AI Analytics

Retrieve usage and performance analytics for AI models managed by the Strongly AI Gateway, counted in requests and tokens. All analytics endpoints are read-only and cover one date range: the last 24h, 7d, 30d or 90d.

Each figure counts the requests the caller may see: a platform administrator sees every request, an organization owner or admin on a multi-tenant platform sees their organization's members' requests, and anyone else sees their own.

---

GET /api/v1/ai/analytics/usage

Get usage statistics

Returns the range's totals: requests, tokens, latency, error rate, users and models.

Scope: ai-gateway:read

Parameters:

Name	In	Type	Required	Description
dateRange	query	string	Yes	24h, 7d, 30d or 90d
modelId	query	string	No	Only this model's requests

Response: 200 OK

{
  "data": {
    "total_requests": 145230,
    "total_tokens": 28500000,
    "prompt_tokens": 18200000,
    "completion_tokens": 10300000,
    "avg_response_time": 485,
    "min_response_time": 42,
    "max_response_time": 9120,
    "p95_response_time": 1500,
    "p95_over_bound": false,
    "p99_response_time": 3000,
    "p99_over_bound": false,
    "error_rate": 1.5,
    "success_rate": 98.5,
    "unique_users_count": 38,
    "unique_models_count": 7
  },
  "meta": { "requestId": "req_abc123" }
}

See UsageStats for the fields.

---

GET /api/v1/ai/analytics/performance

Get performance metrics

Returns request latency per model over the range, most requests first.

Scope: ai-gateway:read

Parameters:

Name	In	Type	Required	Description
dateRange	query	string	Yes	24h, 7d, 30d or 90d
modelId	query	string	No	Only this model

Response: 200 OK

{
  "data": [
    {
      "model_id": "model_abc123",
      "model_name": "GPT-4 Production",
      "provider": "openai",
      "total_requests": 52000,
      "avg_response_time": 420,
      "min_response_time": 38,
      "max_response_time": 8800,
      "p95_response_time": 1500,
      "p95_over_bound": false,
      "p99_response_time": 3000,
      "p99_over_bound": false
    }
  ],
  "meta": { "requestId": "req_abc123" }
}

Field	Type	Description
model_id	string	Model ID
model_name	string	Model name
provider	string	Model provider
total_requests	integer	Requests in the range
avg_response_time	integer | null	Mean latency in milliseconds
min_response_time	number | null	Fastest request in milliseconds
max_response_time	number | null	Slowest request in milliseconds
p95_response_time	integer | null	95th percentile latency in milliseconds, as the upper bound of its latency bucket
p95_over_bound	boolean	true when the 95th percentile is above the highest bucket bound (10000 ms), so the true value is over p95_response_time
p99_response_time	integer | null	99th percentile latency in milliseconds, as the upper bound of its latency bucket
p99_over_bound	boolean	As p95_over_bound, for the 99th percentile

---

GET /api/v1/ai/analytics/time-series

Get time-series data

Returns requests, tokens, mean latency and errors per provider, per hour or per UTC day, suitable for charting and trend analysis.

Scope: ai-gateway:read

Parameters:

Name	In	Type	Required	Description
dateRange	query	string	Yes	24h, 7d, 30d or 90d
granularity	query	string	Yes	hourly or daily. hourly is allowed only with 24h; any other range is refused with the message An hourly series is of the last 24 hours only
provider	query	string	No	Only this provider (all means every provider)

Response: 200 OK

{
  "data": [
    {
      "timestamp": "2025-02-06",
      "provider": "anthropic",
      "requests": 1850,
      "tokens": 410000,
      "avg_latency": 540,
      "errors": 12
    },
    {
      "timestamp": "2025-02-06",
      "provider": "openai",
      "requests": 4200,
      "tokens": 820000,
      "avg_latency": 410,
      "errors": 30
    }
  ],
  "meta": { "requestId": "req_abc123" }
}

data holds one point per period and provider, ordered by timestamp then provider. timestamp is YYYY-MM-DD HH:00 for hourly and YYYY-MM-DD for daily (UTC). With daily, every day of the range is present for each provider: a day with no requests has zero requests, tokens and errors and a null avg_latency (milliseconds).

---

GET /api/v1/ai/analytics/providers

Get per-provider statistics

Returns aggregated statistics grouped by AI provider, most requests first, useful for comparing providers side by side.

Scope: ai-gateway:read

Parameters:

Name	In	Type	Required	Description
dateRange	query	string	Yes	24h, 7d, 30d or 90d

Response: 200 OK

{
  "data": [
    {
      "provider": "openai",
      "models_count": 5,
      "total_requests": 82000,
      "total_tokens": 18500000,
      "avg_latency": 420,
      "unique_users_count": 31
    },
    {
      "provider": "anthropic",
      "models_count": 3,
      "total_requests": 45000,
      "total_tokens": 12000000,
      "avg_latency": 550,
      "unique_users_count": 22
    }
  ],
  "meta": { "requestId": "req_abc123" }
}

Field	Type	Description
provider	string	Provider name
models_count	integer	Models of this provider with requests in the range
total_requests	integer	Requests in the range
total_tokens	integer	Tokens in the range (prompt + completion)
avg_latency	integer | null	Mean latency in milliseconds
unique_users_count	integer	Users with requests to this provider

---

Response Models Reference

UsageStats

Field	Type	Description
total_requests	integer	Total number of inference requests
total_tokens	integer	Total tokens consumed (prompt + completion)
prompt_tokens	integer	Total input/prompt tokens
completion_tokens	integer	Total output/completion tokens
avg_response_time	integer | null	Mean latency in milliseconds (null with no requests)
min_response_time	number | null	Fastest request in milliseconds
max_response_time	number | null	Slowest request in milliseconds
p95_response_time	integer | null	95th percentile latency in milliseconds, as the upper bound of its latency bucket
p95_over_bound	boolean	true when the 95th percentile is above the highest bucket bound (10000 ms)
p99_response_time	integer | null	99th percentile latency in milliseconds, as the upper bound of its latency bucket
p99_over_bound	boolean	As p95_over_bound, for the 99th percentile
error_rate	number | null	Percentage of requests that failed (0 - 100), null with no requests
success_rate	number | null	Percentage of requests that succeeded (0 - 100), null with no requests
unique_users_count	integer	Users with requests in the range
unique_models_count	integer	Models with requests in the range