Skip to main content
POST
/
v1
/
evals
/
runs
Create Eval Run
curl --request POST \
  --url https://api.bland.ai/v1/evals/runs \
  --header 'Content-Type: application/json' \
  --header 'authorization: <authorization>' \
  --data '
{
  "call_ids": {},
  "attached_agents": {
    "eval_agent_id": "<string>",
    "eval_agent_version_id": "<string>",
    "weight": 123,
    "target_level_keys": {}
  },
  "run_mode": "<string>",
  "pass_threshold_pct": 123,
  "workbench_setup_id": "<string>",
  "workbench_setup_version_id": "<string>",
  "triggered_by": "<string>",
  "metadata": {}
}
'
import requests

url = "https://api.bland.ai/v1/evals/runs"

payload = {
"call_ids": {},
"attached_agents": {
"eval_agent_id": "<string>",
"eval_agent_version_id": "<string>",
"weight": 123,
"target_level_keys": {}
},
"run_mode": "<string>",
"pass_threshold_pct": 123,
"workbench_setup_id": "<string>",
"workbench_setup_version_id": "<string>",
"triggered_by": "<string>",
"metadata": {}
}
headers = {
"authorization": "<authorization>",
"Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)
const options = {
method: 'POST',
headers: {authorization: '<authorization>', 'Content-Type': 'application/json'},
body: JSON.stringify({
call_ids: {},
attached_agents: {
eval_agent_id: '<string>',
eval_agent_version_id: '<string>',
weight: 123,
target_level_keys: {}
},
run_mode: '<string>',
pass_threshold_pct: 123,
workbench_setup_id: '<string>',
workbench_setup_version_id: '<string>',
triggered_by: '<string>',
metadata: {}
})
};

fetch('https://api.bland.ai/v1/evals/runs', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));
<?php

$curl = curl_init();

curl_setopt_array($curl, [
CURLOPT_URL => "https://api.bland.ai/v1/evals/runs",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'call_ids' => [

],
'attached_agents' => [
'eval_agent_id' => '<string>',
'eval_agent_version_id' => '<string>',
'weight' => 123,
'target_level_keys' => [

]
],
'run_mode' => '<string>',
'pass_threshold_pct' => 123,
'workbench_setup_id' => '<string>',
'workbench_setup_version_id' => '<string>',
'triggered_by' => '<string>',
'metadata' => [

]
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"authorization: <authorization>"
],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}
package main

import (
"fmt"
"strings"
"net/http"
"io"
)

func main() {

url := "https://api.bland.ai/v1/evals/runs"

payload := strings.NewReader("{\n \"call_ids\": {},\n \"attached_agents\": {\n \"eval_agent_id\": \"<string>\",\n \"eval_agent_version_id\": \"<string>\",\n \"weight\": 123,\n \"target_level_keys\": {}\n },\n \"run_mode\": \"<string>\",\n \"pass_threshold_pct\": 123,\n \"workbench_setup_id\": \"<string>\",\n \"workbench_setup_version_id\": \"<string>\",\n \"triggered_by\": \"<string>\",\n \"metadata\": {}\n}")

req, _ := http.NewRequest("POST", url, payload)

req.Header.Add("authorization", "<authorization>")
req.Header.Add("Content-Type", "application/json")

res, _ := http.DefaultClient.Do(req)

defer res.Body.Close()
body, _ := io.ReadAll(res.Body)

fmt.Println(string(body))

}
HttpResponse<String> response = Unirest.post("https://api.bland.ai/v1/evals/runs")
.header("authorization", "<authorization>")
.header("Content-Type", "application/json")
.body("{\n \"call_ids\": {},\n \"attached_agents\": {\n \"eval_agent_id\": \"<string>\",\n \"eval_agent_version_id\": \"<string>\",\n \"weight\": 123,\n \"target_level_keys\": {}\n },\n \"run_mode\": \"<string>\",\n \"pass_threshold_pct\": 123,\n \"workbench_setup_id\": \"<string>\",\n \"workbench_setup_version_id\": \"<string>\",\n \"triggered_by\": \"<string>\",\n \"metadata\": {}\n}")
.asString();
require 'uri'
require 'net/http'

url = URI("https://api.bland.ai/v1/evals/runs")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["authorization"] = '<authorization>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"call_ids\": {},\n \"attached_agents\": {\n \"eval_agent_id\": \"<string>\",\n \"eval_agent_version_id\": \"<string>\",\n \"weight\": 123,\n \"target_level_keys\": {}\n },\n \"run_mode\": \"<string>\",\n \"pass_threshold_pct\": 123,\n \"workbench_setup_id\": \"<string>\",\n \"workbench_setup_version_id\": \"<string>\",\n \"triggered_by\": \"<string>\",\n \"metadata\": {}\n}"

