task id.
Fields
| Field | Type | Required | Description | Constraints |
|---|---|---|---|---|
group | enum | yes |
| |
key | string | yes |
| |
provider | string | null |
| ||
range | object |
| ||
range.from | string |
| ||
range.to | string |
| ||
calls | integer | yes |
| |
succeeded | integer |
| ||
errors | integer |
| ||
success_rate | number | null |
| ||
fallback_rate | number | null |
| ||
streamed_share | number | null |
| ||
cache_hit_rate | number | null |
| ||
cache_read_share | number | null | Cache-read tokens as a share of all input tokens. |
| |
ttft_ms | object |
| ||
ttft_ms.p50 | number | null |
| ||
ttft_ms.p90 | number | null |
| ||
ttft_ms.p95 | number | null |
| ||
ttft_ms.n | integer |
| ||
latency_ms | object |
| ||
latency_ms.p50 | number | null |
| ||
latency_ms.p90 | number | null |
| ||
latency_ms.p95 | number | null |
| ||
latency_ms.n | integer |
| ||
tps | object |
| ||
tps.p50 | number | null |
| ||
tps.p90 | number | null |
| ||
tps.p95 | number | null |
| ||
tps.n | integer |
| ||
tokens | object |
| ||
tokens.input | integer |
| ||
tokens.output | integer |
| ||
tokens.reasoning | integer |
| ||
tokens.cache_read | integer |
| ||
tokens.cache_write | integer |
| ||
cost | object |
| ||
cost.charged_usd | number |
| ||
cost.list_usd | number |
| ||
cost.cache_saved_usd | number |
| ||
cost.per_call_usd | number | null |
| ||
cost.per_million_output_usd | number | null |
| ||
tasks | object | null | |||
top_errors | array of object |
| ||
top_errors[].error_class | string | yes |
| |
top_errors[].count | integer | yes |
|
Examples
From the contract's own test fixtures: valid ones validate, rejected ones must fail.
Valid: a-model-over-a-week
{
"group": "model",
"key": "deepseek-v4-flash",
"provider": "deepseek",
"range": {
"from": "2026-11-05",
"to": "2026-11-12"
},
"calls": 18420,
"succeeded": 18311,
"errors": 109,
"success_rate": 0.9941,
"fallback_rate": 0.012,
"streamed_share": 0.71,
"cache_hit_rate": 0.04,
"cache_read_share": 0.63,
"ttft_ms": {
"p50": 540,
"p90": 980,
"p95": 1310,
"n": 13080
},
"latency_ms": {
"p50": 3900,
"p90": 9100,
"p95": 12800,
"n": 18420
},
"tps": {
"p50": 86,
"p90": 121,
"p95": 133,
"n": 12990
},
"tokens": {
"input": 210000000,
"output": 9100000,
"reasoning": 0,
"cache_read": 132000000,
"cache_write": 0
},
"cost": {
"charged_usd": 61.2,
"list_usd": 74.9,
"cache_saved_usd": 19.8,
"per_call_usd": 0.0033,
"per_million_output_usd": 6.72
},
"tasks": {
"count": 4120,
"cost_per_task_usd": {
"p50": 0.006,
"p90": 0.031,
"p95": 0.05,
"n": 4120
},
"time_per_task_ms": {
"p50": 14000,
"p90": 61000,
"p95": 98000,
"n": 4120
}
},
"top_errors": [
{
"error_class": "rate_limited",
"count": 71
},
{
"error_class": "timeout",
"count": 30
}
]
}Rejected: a-group-nobody-has
{
"group": "person",
"key": "usr_x",
"calls": 3
}Validate
const contracts = require('openvibe-contracts');
contracts.validate('report.ai-performance@1', value); // { valid, errors: [{ path, message }] }