Skip to main content
POST
/
evaluations
/
trace-runs
/
batch
Create Batch Eval Run
curl --request POST \
  --url https://api.pandaprobe.com/evaluations/trace-runs/batch \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "trace_ids": [
    "3c90c3cc-0d44-4b50-8888-8dd25736052a"
  ],
  "metrics": [
    "<string>"
  ]
}
'
{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "name": "<string>",
  "metric_names": [
    "<string>"
  ],
  "total_traces": 123,
  "evaluated_count": 123,
  "failed_count": 123,
  "created_at": "<string>",
  "completed_at": "<string>",
  "project_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "target_type": "<string>",
  "filters": {},
  "sampling_rate": 123,
  "model": "<string>",
  "monitor_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "error_message": "<string>"
}

Documentation Index

Fetch the complete documentation index at: https://docs.pandaprobe.com/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

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

Body

application/json

Create an eval run for an explicit list of trace IDs.

Use this when the user has manually selected specific traces in the dashboard rather than using filter-based selection.

​
trace_ids
string<uuid>[]
required

List of trace UUIDs to evaluate. Duplicates are removed automatically.

Minimum array length: 1
​
metrics
string[]
required

List of metric names to run on each trace. Example: ['task_completion', 'step_efficiency'].

Minimum array length: 1
​
name
string | null

Optional human-readable label for this run.

​
model
string | null

LLM model string override for the judge. Null uses the system default.

Response

Successful Response

Full eval run representation used by both list and detail endpoints.

​
id
string<uuid>
required
​
name
string | null
required
​
status
enum<string>
required

Lifecycle status of an evaluation job.

Available options:
PENDING,
RUNNING,
COMPLETED,
FAILED
​
metric_names
string[]
required
​
total_traces
integer
required
​
evaluated_count
integer
required
​
failed_count
integer
required
​
created_at
string
required
​
completed_at
string | null
required
​
project_id
string<uuid>
required
​
target_type
string
required
​
filters
Filters · object
required
​
sampling_rate
number
required
​
model
string | null
required
​
monitor_id
string<uuid> | null
required
​
error_message
string | null
required