Studio
Hanzo Studio's workflow backend: every creation — an image, a poster, a document, a deck, a type system, a 3D model, an ad, a film, a voice, a song — is a run of a graph of steps that the person who started it owns.
Also for this capability: API · CLI · MCP · SDKs
Hanzo Studio's workflow backend: every creation — an image, a poster, a document, a deck, a type system, a 3D model, an ad, a film, a voice, a song — is a run of a graph of steps that the person who started it owns.
| Base URL | https://api.hanzo.ai |
| Operations | 34 |
| Auth | Authorization: Bearer $HANZO_API_KEY |
Specification
Specification pending — no HIP in hanzoai/hips declares capability: studio yet. What this capability serves is below, from the API document; what it is — the store it owns, how it meters, what it publishes — is written as a HIP under HIP-0139.
Four surfaces
| Surface | Reaches this capability as | Coverage |
|---|---|---|
| REST | studio at its own prefix | 34 operations |
| CLI | hanzo studio … | 34 of 34 |
| SDK | StudioApi in every published client | 34 methods |
| MCP | tool studio on https://api.hanzo.ai/v1/mcp | 32 operations, 1 under the document's own id — ask describe for the rest |
Quickstart
export HANZO_API_KEY=sk-... # console.hanzo.ai → API keysThen the first call — a read that needs nothing but the key. GET /v1/studio/gpus, operation get_studio_gpus:
hanzo studio gpusimport { Configuration, StudioApi } from 'hanzoai';
const api = new StudioApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.getStudioGpus();from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import StudioApi
client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = StudioApi(client).get_studio_gpus()cfg := hanzoai.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := hanzoai.NewAPIClient(cfg)
resp, _, err := client.StudioAPI.GetStudioGpus(context.Background()).Execute()
if err != nil {
return err
}use hanzo_client::apis::{configuration::Configuration, studio_api};
let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();
let result = studio_api::get_studio_gpus(&cfg, Default::default()).await?;import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.StudioApi;
ApiClient client = new ApiClient();
client.setBearerToken(System.getenv("HANZO_API_KEY"));
var result = new StudioApi(client).getStudioGpus();curl https://api.hanzo.ai/v1/studio/gpus \
-H "Authorization: Bearer $HANZO_API_KEY"Tool studio, op get_studio_gpus — POST the JSON-RPC envelope to https://api.hanzo.ai/v1/mcp.
curl -X POST https://api.hanzo.ai/v1/mcp \
-H "Authorization: Bearer $HANZO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "studio",
"arguments": {
"op": "get_studio_gpus",
"input": {}
}
}
}'Answers 200 with object — ok.
Endpoints
| Endpoint | What it does |
|---|---|
GET /v1/studio/brands/{id} | Reads one brand you may read. |
PATCH /v1/studio/brands/{id} | Changes one of your brands; absent fields stay as they are. |
DELETE /v1/studio/brands/{id} | Deletes one of your brands. |
GET /v1/studio/brands | Lists the brands you may read — palettes and type systems as design tokens. |
POST /v1/studio/brands | Saves a brand: its tokens in the W3C design-token format (color, font, type, space, radius groups) and up to 16 logo items. |
POST /v1/studio/chat | One chat turn that plans and launches runs, streamed |
GET /v1/studio/documents/{id} | Reads one document you may read. |
PATCH /v1/studio/documents/{id} | Changes one of your documents; absent fields stay as they are. |
DELETE /v1/studio/documents/{id} | Deletes one of your documents. |
GET /v1/studio/documents | Lists the documents and decks you may read, most recently changed first. |
POST /v1/studio/documents | Writes a document (kind doc, its IR blocks) or a deck (kind deck, its slides). |
POST /v1/studio/estimate | Prices a run without starting it: the estimate POST /v1/studio/runs would reserve, step by step. |
GET /v1/studio/flows/{id} | Reads one flow you may read. |
PATCH /v1/studio/flows/{id} | Changes one of your flows; absent fields stay as they are. |
DELETE /v1/studio/flows/{id} | Deletes one of your flows. |
GET /v1/studio/flows | Lists the flows you may read, most recently changed first. |
POST /v1/studio/flows | Saves a graph as a flow of yours. |
GET /v1/studio/gpus | Lists the GPUs your org has linked with hanzo link that can take a studio.render step, each with whether it is free now. |
POST /v1/studio/runs/{id}/cancel | Cancels one of your runs: a step in flight is told to stop, nothing new starts, and the reservation settles to what finished steps cost. |
GET /v1/studio/runs/{id}/events | Stream a run's progress as Server-Sent Events |
POST /v1/studio/runs/{id}/retry | Resumes one of your runs that failed or was cancelled: the steps that did not succeed run again in the same run, and the steps that did keep their outputs and are neither run nor charged again. |
GET /v1/studio/runs/{id}/versions | Lists every version of a creation you may read — the runs in this run's lineage — oldest (version 1) first. |
GET /v1/studio/runs/{id} | Reads one run: its graph, its input, every step's state, the assets it made and what it cost. |
PATCH /v1/studio/runs/{id} | Renames or shares one of your runs. |
GET /v1/studio/runs | Lists the runs you may read — your own and those your org shares — newest first. |
POST /v1/studio/runs | Starts a run: name exactly one of template, flow or graph, with the input its inputs schema asks for. |
GET /v1/studio/templates/{id} | Reads one template: a catalog slug or one of your org's templates you may read. |
PATCH /v1/studio/templates/{id} | Changes one of your templates; absent fields stay as they are. |
DELETE /v1/studio/templates/{id} | Deletes one of your templates. |
GET /v1/studio/templates | Lists templates: the public catalog (org empty) first, then your org's own that you may read. |
POST /v1/studio/templates | Saves a template to your org: a graph and the inputs schema its runs are started with. |
GET /v1/studio/threads/{id} | Reads one of your threads and its messages, oldest first. |
DELETE /v1/studio/threads/{id} | Deletes one of your threads. |
GET /v1/studio/threads | Lists your chat threads, most recent first. |