Report batch evaluation results

import requests

url = "https://app.langwatch.ai/api/v1/evaluations/batch/log_results"

payload = {
    "run_id": "<string>",
    "dataset": [
        {
            "index": 123,
            "entry": {},
            "target_id": "<string>",
            "predicted": {},
            "cost": 123,
            "duration": 123,
            "error": "<string>",
            "trace_id": "<string>"
        }
    ],
    "evaluations": [
        {
            "evaluator": "<string>",
            "status": "processed",
            "index": 123,
            "name": "<string>",
            "target_id": "<string>",
            "duration": 123,
            "inputs": {},
            "score": 123,
            "label": "<string>",
            "passed": True,
            "details": "<string>",
            "cost": 123
        }
    ],
    "name": "<string>"
}
headers = {
    "X-Auth-Token": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'X-Auth-Token': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    run_id: '<string>',
    dataset: [
      {
        index: 123,
        entry: {},
        target_id: '<string>',
        predicted: {},
        cost: 123,
        duration: 123,
        error: '<string>',
        trace_id: '<string>'
      }
    ],
    evaluations: [
      {
        evaluator: '<string>',
        status: 'processed',
        index: 123,
        name: '<string>',
        target_id: '<string>',
        duration: 123,
        inputs: {},
        score: 123,
        label: '<string>',
        passed: true,
        details: '<string>',
        cost: 123
      }
    ],
    name: '<string>'
  })
};

fetch('https://app.langwatch.ai/api/v1/evaluations/batch/log_results', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

curl --request POST \
  --url https://app.langwatch.ai/api/v1/evaluations/batch/log_results \
  --header 'Content-Type: application/json' \
  --header 'X-Auth-Token: <api-key>' \
  --data '
{
  "run_id": "<string>",
  "dataset": [
    {
      "index": 123,
      "entry": {},
      "target_id": "<string>",
      "predicted": {},
      "cost": 123,
      "duration": 123,
      "error": "<string>",
      "trace_id": "<string>"
    }
  ],
  "evaluations": [
    {
      "evaluator": "<string>",
      "status": "processed",
      "index": 123,
      "name": "<string>",
      "target_id": "<string>",
      "duration": 123,
      "inputs": {},
      "score": 123,
      "label": "<string>",
      "passed": true,
      "details": "<string>",
      "cost": 123
    }
  ],
  "name": "<string>"
}
'

{
  "message": "<string>"
}

{
  "message": "<string>",
  "error": "<string>"
}

{
  "error": "<string>",
  "kind": "<string>",
  "meta": {}
}

{
  "error": "<string>",
  "kind": "<string>",
  "meta": {}
}

This response has no body data.

Evaluations

Report batch evaluation results

Report the rows of a batch evaluation against an experiment, so its scores and progress show up in the app. This is the second half of an SDK batch evaluation: create the experiment with POST /api/experiment/init, then post rows here as they finish. Identify the experiment by either experiment_id or experiment_slug. Bodies up to 267 MB are accepted, sized for one dataset row with ten 20 MB images inline. A larger body is refused with evaluation_log_results_too_large.

POST

api

evaluations

batch

log_results

Report batch evaluation results

import requests

url = "https://app.langwatch.ai/api/v1/evaluations/batch/log_results"

payload = {
    "run_id": "<string>",
    "dataset": [
        {
            "index": 123,
            "entry": {},
            "target_id": "<string>",
            "predicted": {},
            "cost": 123,
            "duration": 123,
            "error": "<string>",
            "trace_id": "<string>"
        }
    ],
    "evaluations": [
        {
            "evaluator": "<string>",
            "status": "processed",
            "index": 123,
            "name": "<string>",
            "target_id": "<string>",
            "duration": 123,
            "inputs": {},
            "score": 123,
            "label": "<string>",
            "passed": True,
            "details": "<string>",
            "cost": 123
        }
    ],
    "name": "<string>"
}
headers = {
    "X-Auth-Token": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'X-Auth-Token': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    run_id: '<string>',
    dataset: [
      {
        index: 123,
        entry: {},
        target_id: '<string>',
        predicted: {},
        cost: 123,
        duration: 123,
        error: '<string>',
        trace_id: '<string>'
      }
    ],
    evaluations: [
      {
        evaluator: '<string>',
        status: 'processed',
        index: 123,
        name: '<string>',
        target_id: '<string>',
        duration: 123,
        inputs: {},
        score: 123,
        label: '<string>',
        passed: true,
        details: '<string>',
        cost: 123
      }
    ],
    name: '<string>'
  })
};

fetch('https://app.langwatch.ai/api/v1/evaluations/batch/log_results', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

curl --request POST \
  --url https://app.langwatch.ai/api/v1/evaluations/batch/log_results \
  --header 'Content-Type: application/json' \
  --header 'X-Auth-Token: <api-key>' \
  --data '
{
  "run_id": "<string>",
  "dataset": [
    {
      "index": 123,
      "entry": {},
      "target_id": "<string>",
      "predicted": {},
      "cost": 123,
      "duration": 123,
      "error": "<string>",
      "trace_id": "<string>"
    }
  ],
  "evaluations": [
    {
      "evaluator": "<string>",
      "status": "processed",
      "index": 123,
      "name": "<string>",
      "target_id": "<string>",
      "duration": 123,
      "inputs": {},
      "score": 123,
      "label": "<string>",
      "passed": true,
      "details": "<string>",
      "cost": 123
    }
  ],
  "name": "<string>"
}
'

{
  "message": "<string>"
}

{
  "message": "<string>",
  "error": "<string>"
}

{
  "error": "<string>",
  "kind": "<string>",
  "meta": {}
}

{
  "error": "<string>",
  "kind": "<string>",
  "meta": {}
}

This response has no body data.

Authorizations

X-Auth-Token

string

header

required

Project API key for sending traces and accessing project-scoped resources. Format: sk-lw-... (no underscore). Obtain one by creating a project via the Admin API or the LangWatch UI.

Body

application/json

run_id

string

required

workflow_version_id

string | null

progress

number | null

total

number | null

dataset

object[]

Show child attributes

evaluations

object[]

Show child attributes

experiment_id

string | null

experiment_slug

string | null

workflow_id

string | null

name

string | null

targets

object[] | null

Show child attributes

timestamps

object

Show child attributes

expected

object | null

Show child attributes

Response

The rows were recorded

message

string

required

Human-readable confirmation

Last modified on October 12, 2026