---
title: "report.ai-performance@1 · OpenVibe.Services"
canonical: "https://openvibe.services/docs/contracts/report.ai-performance"
updated: null
---

# report.ai-performance@1 · OpenVibe.Services

HTML: [report.ai-performance@1 · OpenVibe.Services](https://openvibe.services/docs/contracts/report.ai-performance)

# ReportAiPerformance `report.ai-performance@1`

Generated at 2026-11-17 06:52:56 UTC from [`openvibe-contracts v0.443.0`](https://github.com/OpenVibers/OpenVibe.Contracts/tree/v0.443.0) and [`openvibe-sdk v0.177.0`](https://github.com/OpenVibers/OpenVibe.SDK/tree/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`](/docs/contracts/report.ai-performance.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 |  | - `one of "model", "provider", "operation", "system", "task", "place", "harness"` |
| `key` | string | yes |  | - `maxLength 200` |
| `provider` | string \| null |  |  | - `maxLength 120` |
| `range` | object |  |  | - `no other fields` |
| `range.from` | string |  |  | - `format date` |
| `range.to` | string |  |  | - `format date` |
| `calls` | integer | yes |  | - `minimum 0` |
| `succeeded` | integer |  |  | - `minimum 0` |
| `errors` | integer |  |  | - `minimum 0` |
| `success_rate` | number \| null |  |  | - `minimum 0`<br>- `maximum 1` |
| `fallback_rate` | number \| null |  |  | - `minimum 0`<br>- `maximum 1` |
| `streamed_share` | number \| null |  |  | - `minimum 0`<br>- `maximum 1` |
| `cache_hit_rate` | number \| null |  |  | - `minimum 0`<br>- `maximum 1` |
| `cache_read_share` | number \| null |  | Cache-read tokens as a share of all input tokens. | - `minimum 0`<br>- `maximum 1` |
| `ttft_ms` | object |  |  | - `no other fields` |
| `ttft_ms.p50` | number \| null |  |  | - `minimum 0` |
| `ttft_ms.p90` | number \| null |  |  | - `minimum 0` |
| `ttft_ms.p95` | number \| null |  |  | - `minimum 0` |
| `ttft_ms.n` | integer |  |  | - `minimum 0` |
| `latency_ms` | object |  |  | - `no other fields` |
| `latency_ms.p50` | number \| null |  |  | - `minimum 0` |
| `latency_ms.p90` | number \| null |  |  | - `minimum 0` |
| `latency_ms.p95` | number \| null |  |  | - `minimum 0` |
| `latency_ms.n` | integer |  |  | - `minimum 0` |
| `tps` | object |  |  | - `no other fields` |
| `tps.p50` | number \| null |  |  | - `minimum 0` |
| `tps.p90` | number \| null |  |  | - `minimum 0` |
| `tps.p95` | number \| null |  |  | - `minimum 0` |
| `tps.n` | integer |  |  | - `minimum 0` |
| `tokens` | object |  |  | - `no other fields` |
| `tokens.input` | integer |  |  | - `minimum 0` |
| `tokens.output` | integer |  |  | - `minimum 0` |
| `tokens.reasoning` | integer |  |  | - `minimum 0` |
| `tokens.cache_read` | integer |  |  | - `minimum 0` |
| `tokens.cache_write` | integer |  |  | - `minimum 0` |
| `cost` | object |  |  | - `no other fields` |
| `cost.charged_usd` | number |  |  | - `minimum 0` |
| `cost.list_usd` | number |  |  | - `minimum 0` |
| `cost.cache_saved_usd` | number |  |  | - `minimum 0` |
| `cost.per_call_usd` | number \| null |  |  | - `minimum 0` |
| `cost.per_million_output_usd` | number \| null |  |  | - `minimum 0` |
| `tasks` | object \| null |  |  |  |
| `top_errors` | array of object |  |  | - `maxItems 5`<br>- `items: no other fields` |
| `top_errors[].error_class` | string | yes |  | - `maxLength 60` |
| `top_errors[].count` | integer | yes |  | - `minimum 0` |

## 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 }] }
~~~~
