Create items

Writes one graded example — its input, its expected output, free-form metadata and a status — into the dataset named in the path, and answers 201 with it.

POST /v1/eval/datasets/{name}/items

Eval → · All API references → · Get started →

Address	`https://api.hanzo.ai/v1/eval/datasets/{name}/items`
Method	`POST`
Operation	`post_eval_datasets_by_name_items`
Auth	`Authorization: Bearer $HANZO_API_KEY`

Writes one graded example — its input, its expected output, free-form metadata and a status — into the dataset named in the path, and answers 201 with it.

That dataset MUST already exist for this org: an unknown one is 404, never a silent create. Requires a validated principal; 401 without one.

Request

7 fields, body application/json (required).

Field	In	Type	Required	Description
`name`	path	string	yes
`expectedOutput`	body	any	—	Expected is the answer a correct model produces, which the judge grades against, stored as raw JSON exactly as sent, up to 64 KiB.
`id`	body	string	—	ID makes the write idempotent — re-posting the same id replaces that example in place.
`input`	body	any	—	Input is what the model under test will be given, stored as raw JSON exactly as sent, up to 64 KiB.
`metadata`	body	object	—	Metadata is a free-form object stored with the example.
`metadata.*`	body	any	—
`status`	body	string	—	Status is ACTIVE (the default) or ARCHIVED.

Response

Status	Body	Meaning
`201`	eval.itemView	created
`default`	problem-details	refused

201 body — 9 fields.

Field	In	Type	Always	Description
`createdAt`	body	string	—	CreatedAt is when the example was first written.
`datasetName`	body	string	—	Dataset is the set this example belongs to.
`expectedOutput`	body	any	—	Expected is the answer a correct model produces, which the judge grades against.
`id`	body	string	—	ID is the example's handle, unique within the caller's org.
`input`	body	any	—	Input is what the model under test is given, as it was written.
`metadata`	body	object	—	Metadata is the free-form object stored with the example.
`metadata.*`	body	any	—
`status`	body	string	—	Status is ACTIVE or ARCHIVED.
`updatedAt`	body	string	—	UpdatedAt is when it last changed.

Failure carries the platform error shape — see Errors.

Examples

CLI

SDK

HTTP

MCP

hanzo eval datasets items create <name>

.ts

.py

.go

.rs

.java

import { Configuration, EvalApi } from 'hanzoai';

const api = new EvalApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.postEvalDatasetsByNameItems({ name: 'name', expectedOutput: "<expectedOutput>", id: "<id>" });

from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import EvalApi

client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = EvalApi(client).post_eval_datasets_by_name_items(name='name', expected_output="<expectedOutput>", id="<id>")

cfg := hanzoai.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := hanzoai.NewAPIClient(cfg)

resp, _, err := client.EvalAPI.PostEvalDatasetsByNameItems(context.Background()).Execute()
if err != nil {
	return err
}

use hanzo_client::apis::{configuration::Configuration, eval_api};

let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();

let result = eval_api::post_eval_datasets_by_name_items(&cfg, Default::default()).await?;

import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.EvalApi;

ApiClient client = new ApiClient();
client.setBearerToken(System.getenv("HANZO_API_KEY"));

var result = new EvalApi(client).postEvalDatasetsByNameItems();

curl -X POST https://api.hanzo.ai/v1/eval/datasets/<name>/items \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
       "expectedOutput": "<expectedOutput>",
       "id": "<id>"
     }'

MCP reaches eval through the eval tool, which names its 16 operations with its own verbs — this one among them, under a name only MCP declares. describe explains any of them:

curl -X POST https://api.hanzo.ai/v1/mcp \
  -H "Content-Type: application/json" \
  -d '{
       "jsonrpc": "2.0",
       "id": 1,
       "method": "tools/call",
       "params": {
         "name": "describe",
         "arguments": {
           "op": "list_eval_datasets"
         }
       }
     }'

Eval API · All Hanzo APIs · Interactive reference

Was this page useful?

PreviousList traces NextCreate datasets