OVovermindlab
deployed-models

Aggregate inference metrics (tokens, latency, TPS, crude cost)

get/api/deployed-models/{id}/metrics/

Request

  • Base URL
    https://api.overmindlab.ai
  • Auth
    • HTTP bearer
    • or API key in header X-Api-Key
    • or API key in cookie sessionid
    • or API key in header X-Api-Key
    • or HTTP bearer

Path parameters

idstring uuid required

A UUID string identifying this deployed model.

Query parameters

period'1h' | '24h' | '7d' | '30d' | 'all'
  • 1h - 1h
  • 24h - 24h
  • 7d - 7d
  • 30d - 30d
  • all - all
source'all' | 'application'
  • all - all
  • application - application

Response

last_request_atstring date-time nullable required
cost_recorded_request_countinteger required
failed_request_countinteger required
cold_request_countinteger required
end_to_end_p50_msnumber double nullable required
end_to_end_p95_msnumber double nullable required
request_countinteger required
prompt_tokensinteger required
completion_tokensinteger required
total_tokensinteger required
costnumber double nullable required
cost_this_monthnumber double nullable required
cost_is_estimateboolean required
avg_tokens_per_secondnumber double nullable required
avg_latency_msnumber double nullable required
latency_p95_msnumber double nullable required
cold_start_msnumber double nullable required
baseline_modelstring nullable required
baseline_costnumber double nullable required
savingsnumber double nullable required

Changes

No recorded changes to this operation across all 1 revision of this API.