List Llm Metrics

POST

https://api.respan.ai/api/dashboard/llm-metrics/

POST

/api/dashboard/llm-metrics/

$ curl -X POST https://api.respan.ai/api/dashboard/llm-metrics/ \
>      -H "Authorization: Bearer <token>" \
>      -H "Content-Type: application/json" \
>      -d '{
>   "date_group": "2024-01-15T09:30:00Z"
> }'

201Created

1 {
2   "date_group": "2024-01-15T09:30:00Z",
3   "number_of_requests": 1,
4   "total_cost": 1.1,
5   "total_prompt_tokens": 1,
6   "total_completion_tokens": 1,
7   "total_tokens": 1,
8   "max_tpm": 1,
9   "error_count": 1,
10   "error_percentage": 1.1,
11   "average_prompt_tokens": 1,
12   "average_completion_tokens": 1,
13   "average_tokens": 1,
14   "average_cost": 1.1,
15   "average_latency": 1.1,
16   "average_tps": 1.1,
17   "average_ttft": 1.1,
18   "prompt_cache_hit_tokens": 1,
19   "reasoning_tokens": 1,
20   "max_cost": 1.1,
21   "max_tokens": 1,
22   "max_latency": 1.1,
23   "unique_customers": 1,
24   "latency_p_50": 1.1,
25   "latency_p_95": 1.1,
26   "latency_p_99": 1.1,
27   "cache_hit_percentage": 1.1,
28   "requests_per_second": 1.1
29 }

POST handler with superadmin-only field protection.

Strips superadmin-only fields from non-superadmin requests before delegating to OrganizationInjectionMixin.post() for org injection.

Authentication

AuthorizationBearer

Use your Respan API key for Respan API authentication. Enter only the Respan API key value; clients send Authorization: Bearer <RESPAN_API_KEY>. For /api/responses, provider credentials such as Perplexity, OpenAI, or Azure OpenAI go in Settings -> Providers or respan_params.credential_override in the request body, not in this authentication field.

Request

This endpoint expects an object.

date_groupdatetimeRequired

number_of_requestsinteger or nullOptional

total_costdouble or nullOptional

total_prompt_tokensinteger or nullOptional

total_completion_tokensinteger or nullOptional

total_tokensinteger or nullOptional

max_tpminteger or nullOptional

error_countinteger or nullOptional

error_percentagedouble or nullOptional

average_prompt_tokensinteger or nullOptional

average_completion_tokensinteger or nullOptional

average_tokensinteger or nullOptional

average_costdouble or nullOptional

average_latencydouble or nullOptional

average_tpsdouble or nullOptional

average_ttftdouble or nullOptional

prompt_cache_hit_tokensinteger or nullOptional

reasoning_tokensinteger or nullOptional

max_costdouble or nullOptional

max_tokensinteger or nullOptional

max_latencydouble or nullOptional

unique_customersinteger or nullOptional

latency_p_50double or nullOptional

latency_p_95double or nullOptional

latency_p_99double or nullOptional

cache_hit_percentagedouble or nullOptional

requests_per_seconddouble or nullOptional

Response

date_groupdatetime