Skip to content

LLM response time breakdown

GET
/api/v1/monitoring/llm-performance

Returns response time percentiles by model and agent role.

Authorizations

Parameters

Query Parameters

time_range

Time window for metrics aggregation

string
default: 1h /^(1h|6h|24h|7d)$/

Time window for metrics aggregation

model
Any of:
string

Filter to a specific LLM model

agent_role
Any of:
string

Filter to a specific agent role

Responses

200

Successful Response

LLM performance dashboard data.

object
models
required
Array<object>

LLM response time statistics for a model + agent combination.

object
agent_role
required
string
avg
required
number
model
required
string
p50
required
number
p95
required
number
p99
required
number
sample_count
required
integer
total_tokens
required
integer
time_range
required
string
total_calls
required
integer

422

Validation Error

object
detail
Array<object>
object
ctx
object
input
loc
required
Array
msg
required
string
type
required
string