Model Performance Metrics

Get model performance metrics	GET https://api.aimlapi.com/models/metrics

GET /models/metrics reports how fast models are responding right now — ttft_ms, tps and duration_ms as p50/p75/p90/p99 over a short sliding window, per model. No API key is required for this request. You can also open the endpoint directly in a browser.

Use it to pick between models that are otherwise interchangeable, or to check whether slowness you are seeing is on your side. These are the same numbers the model cards in the dashboard show.

A higher percentile of tps is better, not worse. These are percentiles of the measured value itself, so p99 of ttft_ms or duration_ms is the slow tail — but p99 of tps is the fastest requests, and p50 is the typical one. Comparing models on tps p99 compares their best cases.

A model that served no successful requests inside the window is absent from models entirely. That is "no data", not "zero latency" — and since only successful requests are measured, a model that is failing everything drops off the list rather than showing bad numbers.

aliases does not split on commas: repeat the parameter, as in ?aliases=openai/gpt-5&aliases=google/veo-3. Names are matched exactly against the id and aliases from the Complete Model List.

Get model performance metrics

Returns latency percentiles per model over the current window.

get

Query parameters

aliasesstringOptional

Keep only these models. Repeat the parameter once per model (?aliases=openai/gpt-5&aliases=google/veo-3), up to 100 values. Values are matched exactly, so a comma-separated list is read as one long name and matches nothing. Omit the parameter to get every measured model. Any other query parameter is rejected with 400.

Example: openai/gpt-5

Responses

200

Latency percentiles per model over the current window.

application/json

window_secondsintegerRequired

Length of the sliding window the percentiles were computed over.

Example: 300

generated_atstringRequired

When the aggregation was computed, in UTC.

Example: 2026-08-19T12:00:05.000Z

get/models/metrics

curl -L \
  --url 'https://api.aimlapi.com/models/metrics?aliases=openai/gpt-5&aliases=google/veo-3'

200

Latency percentiles per model over the current window.

{
  "window_seconds": 300,
  "generated_at": "2026-08-19T12:00:05.000Z",
  "models": [
    {
      "alias": "openai/gpt-5",
      "endpoint": "/v1/chat/completions",
      "metrics": {
        "ttft_ms": {
          "p50": 412,
          "p75": 588,
          "p90": 910,
          "p99": 2140
        },
        "tps": {
          "p50": 51.7,
          "p75": 64.1,
          "p90": 78.4,
          "p99": 96.2
        },
        "duration_ms": {
          "p50": 1830,
          "p75": 2450,
          "p90": 3900,
          "p99": 9100
        }
      }
    }
  ]
}