response = http.request(request)
puts response.read_body
{
  "data": {
    "id": "e5f6a7b8-c9d0-1234-efab-345678901234",
    "org_id": "f6a7b8c9-d0e1-2345-fabc-456789012345",
    "status": "PENDING",
    "triggered_by": "manual",
    "run_mode": "text",
    "submitted_call_ids": [
      "a1b2c3d4-0000-0000-0000-000000000001",
      "a1b2c3d4-0000-0000-0000-000000000002"
    ],
    "submitted_attached_agents": [
      {
        "eval_agent_id": "11111111-aaaa-bbbb-cccc-dddddddddddd",
        "eval_agent_version_id": "22222222-aaaa-bbbb-cccc-dddddddddddd",
        "weight": 100,
        "target_level_keys": ["pass"]
      }
    ],
    "workbench_setup_id": null,
    "workbench_setup_version_id": null,
    "resolved_call_count": 2,
    "resolved_agent_count": 1,
    "resolved_atom_count": 2,
    "completed_atom_count": 0,
    "summary": null,
    "billable_cost_usd": null,
    "error_code": null,
    "error_message": null,
    "workflow_id": null,
    "metadata": {},
    "created_at": "2026-05-27T10:00:00.000Z",
    "started_at": null,
    "completed_at": null
  },
  "errors": null
}

Headers

authorization
string
required
Your API key for authentication.

Body Parameters

call_ids
array of string
required
The call IDs to score. Between 1 and 5000 calls.
attached_agents
array of objects
The eval agents to score with. Maximum 50 agents. Each object:
run_mode
string
The scoring modality. One of text, audio, or full. Defaults to text.
pass_threshold_pct
number
Percentage of evaluations that must pass for the run to be marked passing overall, 0-100. Omit to run without a threshold.
workbench_setup_id
string
UUID of a workbench setup to associate with this run. Must be provided together with workbench_setup_version_id.
workbench_setup_version_id
string
UUID of the pinned workbench setup version. The version’s agent roster is used when attached_agents is omitted. Must be provided together with workbench_setup_id.
triggered_by
string
How this run was initiated. One of manual, auto, or backfill. Defaults to manual.
metadata
object
Key-value metadata to attach to the run. Keys and values must be strings.
You must supply either a non-empty attached_agents array or a workbench_setup_version_id (whose pinned roster supplies the agents). If you provide workbench_setup_id or workbench_setup_version_id, both fields are required together. A valid billing record must be on file before a run can start.

Response

id
string
Unique identifier for the newly created eval run.
org_id
string
The organization that owns this run.
status
string
Initial status of the run. Will be PENDING immediately after creation.
triggered_by
string
How the run was triggered.
run_mode
string
The scoring modality for this run.
submitted_call_ids
array of string
The call IDs submitted for scoring.
submitted_attached_agents
array of objects
The agent attachments submitted with the run. Each object contains eval_agent_id, eval_agent_version_id, weight, and target_level_keys.
workbench_setup_id
string or null
The associated workbench setup, if provided.
workbench_setup_version_id
string or null
The pinned workbench setup version, if provided.
resolved_call_count
integer
Number of calls resolved for the run.
resolved_agent_count
integer
Number of eval agents resolved for the run.
resolved_atom_count
integer
Total call-by-agent evaluations to perform.
completed_atom_count
integer
Number of evaluations completed so far.
summary
null
Always null at creation time.
billable_cost_usd
null
Always null at creation time.
error_code
string or null
Error code if the run failed, otherwise null.
error_message
string or null
Human-readable error message if the run failed, otherwise null.
workflow_id
string or null
Internal workflow identifier, if applicable.
metadata
object
Key-value metadata attached to the run.
created_at
string
ISO 8601 timestamp when the run was created.
started_at
null
Always null at creation time.
completed_at
null
Always null at creation time.
{
  "data": {
    "id": "e5f6a7b8-c9d0-1234-efab-345678901234",
    "org_id": "f6a7b8c9-d0e1-2345-fabc-456789012345",
    "status": "PENDING",
    "triggered_by": "manual",
    "run_mode": "text",
    "submitted_call_ids": [
      "a1b2c3d4-0000-0000-0000-000000000001",
      "a1b2c3d4-0000-0000-0000-000000000002"
    ],
    "submitted_attached_agents": [
      {
        "eval_agent_id": "11111111-aaaa-bbbb-cccc-dddddddddddd",
        "eval_agent_version_id": "22222222-aaaa-bbbb-cccc-dddddddddddd",
        "weight": 100,
        "target_level_keys": ["pass"]
      }
    ],
    "workbench_setup_id": null,
    "workbench_setup_version_id": null,
    "resolved_call_count": 2,
    "resolved_agent_count": 1,
    "resolved_atom_count": 2,
    "completed_atom_count": 0,
    "summary": null,
    "billable_cost_usd": null,
    "error_code": null,
    "error_message": null,
    "workflow_id": null,
    "metadata": {},
    "created_at": "2026-05-27T10:00:00.000Z",
    "started_at": null,
    "completed_at": null
  },
  "errors": null
}