Skip to content
PensievePensievePensieve

Change how calls are routed

PATCH
/v1/models/{model}/routing
curl --request PATCH \
  --url https://api.pensievelabs.co/v1/models/grade-audit/routing \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{ "mode": "model", "threshold": 0.8 }'

observe records calls only: your own code keeps answering, through capture. model sends calls to the expert model and falls back under threshold. split sends split_percent of calls to the model and the rest to your code.

Authorizations

Section titled “Authorizations”

Parameters

Section titled “Parameters”

Path Parameters

Section titled “Path Parameters”
model
required
string

The model’s slug, such as grade-audit, or its mdl_ id.

Example 

grade-audit

Request Bodyrequired

Section titled “Request Bodyrequired”
Media typeapplication/json
object
mode
string
Allowed values: observe model split
threshold
number
<= 1
split_percent
integer
<= 100

Example 

{
  "mode": "model",
  "threshold": 0.8
}

Responses

Section titled “Responses”

200

Section titled “200”

The routing now in force.

Media typeapplication/json
object
object
required
Allowed value: routing
model
required
string
mode
required
string
Allowed values: observe model split
threshold
required

Under this confidence a call falls back.

number
<= 1
split_percent
required
integer | null
<= 100
updated_at
required
string format: date-time

Example 

{
  "object": "routing",
  "mode": "observe"
}

default

Section titled “default”

Something went wrong; error.type says what.

Media typeapplication/json
object
error
required
object
type
required
string
Allowed values: invalid_request authentication permission not_found conflict rate_limit not_available server
message
required
string
param

The request field the error is about.

string | null
request_id
required
string

Example 

{
  "error": {
    "type": "invalid_request"
  }
}