Launch a bot machine — an agent plus the machine that runs it — or price one
Creates BOTH halves of a bot in one call and answers 201 with the bot: the cloud agent it runs, then a bot-kind machine bootstrapped with the bot runtime,…
POST /v1/visor/compute/bots/launch
| Address | https://api.hanzo.ai/v1/visor/compute/bots/launch |
| Method | POST |
| Operation | post_visor_compute_bots_launch |
| Auth | Authorization: Bearer $HANZO_API_KEY |
Creates BOTH halves of a bot in one call and answers 201 with the bot: the cloud agent it runs, then a bot-kind machine bootstrapped with the bot runtime, then the binding between them, so a launched bot is immediately messageable. Send dryRun: true for a price quote instead — 200 with the upstream quote verbatim, no agent created, no machine launched, nothing spent.
The agent is created FIRST and on purpose: it is create-if-absent (an agent that already exists is reused, so a relaunch is fine and several bots may share one explicit agent), and doing it before the machine means a bad request — a model that is not in the catalog, say — fails with the real reason BEFORE any metered machine is provisioned. agent defaults to the bot's name and an empty model takes the deployment default.
Org-scoped and fails closed: a validated principal is required (403 without one), the owning org is that principal's and never a body field, size is required (400), and name is required for a real launch though not for a quote.
Request
The document declares no body for POST /v1/visor/compute/bots/launch. The handler is typed in cloud but its shape is not yet emitted, so the fields are not listed here — ask the MCP door's describe for post_visor_compute_bots_launch, which answers from the running route.
Response
The document declares no response body for this operation. It answers 200 on success and the platform error shape on failure — see Errors.
Examples
hanzo has no subcommand for this operation — the CLI serves only what cloud's live route table confirms. Use HTTP or an SDK.
import { Configuration, VisorApi } from 'hanzoai';
const api = new VisorApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.postVisorComputeBotsLaunch();from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import VisorApi
client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = VisorApi(client).post_visor_compute_bots_launch()cfg := cloud.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := cloud.NewAPIClient(cfg)
resp, _, err := client.VisorAPI.PostVisorComputeBotsLaunch(context.Background()).Execute()
if err != nil {
return err
}use hanzo_cloud::apis::{configuration::Configuration, visor_api};
let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();
let result = visor_api::post_visor_compute_bots_launch(&cfg, Default::default()).await?;import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.VisorApi;
ApiClient client = new ApiClient();
client.setRequestInterceptor(b -> b.header("Authorization", "Bearer " + System.getenv("HANZO_API_KEY")));
var result = new VisorApi(client).postVisorComputeBotsLaunch();The method above is the one at the current release of the document. [email protected] (npm) and [email protected] (PyPI) were generated from an earlier release, where this operation carried a different id, so it spells the method differently — regenerating the clients is what makes the two agree. SDKs →
curl -X POST https://api.hanzo.ai/v1/visor/compute/bots/launch \
-H "Authorization: Bearer $HANZO_API_KEY"The door reaches visor through the visor tool, which names its 34 operations with its own verbs — this one among them, under a name only the door 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_compute_regions"
}
}
}'How is this guide?