Usage by model
⚠️
Preview — this feature is being built; the design below is the spec.
GET https://app.syntic.ai/v1/organizations/analytics/modelsRequests, tokens, cache hit rate, average latency and errors per model, in time buckets. Use it to see the effect of moving traffic between models.
For how this fits into a full workflow, see Usage analytics.
Headers
| Header | Required | Value |
|---|---|---|
Authorization | Yes | Bearer <admin key>: an Admin API key (sk_admin_...). Inference keys are refused with 403 admin_key_required. See Admin API keys. |
syntic-beta | Yes, while in preview | admin-2026-11-01. Without it the call fails with 400 beta_required. See Versioning. |
Query parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
starting_at | string | RFC 3339; required. Inclusive. | |
ending_at | string | now | Exclusive. At most 92 days after starting_at. |
workspace_id | string | Restrict to one workspace. | |
bucket_width | string | 1d | 1h (ranges up to 7 days) or 1d. |
Response
200 OK, Content-Type: application/json
{
"data": [
{
"bucket_start": "2026-11-01T00:00:00Z",
"results": [
{
"model": "Amara S1.2",
"requests": 51022,
"input_tokens": 244001220,
"output_tokens": 16004110,
"cache_hit_rate": 0.61,
"p50_latency_ms": 820,
"p95_latency_ms": 4100,
"error_rate": 0.004
},
{
"model": "Amara Quick",
"requests": 90311,
"input_tokens": 120440201,
"output_tokens": 9011220,
"cache_hit_rate": 0.48,
"p50_latency_ms": 390,
"p95_latency_ms": 1300,
"error_rate": 0.002
}
]
}
],
"has_more": false,
"next_page": null
}| Field | Type | Description |
|---|---|---|
cache_hit_rate | number | Share of input tokens served from the prompt cache, 0 to 1. |
p50_latency_ms | integer | Median time to the last token. |
error_rate | number | Share of requests that ended in a 4xx or 5xx other than 429. |
Examples
curl -sS "https://app.syntic.ai/v1/organizations/analytics/models?starting_at=2026-11-01T00:00:00Z&bucket_width=1d" \
-H "Authorization: Bearer $SYNTIC_ADMIN_KEY" \
-H "syntic-beta: admin-2026-11-01"Errors
Errors use the error envelope and carry a request_id. Codes specific to this operation:
| Status | type | code | When |
|---|---|---|---|
| 400 | invalid_request_error | beta_required | The syntic-beta header is missing. |
| 401 | authentication_error | invalid_api_key | The admin key is missing, unknown, revoked or expired. |
| 403 | permission_error | admin_key_required | An inference key was used. |
| 429 | rate_limit_error | rate_limited | Too many requests; wait for Retry-After. See Rate-limit headers. |
Was this page helpful?