POST
/
v1
/
run
/
{run_id}
/
testrecord
/
{testrecord_id}
/
score
curl --request POST \
  --url https://api.getscorecard.ai/v1/run/{run_id}/testrecord/{testrecord_id}/score \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '{
  "metric_id": 1,
  "int_score": 10,
  "binary_score": true,
  "reasoning": "The moon is made of cheese."
}'
{
  "user_id": "<string>",
  "id": 1,
  "run_id": 1,
  "testcase_id": 1,
  "testrecord_id": 1,
  "metric_id": 1,
  "binary_score": true,
  "int_score": 1,
  "reasoning": "The moon is not made of cheese so this result is not factual.",
  "human_eval": true,
  "status": "pending",
  "error_message": "An error occurred while creating the grade.",
  "created_at": "2025-02-06T23:05:50.132525",
  "updated_at": "2025-02-07T00:04:50.132584"
}

Authorizations

​
X-API-Key
string
header
required

Path Parameters

​
run_id
integer
required

The ID of the run that created the testrecord to be scored.

Example:

1

​
testrecord_id
integer
required

The ID of the testrecord to be scored.

Example:

12

Body

application/json
​
metric_id
integer
required

The ID of the metric

Example:

1

​
int_score
integer | null
required

Specify integer scores.

Example:

10

​
binary_score
boolean | null
required

Specify boolean scores.

Example:

true

​
reasoning
string | null
required

The reasoning for the assigned score.

Example:

"The moon is made of cheese."

Response

200
application/json
Successful Response
​
user_id
string | null
​
id
integer | null

The ID of the grade.

Example:

1

​
run_id
integer | null

The ID of the run that created the grade.

Example:

1

​
testcase_id
integer | null

The ID of the testcase associated with the grade.

Example:

1

​
testrecord_id
integer | null

The ID of the testrecord for which the grade was created.

Example:

1

​
metric_id
integer | null

The ID of the metric used to compute the grade.

Example:

1

​
binary_score
boolean | null

The binary score assigned to the grade.

Example:

true

​
int_score
integer | null

The integer score assigned to the grade.

Example:

1

​
reasoning
string | null

The reasoning for the assigned score.

Example:

"The moon is not made of cheese so this result is not factual."

​
human_eval
boolean
default:true

Indicates if a human should assign a grade.

Example:

true

​
status
enum<string>
default:pending

The status of the grade.

Available options:
pending,
error,
completed
Example:

"pending"

​
error_message
string | null

The error message if the grade was not created successfully.

Example:

"An error occurred while creating the grade."

​
created_at
string | null

when the grade was created.

Example:

"2025-02-06T23:05:50.132525"

​
updated_at
string | null

when the grade was last updated.

Example:

"2025-02-07T00:04:50.132584"

Was this page helpful?

Suggest editsRaise issue