Run a kept eval set
Start a run of a kept eval set, or score the next cases of a run in progress, up to 10 at a time.
POST
/
assistants
/
{assistant_id}
/
eval-sets
/
{set_id}
/
runs
Run a kept eval set
curl --request POST \
--url https://app.mithunai.com/mithunai/api/v1/assistants/{assistant_id}/eval-sets/{set_id}/runs \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"run_id": "<string>"
}
'import requests
url = "https://app.mithunai.com/mithunai/api/v1/assistants/{assistant_id}/eval-sets/{set_id}/runs"
payload = { "run_id": "<string>" }
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({run_id: '<string>'})
};
fetch('https://app.mithunai.com/mithunai/api/v1/assistants/{assistant_id}/eval-sets/{set_id}/runs', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"id": "<string>",
"eval_set_id": "<string>",
"status": "<string>",
"problem": {},
"total": 123,
"scored": {},
"passed": 123,
"started_by": "<string>",
"started_at": "<string>",
"finished_at": {},
"results": [
{}
]
}Without
run_id this starts a run of the set. With one it scores that run’s next cases. Each call scores up to 10 cases exactly as an unstored eval does, and keeps them. Each case counts as one answer against your monthly allowance, and the call is audited as assistant.eval_run. Call again with the run’s id until status is no longer running. Requires the owner, admin or editor role.
Off by default. These routes answer
404 unless the deployment has switched on
ARUKZ_EVAL_HISTORY. See Answer quality
evals.string
required
The assistant (UUID). Another organization’s assistant returns
404.string
required
The kept set to run. One that does not exist returns
404.string
The run to continue, at most 64 characters. Absent starts a new run. A run that is already
finished returns
409.Response
The run so far, with every case scored.string
required
The run.
string
required
The set it ran.
string
required
running, done or cannot_run. Treat a value you do not recognise as cannot_run.string | null
required
Why it stopped, when it did.
integer
required
Cases in the set.
integer | null
required
Cases scored so far.
integer
required
Cases that passed.
string
required
Who started it.
string
required
When, RFC 3339.
string | null
required
When it finished, or
null while it is running.object[]
required
Each scored case, in order, as in Run an eval.
Last modified on November 11, 2026
Run a kept eval set
curl --request POST \
--url https://app.mithunai.com/mithunai/api/v1/assistants/{assistant_id}/eval-sets/{set_id}/runs \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"run_id": "<string>"
}
'import requests
url = "https://app.mithunai.com/mithunai/api/v1/assistants/{assistant_id}/eval-sets/{set_id}/runs"
payload = { "run_id": "<string>" }
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({run_id: '<string>'})
};
fetch('https://app.mithunai.com/mithunai/api/v1/assistants/{assistant_id}/eval-sets/{set_id}/runs', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"id": "<string>",
"eval_set_id": "<string>",
"status": "<string>",
"problem": {},
"total": 123,
"scored": {},
"passed": 123,
"started_by": "<string>",
"started_at": "<string>",
"finished_at": {},
"results": [
{}
]
}