Skip to main content
POST
/
eval-runs
{
  "id": "f2b2d72f-e9e2-4f0e-8810-0a7e1ff58614",
  "agent_id": "basic-agent",
  "model_id": "gpt-4o",
  "model_provider": "OpenAI",
  "eval_type": "reliability",
  "eval_data": {
    "eval_status": "PASSED",
    "failed_tool_calls": [],
    "passed_tool_calls": [
      "multiply"
    ]
  },
  "created_at": "2025-08-27T15:41:59Z",
  "updated_at": "2025-08-27T15:41:59Z"
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Query Parameters

​
db_id
string | null

Database ID to use for evaluation

Body

application/json
​
eval_type
enum<string>
required
Available options:
accuracy,
performance,
reliability
​
input
string
required
​
agent_id
string | null
​
team_id
string | null
​
model_id
string | null
​
model_provider
string | null
​
additional_guidelines
string | null
​
additional_context
string | null
​
num_iterations
integer | null
default:1
​
name
string | null
​
expected_output
string | null
​
warmup_runs
integer | null
default:0
​
expected_tool_calls
string[] | null

Response

Evaluation executed successfully

​
id
string
required
​
eval_type
enum<string>
required
Available options:
accuracy,
performance,
reliability
​
eval_data
object
required
​
agent_id
string | null
​
model_id
string | null
​
model_provider
string | null
​
team_id
string | null
​
workflow_id
string | null
​
name
string | null
​
evaluated_component_name
string | null
​
eval_input
object | null
​
created_at
string<date-time> | null
​
updated_at
string<date-time> | null