cURL
curl --request GET \ --url https://api.example.com/deploy/{deploy_id}/stats2 \ --header 'Authorization: Bearer <token>'
{ "llm": { "requests": 123, "input_tokens": 123, "output_tokens": 123, "avg_ttft_ms": 123, "avg95_ttft_ms": 123, "avg_tpt_ms": 123, "avg95_tpt_ms": 123, "total_amount_cents": 123, "errors": 123 }, "embeddings": { "requests": 123, "input_tokens": 123, "avg_tpt_ms": 123, "avg95_tpt_ms": 123, "total_amount_cents": 123, "errors": 123 }, "time": { "requests": 123, "total_time_s": 123, "total_amount_cents": 123, "avg_time_ms": 123, "avg95_time_ms": 123, "errors": 123 } }
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Bearer <token>
<token>
start of period, unix ts or 'now-5h', supported units s, m, h, d, w
end of period, unix ts or now-relative, check from, defaults to now
Successful Response
LLM Deployment Stats
Show child attributes
Embeddings Deployment Stats
Time based Deployment Stats