Create sample
Decodes from the client's current weights.
POST /v1/train/clients/{id}/sample
| Address | https://api.hanzo.ai/v1/train/clients/{id}/sample |
| Method | POST |
| Operation | post_train_clients_by_id_sample |
| Auth | Authorization: Bearer $HANZO_API_KEY |
Decodes from the client's current weights.
Request
6 fields, body application/json (required).
| Field | In | Type | Required | Description |
|---|---|---|---|---|
id | path | string | yes | ID names the client. |
id | body | string | — | ID names the client. |
num_samples | body | integer (int64) | — | NumSamples is how many sequences to decode. |
prompt | body | string | — | Prompt is a text prompt; exactly one of prompt and tokens. |
sampling_params | body | any | — | SamplingParams are the decoding parameters. |
tokens | body | integer (uint32)[] | — | Tokens is a tokenized prompt. |
Response
| Status | Body | Meaning |
|---|---|---|
200 | ok | |
default | problem-details | refused |
200 body — 1 field.
| Field | In | Type | Always | Description |
|---|---|---|---|---|
(body) | body | any | yes |
Failure carries the platform error shape — see Errors.
Examples
CLI
SDK
HTTP
MCP
hanzo has no subcommand for this operation — the CLI serves only what cloud's live route table confirms. Use HTTP or an SDK.
.ts
.py
.go
.rs
.java
import { Configuration, TrainApi } from 'hanzoai';
const api = new TrainApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.postTrainClientsByIdSample({ id: 'id', id: "<id>", num_samples: 0 });from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import TrainApi
client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = TrainApi(client).post_train_clients_by_id_sample(id='id', id="<id>", num_samples=0)cfg := hanzoai.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := hanzoai.NewAPIClient(cfg)
resp, _, err := client.TrainAPI.PostTrainClientsByIdSample(context.Background()).Execute()
if err != nil {
return err
}use hanzo_client::apis::{configuration::Configuration, train_api};
let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();
let result = train_api::post_train_clients_by_id_sample(&cfg, Default::default()).await?;import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.TrainApi;
ApiClient client = new ApiClient();
client.setBearerToken(System.getenv("HANZO_API_KEY"));
var result = new TrainApi(client).postTrainClientsByIdSample();curl -X POST https://api.hanzo.ai/v1/train/clients/<id>/sample \
-H "Authorization: Bearer $HANZO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"id": "<id>",
"num_samples": 0
}'MCP declares no tool for train — tools/list on https://api.hanzo.ai/v1/mcp names the products it does reach. Use HTTP or an SDK.
Was this page useful?